record_id,doi,title,year,venue,authors,abstract,citations,oa_pdf
3fff47f2ad1427c42ba357bc9b2363011924b07a,10.1007/s10258-026-00295-2,Short-term rentals and the housing market: evidence from Portuguese metropolitan areas,2026.0,Portuguese Economic Journal,Francisco Nobre; Diogo Jardim Gonçalves; Ronize Cruz,"
 In this paper, we study the impact of short-term rentals (STR) on housing markets in Portugal, exploiting a 2014 policy reform that eased registration requirements. Using a novel dataset of property transactions from 2010 to 2017 for the Lisbon and Porto metropolitan areas, we estimate the effect of STR expansion using a two-way fixed effects model and a difference-in-differences design that leverages staggered treatment across postcodes. The analysis controls for detailed property characteristics, location and time fixed effects. We find that each additional STR per quarter and postcode raises transaction values by 2.3–6.0%, representing an average increase of €104–€329 per transaction. Effects are larger in higher-end market segments and in parishes with lower unemployment and population density. Event-study estimates show that effects emerge gradually and become significant around ten quarters after the first STR listing. We also find positive spillovers to commercial property values, particularly for retail stores, and in suggesting short-term rentals drive demand for local consumption amenities.",0.0,https://link.springer.com/content/pdf/10.1007/s10258-026-00295-2.pdf
af684e77f7935d3f17a14670aa47f90ea14c588f,10.1080/13549839.2025.2593237,"Assessing equity in visual landscape quality toward a “15-minute living circle” in Binjiang, Hangzhou: using deep learning and image recognition",2026.0,Local Environment : the International Journal of Justice and Sustainability,Ruoxi Zhao; Xiaohua Wu; Lin-Ke Li; Ang-Yang Li; Jun Ying,"ABSTRACT In the process of promoting the construction of livable cities, visual landscape quality (LVQ) has gradually become an important indicator of urban livability. However, there are significant imbalances in visual landscape quality among different communities due to differences in economic, policy and other factors, and this variability has triggered public concern about its fairness. An in-depth assessment of the equity of visual landscape quality can help provide strong theoretical support and practical guidance for the scientific allocation of landscape resources. This study aims to assess the fairness of the visual landscape quality of the community living circle, for which a fairness assessment framework is constructed, which integrates the visual landscape quality, deep learning and image recognition, spatial statistical analysis, and community house price big data, to conduct a community-level visual landscape for the “15-minute living circle” in the Binjiang District of Hangzhou as an example of the quality fairness assessment. The results show that there is a obvious inequity in visual landscape quality between residential neighbourhoods, with the Riverside South St",0.0,
70b9c8932989bec9b5f5cfe4e079c51d8a3bf360,10.21685/2072-3059-2025-3-2,Estimation of parameters for a cluster-based piecewise linear risk regression function,2025.0,University proceedings Volga region Technical sciences,S. Noskov; Aleksandra R. Chekalova; S. Belyaev,"Background. The article notes that cluster regression models are highly effective in studying various aspects of the analyzed objects’ functioning, including those related to risk. In particular, the following risk analysis problems are considered: country risk, software project risk, failure risk in urban pipeline networks, groundwater contamination risk, building fire risk, flood risk, and loan default risk. The objective of this work is to develop an algorithmic method for identifying the parameters of a cluster-based piecewise linear risk function. Results. A cluster-based piecewise linear risk function has been constructed for housing prices in the regions of the Siberian Federal District. Independent variables include the prices of bricks, cement, and edged boards. The model demonstrates high approximation accuracy, with an average percentage error of 0.4. Conclusions. The problem of estimating unknown parameters of a cluster-based piecewise linear risk function, with the loss function defined as the sum of absolute approximation errors, has been reduced to a linear Boolean programming problem.",0.0,https://doi.org/10.21685/2072-3059-2025-3-2
627ac9d0af8bbf8d26a14b2f22b5da9f36d7d45e,10.1007/s00168-020-00986-4,The effect of bank branch closures on new firm formation: the Swedish case,2020.0,The annals of regional science,Cynthia Sin Tian Ho; B. Berggren,"In this paper, the effect of local bank branch closures on new firm formation in Sweden is analysed using a panel database that captures the geographical locations of all Swedish bank branches in 2007 and 2013. The previous research has shown that the further a firm is located away from the bank, the higher the monitoring costs will be for the banks. Furthermore, an increase in the distance to the banks will also increase information asymmetry because of the banks’ eroded ability to collect and analyse soft information. Due to the high risks associated with the lack of information and uncertainty, banks might not be as willing to extend credits to a distant firm compared to a nearby firm. Using spatial econometric analysis at a municipal level, it is shown that bank proximity to firms, unemployment rate, industry structures, income growth, change in housing price and percentage of immigrants are vital for new firm formation in Sweden. From the spatial Durbin model with fixed effects, an increase in the weighted distance to the nearest bank branches is shown to affect new firm formation negatively.",0.0,https://link.springer.com/content/pdf/10.1007/s00168-020-00986-4.pdf
5dba62e533b62357cc2b8976a5a95cf8748fdfa2,10.1109/iscon65210.2025.11341107,Predictive Analytics of Housing Markets Using Random Forests and Multidimensional Urban Indicators,2025.0,2025 7th International Conference on Information Systems and Computer Networks (ISCON),Sanjay Oli; Z. Mamadiyarov; Somesh Sharma; J. Yuldoshev; Temur Eshchanov; Siddharth Joshi,"In the past few years, the housing market in rapidly urbanizing regions such as Uttarakhand has seen significant change due to increased infrastructure spending and shifts in urban development policies. Accurate forecasting of house prices matters not only for future homebuyers and investors but also for city planners and government authorities attempting to provide sustainable development. This research study sets forth an integrated machine learning-based model based on Random Forest Regression in order to predict and model the prices of housing in four key cities of Uttarakhand, namely Dehradun, Haridwar, Haldwani, and Rudrapur. The study begins with the collection of relevant datasets that include variables such as historical housing prices, investment in infrastructure, and urban development indicators. Next is data preprocessing and feature selection, followed by training and validation of Random Forest models using MATLAB. The simulation results indicate that the models perform optimally in all the cities, with the lowest Root Mean Squared Error (RMSE) in Dehradun (10.869), implying a higher degree of uniformity in the housing market of the capital city. Visual inspection of",0.0,
8ec68ee17a6327d0220531303c49f28beae75aa3,10.5220/0012832700004547,House Price Prediction and Feature Analysis Based on Multilayer Perceptron (MLP),2024.0,Proceedings of the 1st International Conference on Data Science and Engineering,Mingwei Xu,": Within the ever-changing real estate sector, accurately forecasting housing prices is crucial for different entities. This study aims to enhance forecasting models for housing costs by utilizing the benefits of Multilayer Perceptron (MLP). This research aims to improve the precision of real estate price forecasts by utilizing the sophisticated data processing capabilities of MLPs to assess the significance of different attributes. The chosen approach focuses on crafting an MLP model, intricately structured with various layers and activation mechanisms, to decode intricate connections in assorted housing market data. Findings indicate a notable enhancement in forecasting precision, as the MLP model surpassed traditional regression models, attaining more than 90% accuracy. Such results are crucial for the real estate industry, empowering key players such as purchasers, vendors, and evaluators to make better-informed choices. Implementing MLP effectively in this scenario improves understanding of the market and highlights the expertise of neural networks in predictive analytics in diverse fields.",0.0,http://dx.doi.org/10.5220/0012832700004547
daba573d680bfc66be197986e00856a3e48fb297,10.15446/bitacora.v36n1.123155,New housing markets and affordability gaps in Mexico City,2026.0,Bitácora Urbano Territorial,José Gasca Zamora; Francisco Javier Luna Moreno,"The purpose of this study is to analyze the evolution of new housing markets in Mexico City and its metropolitan area between 2000 and 2024 and how market segmentation in this sector reinforced affordability gaps. Affordability gaps are understood as the distance between household income capacity and actual home purchase prices. Residential segmentation was determined based on submarkets classified by size and price and their spatial distribution in the metropolis, while affordability was measured as the relationship between housing prices and family income. The results show the consolidation of a spatially segmented and differentiated supply of new housing, which generated price structures that acted as differentiated demand mechanisms. This spatial pattern reinforced inequalities in access in the metropolis, deepening the gap between those who managed to acquire higher-quality housing in urban environments with better living conditions and those who were displaced to the peripheries where, although prices were relatively lower, there were significant deficits in public facilities and services.",0.0,https://doi.org/10.15446/bitacora.v36n1.123155
d5fa1a30f0b446809e7d5129c56b30f298ed13b5,10.1007/s00168-026-01528-0,Land conservation policy and rental markets: evaluating unintended housing price effects,2026.0,The annals of regional science,Corey Lang; Jarron VanCeylon,"Environmental policies can generate distributional impacts through the housing market, impacting homeowners and renters in unequal ways. While environmental improvements often benefit disadvantaged groups, one concern is that these improvements can increase the desirability of neighborhoods, which in turn can increase housing costs for renters and leaves the overall welfare effect ambiguous. In contrast, homeowners benefit from the additional amenities and the equity gain. This paper seeks to evaluate how rental prices respond to gains in nearby land conservation relative to owner-occupied home values using a panel of census and conservation data for the whole USA. We employ a first-difference regression model and use propensity score matching as a pre-processing method to improve the comparability of areas with and without new conservation. Our results suggest that local gains in conservation do not capitalize into rental prices but do capitalize into home values. Overall, our findings indicate that concerns for renters’ welfare and unintended consequences of land conservation are unsupported.",0.0,https://link.springer.com/content/pdf/10.1007/s00168-026-01528-0.pdf
b0aeeec6ba1c3a86946d4c2b2af6a1f4b63ac053,10.1016/b978-0-12-813524-2.00002-0,Handbook of the consumer chapter,2019.0,Handbook of US Consumer Economics,A. Haughwout; Donghoon Lee; Joelle W. Scally; Lauren Thomas; W. van der Klaauw,"Abstract Since the onset of the 2008 financial crisis, consumer financial and borrowing behavior, once considered a relatively quiet little corner of finance, has been of enormously increased interest to policymakers and researchers alike. Prior to the Great Recession, there was a historic run-up in household debt, driven primarily by housing debt, which coincided with a speculative bubble and sharp rises in home prices. Then, as prices began to fall, millions of households began defaulting on their mortgages, unable to keep up with home payments, and greatly contributing to the onset of the deepest recession since the 1930s. Following the steep increase in debt balances during the boom, households began rapidly paying off their loans during and immediately after the Great Recession. Since 2013, debt has begun to increase and eventually rise above its previous levels, albeit at a much slower rate than before, at least partially due to stricter lending standards. We examine the trends in household debt before, during, and since the 2000s financial crisis and Great Recession. As we will show, this period is unique in American history in several ways. Our analysis will show the source",0.0,
baf3ccc48ebbb4eb576840b602ce40721e086d60,10.1093/geroni/igad104.2503,ECONOMIC BOOM AND FINANCIAL RECESSION—WHAT ARE THE EFFECTS ON RELOCATION PATTERNS FOR OLDER ADULTS?,2023.0,Innovation in aging,David Dahlgren; Å. Hansson; S. Iwarsson; Steven Schmidt; Maya Kylén,"Abstract While previous research shows that older adults choose to relocate to a different home for numerous reasons (e.g., changes in the household composition, health decline), little is known about the influence of economic factors. The economic situation on aggregated level can influence the individual in more ways than by consumer demand and income, for example, financial crisis, fluctuating housing prices, and more general uncertainties about the future. Representing a novel approach, the aim of this study was to investigate the impact of macroeconomic events on relocation rates among older adults in Sweden. We used high quality panel data from Swedish registers, based on a random sample made 1994 with 300,000 individuals. Data was analyzed from 1970-2016 using a repeated cross-sectional design. Preliminary results show that the number of relocations was volatile the first year of a financial crisis. Depending on the characteristics of the crisis, the number of relocations decreased or increased; crises that are less connected to the property market had a reduction in number of relocations. This effect was observed for 1-2 years and stabilized to “normal levels” in the subseq",0.0,
387c96c46ae3ba42e44096b28ce6985dd4977367,10.69554/vozi8427,The ungodly jumble: Residential address identifiers and embedded uncertainty,2026.0,"Journal of Building Survey, Appraisal & Valuation",Michael Lawson; Graeme Winser,"Property assets exist simultaneously as physical structures, legal constructs and digital abstractions, yet the systems used to identify and evaluate them often struggle to reconcile these overlapping realities. This paper examines the growing disconnect between the physical attributes of residential property, the legal and historical complexity of title, and the digital layers produced through contemporary mapping, modelling and automated valuation. While tools such as digital twins, geographic information systems (GIS), automated valuation models (AVMs) and machine learning aim to deliver precision and scale, each introduces its own assumptions, simplifications and inherent uncertainties. Address identifiers such as the unique property reference number (UPRN) promise consistency, but cannot account for the nuanced and frequently non-conforming nature of legal title boundaries, historical parcelling or rights and obligations embedded in property records. Through exploring these tensions, the paper highlights how system-generated certainty can obscure material ambiguities, and how over-reliance on automation risks misidentifying characteristics essential to valuation, lending and r",0.0,
78db4351ca28f9f4280cec9844247ec8bc04d5a6,10.26634/jste.13.4.21934,The ideal site selection,2025.0,i-manager's Journal on Structural Engineering,P. Lakshmi; Isha Prasuna Bodavula; Jai Siddartha Manikanta Cherukuri; Kavya Sri Bandaru; Abhishek Garnepudi,"The rapid growth of cities has led to a significant shortage of affordable housing, exacerbated by unplanned development and rising population density. This work was initiated to tackle the pressing housing issues by using data-driven analysis to identify neighborhoods that offer a balanced mix of essential amenities. The main goal is to support homebuyers by recommending neighborhoods that are well-equipped with necessary amenities, thus enabling more informed and efficient housing choices in complex urban areas. This methodology can be applied to other cities facing similar challenges related to urban expansion. For this work, a Foursquare Places API is used to gather data on various amenities in different neighborhoods, including hospitals, supermarkets, parks, and public transportation services. Additionally, a housing price data was incorporated to provide budget options, allowing potential buyers to find neighborhoods within their financial limits. Through K-Means clustering, we grouped neighborhoods based on the availability of amenities, aiming to highlight areas with the most potential for growth and affordability. The clustering results were evaluated based on the number ",0.0,
e16a7003a1d7985221f97c7d51e03384677d23aa,10.1109/iccams65118.2025.11234545,A Neural Network approach for predicting house prices using Boston Housing Price dataset,2025.0,"2025 2nd International Conference on New Frontiers in Communication, Automation, Management and Security (ICCAMS)",A. Sowmya; B. S. Sindhu; M. B. Sri; Y. Sri Lalitha,"Predicting house prices is a crucial challenge in real estate, helping buyers, sellers, and investors make informed decisions. In this project, we build a neural network to estimate housing prices using the Boston Housing Price dataset. Our approach leverages a Multilayer Perceptron (MLP), a type of artificial neural network, to learn the complex relationships between various housing features— such as crime rates, property tax, and the number of rooms—and their market value.To ensure accuracy, we preprocess the data using Min-Max Scaling, making it easier for the model to learn meaningful patterns. The MLP consists of multiple layers of neurons with ReLU activation functions, allowing it to capture intricate trends in housing prices. We train the model using backpropagation, optimizing with RMSprop and evaluating performance using metrics like Mean Absolute Error (MAE) and Mean Squared Error (MSE).The results highlight the potential of deep learning in real estate forecasting, showing how neural networks can provide valuable insights into price estimation. While this project focuses on MLPs, it opens the door to exploring even more advanced techniques, like Convolutional Neural Net",0.0,
a01b47cde42a8c1cd89bc16a0a4a541d29153342,10.26417/663ugu12o,Family Planning Policy and Housing Price in China,2020.0,European Journal of Economics and Business Studies,Shichang Ma,"Different intergenerational fertility levels affected by the family planning policy under such altruistic behavior will inevitably affect real estate prices. This paper studies the effect of different intergenerational fertility levels on real estate prices under the parental altruistic behavior model with Chinese characteristics by constructing an Overlapping Generation Model (OLG) with intergenerational wealth transfer. The empirical results show that the lower the intergenerational fertility level of the middle-aged generation, the higher the average wealth level transferred to the youth generation, and the higher the real estate price. This result shows that, unlike the high fertility rate of popular cognition, the low fertility rate of the middle-aged generation under the influence of the family planning policy and the altruistic behavior of the Chinese parents are the important reasons for the current high housing prices. This paper reveals the relationship between China's population policy and real estate price, and can guide the judgment of China's real estate market in the future.",0.0,https://doi.org/10.26417/663ugu12o
2debffb151202652017b172068dc8774008af191,10.37407/kres.2026.44.1.125,A Study on the Efficiency of Real Estate Financial Support Policies Related to Jeonse Fraud,2026.0,Korea Real Estate Society,H. Yun,"Recently, the rapid increase in jeonse fraud—cases in which tenants fail to recover their rental deposits —has emerged as a serious social issue in Korea, threatening housing stability and undermining trust in the real estate market. In particular, since 2021, the risk of deposit non-return has increased due to the combined effects of rising housing prices, higher jeonse price-to-value ratios, and the expansion of gap investment. Subsequently, as interest rates increased and housing prices declined, the scale of jeonse guarantee accidents expanded significantly. This study analyzes the relative efficiency of the jeonse guarantee policy by focusing on the annual policy performance in Seoul, Gyeonggi, and Incheon after subrogation payments, using subrogation data from the Korea Housing & Urban Guarantee Corporation (HUG) from 2021 to 2024. To achieve this, recovery amount, recovery rate, and damage reduction rate were selected as key performance variables, and Data Envelopment Analysis (DEA) was applied to measure efficiency using the CCR and BCC models. The results show that Seoul and Gyeonggi achieved relatively stable recovery performance in some years, thereby maintaining the eff",0.0,
ea1a8e344a91774c9b30fd0acc72ec4791567e4e,10.38124/ijisrt/25jul971,Machine-Learning Valuation of Residential Real Estate in Bishkek,2025.0,International Journal of Innovative Science and Research Technology,Meerim Kuldzhanova; Gulshat Muhametjanova,"This paper outlines the development of a machine learning model for accurate and interpretable forecasting of
Bishkek housing prices, Kyrgyzstan. Leveraging a collection of 9,664 apartment posts from Kaggle, the model takes into
account major real estate attributes such as square footage, building, rooms, and condition. One-hot encoding was applied
to encode categorical values, and a new ""preferred floor"" attribute is included to capture buying preference as per floor
level. In order to model the data, the Light GBM gradient boosting algorithm was chosen due to its excellent performance
on heterogeneous tabular data and its capability to effectively handle missing values and feature interactions. The model
produced an R2 score of 0.958 and a mean squared error (MSE) of 0.0419, reflecting very high predictive accuracy. The
analysis of the important characteristics showed that the area, the number of rooms, and the type of building are the most
important things that influence apartment prices. These results further reveal the dynamics of the urban housing market

and can be used to better fine-tune housing affordability strategies. The model can also be used as a foundation for web-
",0.0,
671412f3dfda0c66b5fc1dcce198490ac44742ee,10.1108/ijhma-07-2025-0167,Do credit supply and urbanization influence housing prices? Evidence from 31 provinces of Iran,2025.0,International Journal of Housing Markets and Analysis,Davoud Mahmoudinia; Mir Hadi Hosseini Kondelaji; Behrouz Sadeghi Amroabadi,"
 
 This study aims to examine the simultaneous and interactive effects of credit supply and urbanization on housing prices in Iranian provinces. The significance of housing as a share of household portfolios, its role as a valuable commodity, has been the main focus of many studies in recent decades. However, housing prices and their fluctuations are influenced by several factors. The economic literature reveals that credit-driven growth and urbanization have emerged as prominent drivers of housing price fluctuations, and the interplay between credit supply and the degree of urbanization significantly affects housing prices in developing countries.
 
 
 
 In this study, the authors investigate the impact of credit supply and urbanization on house prices across 31 Iranian provinces between 2010 and 2022. Diverse long-term estimations indicated that without controlling for total inflation and urban household income, credit supply has a large and statistically significant effect on housing prices. In these models, except for the fixed-effects regression with Driscoll–Kraay standard errors, urbanization negatively influenced housing prices.
 
 
 
 By including overall inflation and ur",0.0,
b62dd57f28797ff414b5b52f702716ebed431035,10.2139/ssrn.3409130,Distributional Effects of Surging Housing Costs Under Schwabe's Law,2019.0,Social Science Research Network,Volker Grossmann; Benjamin Larin; H. Löfflad; Thomas Steger,"The upward sloping trend of rents and house prices has initiated a debate on the consequences of surging housing costs for wealth inequality and welfare. We employ a frictionless two-sectoral macroeconomic model with a housing sector to investigate the dynamics of wealth inequality and the determinants of welfare. Households have non-homothetic preferences, implying that the poor choose a higher housing expenditure share, which is compatible with Schwabe’s Law. We first examine the isolated effects of increasing housing costs in partial equilibrium. The model is closed by introducing a production sector that enables us to analyze the general equilibrium consequences of a widely discussed policy option, which aims at dampening the growth of housing costs. Abolishing zoning regulations triggers a slower rent growth and reduces wealth inequality by 0.7 percentage points (measured by the top 10 percent share). Average welfare increases by 0.5 percent. The household-specific welfare effects are asymmetric. The poor benefit more than the rich, and the richest wealth decile is even worse off.",0.0,https://www.cesifo.org/DocDL/cesifo1_wp7684_0.pdf
4ead3074b68b0aa53bf262191c4c75b444dab505,10.52344/hfr.2023.7.2.31,"Determinants of Housing Environment of Independent Households among
 Young People",2023.0,Housing Finance Research,Kwanghoon Hwang,"For young households who are economically independent from their parents, we estimated the factors affecting the residential environment of young people, including whether they lived in a house or an apartment. The estimation revealed that male, highly educated, high-income, non-metropolitan young people have the characteristics of home and apartment dwelling types. However, among them, we presume that the householder is maintaining the housing characteristic of the jeonse/monthly rent form rather than the owner. This is because the period of transition to the labor market and entry into a job is short, so the economic ability to secure a residential space through housing purchase is insufficient. Additionally, in the case of the metropolitan area, since the cost of purchasing a house, that is, the housing price, is higher than that of non-metropolitan areas, young people living in non-metropolitan areas are highly likely to be self-employed. Therefore, policy efforts should be improved, such as expanding the supply so that young people can sufficiently move into public rental housing.",0.0,http://www.e-hfr.org/download/download_pdf?pid=hfr-7-2-31
8edbbce5aa1468e521c00151c165aa8fe3848f14,10.57017/jaes.v20.3(89).04,State Beveridge Curve Shifts during the Great Recession,2025.0,Journal of Applied Economic Sciences,Aaron Popp,"This paper estimates the size and timing of state-level shifts of the Beveridge Curve to examine changes in US labour market conditions during the Great Recession. Compared to a benchmark based on each state’s share of unemployed, states in the Southwest, Southeast, and Mid-Atlantic experienced excess shifts. The timing of the shifts is heterogeneous, with 35 states shifting between November, 2009 and March, 2010. Regression evidence shows that population growth, higher construction and natural resource employment, house price appreciation, and urbanization explain the size of the state shifts, which suggests that diverse factors contributed to the shifts in the Beveridge curve.Copyright© 2025 The Author(s). This article is distributed under the terms of the license CC-BY 4.0., which permits any further distribution in any medium, provided the original work is properly cited.Article’s history: Received 23rd of June, 2025; Revised 29th of July, 2025; Accepted 12th of August, 2025; Available online: 30th of September, 2025. Published as article in the Volume XX, Fall, Issue 3(89), 2025.",0.0,https://ritha.eu/storage/1579/4_jaes_PoppAaron.pdf
94c2bdc7e41b21ff0011cb85727dad2b255deff0,10.54097/s9r2g104,Shanghai Second-hand Real Estate Price Prediction,2026.0,Journal of Innovation and Development,Yuxuan Yang,"With the rapid urbanization and continuous growth of the real estate market, housing price prediction has become an important research topic in urban economics. This paper studies second-hand housing prices in Shanghai using data from 2022 to 2024. The dataset includes 16 districts and covers factors such as housing size, location, distance to subway stations and school resources. After removing incomplete data 3126 samples were kept for analysis. Both statistical methods and machine learning models were used, including linear regression and random forest. The results suggest that housing prices vary a lot across regions. Central districts are clearly more expensive while outer areas are relatively cheaper. There is also a slight downward trend over time. Compared with other models, random forest performs better, especially when handling more complex relationships. Factors like location and transport seem to play an important role. However, some limitations remain such as missing macro-level data. Future research could improve this by including more variables and trying other models.",0.0,https://drpress.org/ojs/index.php/jid/article/download/35819/34983
c447ce6545a0c5a0b667134b5e77e961a7074a73,10.26577/jpcsit2025338,Forecast of Housing Prices in Almaty Using Machine Learning Algorithms,2025.0,Journal of Problems in Computer Science and Information Technologies,A. Rakhimzhanov; Jelena V. Caiko,"Precise prediction of housing values is an important task for various stakeholders involved in the housing market, including investors, builders, and city planners. In this research, supervised machine learning models are used to predict the price of apartments in Almaty, Kazakhstan, which is a dynamic urban market in Central Asia. With an openly available dataset of apartments for sale, Linear Regression, Lasso Regression, Random Forest, and XGBoost models are implemented and tested. The data is scaled and encoded with scalable pipelines, and models are evaluated with regards to Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R² Score. The best performing model amongst those tested was Random Forest Regressor with an R² of 0.9158, followed by XGBoost with 0.8438. Feature importance visualization identifies district, area, and construction year as primary influencing factors. The research supports that ensembling machine learning models are efficient and scalable predictors for housing forecasts and suggests future improvements with time-series and geospatial features",0.0,https://jpcsit.kaznu.kz/index.php/kaznu/article/download/209/83
5113267c6a4cc23cdb63e00c633c88481cd7fc96,10.54254/2754-1169/2025.bj30089,Predicting House Prices: A Machine Learning Exploration with Decision Trees and Random Forests,2025.0,"Advances in Economics, Management and Political Sciences",Zhuohan Shen,"In the dynamic real estate market, accurate house price prediction is crucial for buyers, sellers, and investors, yet traditional statistical methods often fail to capture the complex non-linear relationships between multiple factors and prices. This paper applies empirical analysis and machine learning, using a simulated real estate dataset with features such as Area and DistrictLevel, to compare the performance of decision trees and random forests. With a 75%25% trainingtest split (random_state=42), max_depth=6 for both models, and n_estimators=100 for the random forest, the results indicate that the random forest model (R-squared = 0.85) outperforms the decision tree model (R-squared = 0.78). Area and DistrictLevel remain the primary drivers of housing prices, jointly contributing over 60% of feature importance, while the importance of SchoolNum increases from 3% in the decision tree to 12% in the random forest. Overall, this study offers practical guidance for real estate market participants and provides methodological insights for model selection in related predictive research.",0.0,https://www.ewadirect.com/proceedings/aemps/article/view/30089/pdf
f77673ecd4b822ddfecae24584e31573fcdb7183,10.2478/cee-2025-0059,Relationship Between Architectural Style and Property Value in the Czech Republic,2025.0,Civil and Environmental Engineering,Pavel Klika; David Brandejs; Karla Háva; Sofie Pokorná; Monika Doležalová; Vítězslava Hlavinková,"Abstract This study investigates the influence of architectural styles on the value of housing units in heritage-listed apartment buildings across four Czech cities: Brno, Olomouc, Pilsen, and Ceske Budejovice (Budweis). Utilizing data from the National Heritage Institute, the Czech Statistical Office and Czech office for Surveying, Mapping and Cadastre, the research evaluates the relationship between architectural styles and property values using statistical methods, including Analysis of Variance (ANOVA). The findings indicate no statistically significant influence of architectural style on property values, contrary to international studies suggesting a price premium for historical styles. However, a statistically significant effect of location on property values was identified, particularly in Brno. The study highlights cultural and geographic differences in architectural valuation and suggests further research to refine valuation methods for heritage-protected buildings, considering additional factors such as building condition, proximity to amenities, and public infrastructure.",0.0,https://doi.org/10.2478/cee-2025-0059
d0e68ced77123d52a4b93cb115c8263c5ea71a56,10.63766/spujstmr.26.000077,Multifunctional Smart Real Estate Platform with Predictive and Utility Features,2026.0,"SPU - Journal of Science, Technology and Management Research",Ravijeet Sharma; V. Verma; Jagruti Jadhav,"The global real estate market, characterized by fragmentation and information asymmetry, is ripe for digital transformation. This paper proposes an AI-enhanced unified platform designed to seamlessly integrate sales and rental operations, offering a comprehensive and intelligent solution for all stakeholders. Leveraging advanced Artificial Intelligence (AI) techniques, including machine learning for predictive analytics, natural language processing for semantic search and content analysis, computer vision for property evaluation, and sophisticated recommender systems, the proposed platform aims to significantly enhance market transparency, operational efficiency, and user experience. We outline a prototype-driven framework, detail the integrated AI components, discuss the methodological considerations for development, and enumerate the profound benefits this unified approach offers over traditional, siloed marketplaces. Furthermore, we address the inherent challenges and delineate future research directions, positioning this platform as a transformative force in the evolving real estate landscape. To validate the feasibility of the proposed framework, a functional prototype was dev",0.0,
5f56714a4334b3651ae5bb2874e9b7262cdd31ba,10.61173/8bw26366,The Impact of Housing Price Fluctuations on Family Fertility Decisions in Modern China: A Review of Theoretical Mechanisms and Empirical Evidence,2025.0,Finance & Economics,Guo-Rui Chen,"This study examines the intricate relationship between housing price fluctuation and household fertility decisions in present-day China, with a focus on the Guangdong- Hong Kong-Macao Greater Bay Area. The article creates a theory called the “dual-effect” that is based on the existing literature and that is made up of two components: a wealth effect and a crowding out effect, in light of that the area has a historically low total fertility rate at the same time as their housing market has unpredictable swings. The literature contains significant gaps, especially with respect to the non-attention to price volatility, and the regional institutional variety. We will use a hybrid research design, consisting of surveys, interviews, and policy research. The research aims to reveal particular mechanisms through which housing market characteristics affect fertility decisions. The research results will provide a comprehensive theoretical framework. There will be evidence-based, unified policy implications on housing stability and population sustainability in a high cost urban agglomeration.",0.0,https://lseee.net/index.php/fe/article/download/1863/FE009542.pdf
a585411f7d48cd2a09a5dd5f912da9f1679ea684,10.2139/ssrn.3983312,Housing Price Prediction Model Selection Based on Lorenz and Concentration Curves: Empirical Evidence from Tehran Housing Market,2021.0,Social Science Research Network,Mohammad Mirbagherijam,"This study contributes a house price prediction model selection in Tehran City based on the area between Lorenz curve (LC) and concentration curve (CC) of the predicted price by using 206,556 observed transaction data over the period from March 21, 2018, to February 19, 2021. Several different methods such as generalized linear models (GLM) and recursive partitioning and regression trees (RPART), random forests (RF) regression models, and neural network (NN) models were examined house price prediction. We used 90% of all data samples which were chosen randomly to estimate the parameters of pricing models and 10% of remaining datasets to test the accuracy of prediction. Results showed that the area between the LC and CC curves (which are known as ABC criterion) of real and predicted prices in the test data sample of the random forest regression model was less than by other models under study. The comparison of the calculated ABC criteria leads us to conclude that the nonlinear regression models such as RF regression models give an accurate prediction of house prices in Tehran City.",0.0,https://doi.org/10.2139/ssrn.3983312
7ae362d87b69773e3862c49902e47486b625b6a2,10.5296/ber.v12i1.19475,"The Role of Demography, Geographical Constraints, and Land Regulations on House Price in Malaysia",2022.0,Business and Economic Research,Saizal bin Pinjaman; S. Aralas; D. Nipo,"The current paper investigates the influence of demography, geographical constraints, and land regulation on house price in Malaysia based on the developers’ perspective. A survey questionnaire was distributed among the real estate developers in the country and for the demographical factors, population growth, income, standard of living, and household confidence on future prices are identified to be important determinants. Meanwhile, in terms of land regulations, a majority of the developers believed that the cost of land acquisition, zoning regulations, and land statuses are important on house price setting. Apart from that, geographical constraints including land reclamation, forest clearing, and hillslope stripping are also considered by the developers. In ensuring that the house price remains affordable, land regulations on real estate development should be more relaxed to stimulate housing projects at lower costs. In addition, price speculation should also be monitored if not curbed so that the house price remains affordable particularly for the medium and low-income earners.",0.0,https://www.macrothink.org/journal/index.php/ber/article/download/19475/15231
6c26a3f40ccaee5e15fb0e565c9bfda58b146b8e,10.1145/3589860.3589878,Prediction and Analysis of House Prices in Boston Based on Regression Model,2022.0,EBEE,Zuo-Han Chen,"In artificial intelligence learning, Boston housing price forecast analysis problem is a classic regression problem. Based on the housing price information collected by the U.S. Census Bureau in Boston, Massachusetts. this paper divides the housing price data set of Boston and builds the regression model linear regression, decision tree regression and support vector machine regression SVR and trains the data set, so as to obtain the relationship between different data related to Boston house price, and use this relationship to connect all data, it can finally predict the future house price trend in Boston and display it through visual operation. Through three regression model prediction value, respectively compared with the actual value, the trend of overall and actual and estimated values of the same, but there is a certain error, especially when spot prices higher or lower, often cannot get accurate forecast, so the data for the selection of the characteristic value still exists space for improvement, future study needs to get more data and the characteristics of abundant data.",0.0,https://dl.acm.org/doi/pdf/10.1145/3589860.3589878
8b414ba341cf07b297a69186e07f61479cc53e76,10.18267/j.pep.816,Modelling Household Mortgage Debt: the case of the Czech Republic,2022.0,Prague Economic Papers,L. Fiala,"2 This paper deals with Czech household mortgage debt and its determinants in the period 1Q2005–2Q2021. Our analysis focuses on the variables determining the level of mortgage debt from both short- and long-term perspectives. Our contribution is two-fold. Firstly, we examine the relationship between the selected variables within a cross-correlation analysis. The results confirm the positive dependency of household mortgage debt and real GDP, real gross average income and the level of house prices. By contrast, a negative relationship was identified for real interest rates, the unemployment rate and the inflation rate. Secondly, we explore the ARDL and EC models and identify one cointegration relationship. Our results confirm that house prices and real wages are determinants of household mortgage debt in the long-term perspective. However, a wider range of variables plays a role in the short run, including house prices, real gross average income, inflation and long-term interest rates. Moreover, our model indicates the insignificance of unemployment in both the short and long run.",0.0,http://pep.vse.cz/doi/10.18267/j.pep.816.pdf
47e4ca2c9ee69fa225e47a66f1bd5b2fd5074eb1,10.54254/2754-1169/66/20241234,Shanghai House Price Prediction Using Random Forest,2024.0,"Advances in Economics, Management and Political Sciences",Shenghan Wu,"With the increasing complexity of the urban real estate market, accurate prediction of housing prices has become an important task. One of the key applications of machine learning is how to raise and accurately estimate costs. Various factors will affect the price of houses. Most of the current frameworks are all using as detailed features as possible to increase their predicting accuracy. But in real-life conditions, many non-local clients also want to have a clear prediction of the house price. These consumers are not from the area; thus they are unaware of the house's surroundings, including nearby amenities. What they know about the house is only its housing characteristics. The objective of the paper is to help these clients put their resources into a bequest properly. The paper collected a wide range of Shanghai real estate data about housing characteristics as characteristics. By harnessing the ensemble learning capabilities of random forests, the paper aims to capture complex relationships and non-linear effects between features, thereby improving prediction accuracy.",0.0,https://www.ewadirect.com/proceedings/aemps/article/view/9363/pdf
a422b7522f572351a603966868023463890756e2,10.70088/8f92z263,An Empirical Study on the Determinants of Housing Prices in Beijing and Model Optimization,2024.0,"Science, Technology and Social Development Proceedings Series",Xiang Lai,"This paper aims to investigate the potential factors influencing housing prices in Beijing and optimize the prediction model. Using the Kaggle dataset ""Housing Price in Beijing"", multiple factors affecting housing prices were examined, including square footage, bedroom count, bathroom count, follower count, the presence of an elevator, and subway proximity. The study initially established a multiple linear regression model (MLR) and then optimized the model through variable selection and hypothesis testing. The final model indicates that square footage, bathroom count, follower count, elevator presence, and subway accessibility significantly impact housing prices. Additionally, subway proximity positively correlates with housing prices, while increased square footage is negatively associated with price, possibly due to lower unit costs for larger properties and the higher market demand for smaller homes. By validating the model's performance using a test dataset, the final model demonstrates effective predictive capability and offers insights for future model improvements.",0.0,http://dx.doi.org/10.70088/8f92z263
22636334140a59a1c6a6004b40b4aed55a85d4fa,10.22423/kreus.2025.18.1.103,A Study on the Impact of the International Exchange Complex District Development on Surrounding Real Estate: Focused on the Third General Residential Area of Gangnam-gu,2025.0,Konkuk Research Institute of Real Estate and Urban Studies,Minjung Joo; Sangyoub Lee,"This study empirically analyzes the impact of the International Exchange Complex Zone development in Seoul's Gangnam on land and building unit prices, focusing on the significance of spatial autocorrelation. Utilizing 1,339 actual transaction cases from 2006 to 2024, OLS, Spatial Lag Model (SAR), and Spatial Error Model (SEM) were comparatively analyzed. OLS regression results indicated that development phases, property area, macroeconomic indicators, and location variables significantly influenced both dependent variables. However, OLS residual diagnostics revealed statistically significant spatial autocorrelation, underscoring the necessity of applying spatial econometric models and leading to a 1000m optimal spatial threshold selection. SAR and SEM models, applied with this threshold, demonstrated comparable or improved explanatory power (R²/Pseudo R²) compared to OLS, with SEM showing the best fit by information criteria (AIC, BIC). Moran's I tests on their residuals confirmed successful resolution of spatial autocorrelation. Significant spatial coefficients (in SAR and SEM) proved strong spatial spillover effects and the influence of unobserved spatial characteristics, highlig",0.0,
2be147906d50c2990377290cae828f47118a300a,10.71097/ijsat.v16.i1.2810,Machine Learning For Bank Loan Eligibility Prediction:Focus on Home Loan and Education Loan,2025.0,International Journal for Sciences and Technology,T.Lakshmi Narasimha; T. V. S. Chandra Rao; P. S. Yashwanth Roy; A.Vinoth Kumar; T.Kumanan,"Machine learning (ML) has emerged as a powerful tool in the financial sector, particularly for predicting outcomes in home loans and education loans. This paper examines the application of ML techniques in assessing loan approval, repayment likelihood, and risk management for these two distinct loan types. For home loans, ML leverages credit scores, income data, and property valuations to enhance decision-making in long-term commitments. In contrast, education loans rely on predictive models of future earning potential, academic performance, and institutional factors to evaluate unsecured lending. By employing supervised and unsupervised learning algorithms—such as Random Forests, neural networks, and clustering—ML improves accuracy, reduces defaults, and personalizes loan terms. Despite challenges like data quality and economic variability, ML offers significant benefits, including operational efficiency and broader financial inclusion. This exploration highlights current practices, comparative differences, and the potential for future advancements in predictive lending.",0.0,https://www.ijsat.org/papers/2025/1/2810.pdf
efe1215eb0dec3153ad452e343573e8fdb63574c,10.14288/1.0072559,Essays on real estate finance and economics : strategies for developments under uncertainty,2012.0,Joint Conference of the Information Retrieval Communities in Europe,Dong-You Seung,"This thesis contains three essays on real estate finance and economics. Both chapter 2 and chapter 3 study a real estate developer's timing strategies under uncertainty and chapter 4 studies the ratio of housing price-to-income. Chapter 2 analyzes the effects of leverage on the timing of developments because most real estate developers depend heavily on leverage. In particular, it investigates the leverage effects on real estate developments that involve conversion of land from agricultural to urban use. Leverage matters for a developer who wants to optimize the timing of developments. Chapter 3 studies the effects of heterogeneity of real assets on the timing of developments because each property is unique and its value is likely to move together with values of neighboring properties. Heterogeneity matters for a developer who builds multiple properties in a project. Chapter 4 analyzes the price-to-income ratio which has been used widely as a measure for housing bubble. A cross-city comparison of price-to-income ratios can overestimate bubble in cities of high amenities.",0.0,http://hdl.handle.net/2429/40338
53a228745dc9a32b1002f59f1be59cdca85e461e,10.54254/2753-8818/39/20240598,Variance analysis and linear regression: Exploring the impact of location factors on the average logarithmic price of pre-owned housing in Shenzhen,2024.0,Theoretical and Natural Science,Yunzhong Ding; Zehua Tang; Min-Jia Wang,"The primary purpose of this report is to investigate the impact of locational factors on the average prices of second-hand homes in Shenzhen, providing a theoretical foundation for the pricing of such properties. To achieve this, the report first establishes indicators to describe the characteristics of second-hand homes. Then, it constructs an analysis of the variance model to explore the impact of multiple related factors on housing prices regarding the average logarithmic price of pre-owned housing in Shenzhen. The model results indicate significant correlations between administrative divisions, whether the property is in a school district, the orientation of the house, the age of the house, and the area with the logarithmic price per unit area of second-hand housing. At the end of the report, two inter-complimentary multivariate linear regression models are constructed, and simulated data produced through R studio are also provided, and the final model is used for practical application to accurately predict the price of second homes under the appropriate conditions.",0.0,https://tns.ewapub.com/article/view/14221.pdf
bd81b598fca1e12e2fddebafd5c0fe29c6dccc47,10.17308/sait/1995-5499/2025/1/133-142,The impact of data preparation techniques on house price prediction task,2025.0,Вестник ВГУ. Серия: Системный анализ и информационные технологии,Ihcene Zitoune,"Accurate house price prediction is considered critical for decision-making in the real estate sector, where datasets are often characterized by missing values, outliers, and skewed distributions. In this study, the impact of various data preprocessing techniques on the performance of the XGBoost algorithm for predicting house prices is investigated. A real estate dataset from Kaggle is used to analyze and compare methods such as missing value imputation, categorical encoding, log transformation, and dimensionality reduction. The results show that preprocessing techniques significantly improve model performance, with certain approaches greatly reducing prediction errors and improving efficiency. Advanced methods, such as PCA with normalization and log transformation, produced the best results, showing the importance of choosing effective preprocessing steps. This study provides practical guidance for using data preprocessing to improve machine learning models, offering insights particularly relevant to real estate price prediction and other structured data applications.",0.0,https://doi.org/10.17308/sait/1995-5499/2025/1/133-142
898c4c4bc9979887debb08e4b1d50a4f1487e303,10.1109/icdsaai65575.2025.11011587,Advanced Real Estate Price Forecasting Using Multivariate Long Short-Term Memory Networks,2025.0,"2025 International Conference on Data Science, Agents & Artificial Intelligence (ICDSAAI)",S. C.; Veeramalai Sankaradass; R. Ravi; R. Ramesh; Poongothai P; R. Ponnusamy,"Forecasting real estate prices is critical in making financial decisions, formulating investment strategies, and designing plans for urban development. Predictive models can enable stakeholders to detect the market's future trends and make meaningful decisions. Forecasting methods often fail to extract complex nonlinear patterns from economic indicators, interest rates, population, and regional trends in the real estate market. The paper proposes a multivariate LSTM network for advanced real estate price forecasting. The input features under consideration for the proposed model are longitude, latitude, median age of housing, total rooms, total bedrooms, population, households, median income, median house value, and ocean proximity. The multivariate technique offers a better facility for capturing time dependency and relations between varied variables. Therefore, the model performs well in correctly predicting house price fluctuations. This model was tested on housing prices in different regions and related economic indicators. We evaluate the performance of our model in terms of actual versus predicted prices and residual plots. We used cross-validation. The model proved robust and",0.0,
dadfcb914fd401118bb37e43d7b8f5560d322427,10.54254/2753-8818/2026.dl33232,Predicting Housing Prices in Urban Areas: Linear Regression and Random Forest,2026.0,Theoretical and Natural Science,Ting-Yu Ma,"This study analyzes urban housing prices using multiple linear regression and Random Forest models based on 50 simulated observations. The predictors include floor area, house age, distance to the city center, number of rooms, and number of toilets. The results show that Random Forest achieves higher prediction accuracy, with an R² of about 0.90, indicating strong ability to capture complex patterns in the data. In contrast, multiple linear regression provides clearer interpretation, allowing each factor's impact to be directly understood through coefficients. Both models consistently identify floor area, house age, and distance to the city center as the most important factors affecting housing prices. Floor area has a positive effect, while house age and distance show negative effects. The findings highlight a key trade-off: Random Forest offers better predictive performance, while linear regression provides better transparency. Therefore, the choice of model should depend on whether prediction accuracy or interpretability is more important in practical applications.",0.0,https://tns.ewapub.com/article/view/33232.pdf
359a69d14a985443ee2b2bfd59ef925620ec072e,10.21686/2073-1051-2025-4-44-75,Birth Rate and Peculiarities of Russian Federalism,2026.0,Federalism,P. Orekhovsky; O. Kislitsyna,"The decline in birth rates is one of the most serious challenges facing the Russian state. Since the mid-2000s, the Russian authorities have pursued an active federal policy aimed at increasing fertility, including the introduction of the maternity capital program, higher child support payments, and the provision of subsidized mortgages and land plots to large families. However, elements of federative policy associated with increasing heterogeneity among the constituent entities of the Russian Federation largely offset these federal efforts. In education, this is reflected in the establishment of a hierarchy of federal, research, and flagship universities; in industry, in the creation of various zones with preferential legal regimes; in culture, in the concentration of performing arts organizations in Moscow and St. Petersburg; and in the social sphere, in fundamentally different levels of social benefits provided to vulnerable population groups across regions. The result is a phenomenon of over-centralization, whereby young people concentrate in the capitals with high housing costs, postponing childbirth indefinitely. Consequently, federal pronatalist measures fail to achieve thei",0.0,
7db2acc57b057317fc0ed63ad39e556f01caa0ce,10.54097/6k15q611,The Research on Factors Influencing House Price-Taking Perth as an Example,2024.0,"Highlights in Business, Economics and Management",Jiarui Li; Pengbo Li; Xiao-Ya Miao; Yuxuan Zhu,"This article aims to identify the factors that have an impact on house prices. Using the method of Multiple Linear Regression to analyze the important factors with samples of Perth. Based on assumption, 8 variables were chosen to find the correlation of the price of house in the suburbs of Perth. This article also considers the interaction effects between the area of the parts of the house which contains the area of the land, the area of the room and number of some types of rooms includes garage, bedroom, living room and the date the house was sold, the distance to nearest public facilities such as station and school and the distance from the house to the central business district and the rank of the nearest school. In order to test the effectiveness of the operation, the research consider the significance of those variables, it turns out the longitude and latitude of the house and the year of building and selling and the postcode of the house. Overall, the fluctuation of the price of house in Perth can be considered by the extent to which these factors affect them.",0.0,https://drpress.org/ojs/index.php/HBEM/article/download/29235/28689
d75d9e4223d7ad93daf7829b2dd31ea5b1329ae8,10.54097/4pa78x23,The Research on Factors Influencing Housing Prices-Take Beijing as an Example,2024.0,Highlights in Science Engineering and Technology,Bowen Chen; Yi Min; Siyu Yu,"This article aims to identify those factors that have an impact on housing prices. The method of Multiple Linear Regression is used to analyze the significant factors with 400 samples of Beijing from 2011 to 2017. Based on an assumption, 12 variables that were chosen do correlate with housing prices. This paper also considers the interaction effects between house squares and the number of living rooms, drawing rooms or bathrooms, and uses Forward Stepwise Regression to solve the covariance problem caused by adding interaction terms. In order to test the effectiveness of this operation, the research compares the VIF value and significance of those variables. It turns out that square, building type, elevator, construction time, renovation condition, and subway have a significant linear relationship with prices, while the number of living rooms, drawing rooms and bathrooms, building structure, property rights, and district fail the significance test. Overall, the volatility of housing prices in Beijing can be considered by the extent to which these factors affect them.",0.0,http://dx.doi.org/10.54097/4pa78x23
793cac9872835d7adc88e61ff90383f771a92b9a,10.54941/ahfe1007583,"Machine Learning and Data Mining Insights into Monthly Housing Price Dynamics in Connecticut, USA",2026.0,AHFE International,Özerk Yavuz,"In today’s market place housing and housing associated goods and services constitutes important value for consumers. As indicated in the Maslow’s hierarcy of needs figure, sheltering, housing is one of the most basic needs of human beings. Later wants and demands take place, individuals engage in behaviours to afford their housing needs by either renting, buying a house or buying hotel, motel or other housing services. If demand of the consumers meet the available housing options and recently constructed housing projects, rent and selling prices of the housing options may be in a balance meaning a significant increase and decrease in the prices are unlikely to occur. If the demand passes the supply it would be on the spot to wait for increases in the housing market, whereas a lower demand in a normal supply scenario is likely to lower the prices in the marketplace for consumers. In this research average housing prices according to location considering date have been ananlysed using machine learning techniques available in data mining and computer science literature.",0.0,https://openaccess-api.cms-conferences.org/articles/download/978-1-964867-91-5_3
3083a07a60cab781adda578bd338d8f6cd8ed348,10.1146/annurev-resource-120524-041300,"Flooding, Housing Prices, and Insurance: Evidence from the United States",2026.0,Annual Review of Resource Economics,Laura Bakkensen; H. K. Friedrich,"Flooding is one of the costliest natural disasters in the United States, and a major source of flood damage is to the residential housing stock. Given the value of housing, both as a major source of household wealth and to the residential mortgage market, a long-standing literature has examined how floods impact house prices and evaluated the protective role of flood insurance. In this review, we synthesize the literature examining the impact of flood risk and flood events on housing value. We also examine research themes in the US flood insurance market including the determinants of flood insurance demand, the impact of insurance on household decisions to manage flood risk, and emerging changes to watch in the public and private flood insurance markets. We then survey key data challenges and opportunities and conclude by examining who bears the flood risk in the US housing market. As climate change is expected to change future precipitation patterns and raise sea levels, flood risk and insurance will likely be even more important for housing markets in the future.",0.0,https://doi.org/10.1146/annurev-resource-120524-041300
d38f630e7f22d16115f90355ad9950f0b3c0aac2,10.54254/2753-8818/38/20240561,Research on housing prices prediction based on multiple linear regression,2024.0,Theoretical and Natural Science,Qi-Jiang Wang,"With the steady development of social economy, commercial housing, as an important real estate, occupies a large proportion in family assets. According to the China Household Wealth Survey Report (2018) compiled by the Social China Economic Trends Institute, household net worth accounts for 70% of household wealth, including housing prices in Beijing and Shanghai. In higher cities, the proportion is as high as 80%. This paper analyzes the transaction data of about 10,000 second-hand houses in Beijing, constructs a multiple regression model with SPSS software, and obtains the dependent variable (housing price per unit area). The dataset used in this paper is fetched from the Kaggle website (Housing Price in Beijing). The results show that the relationship between the elevator, the floor situation, the decoration method, the administrative division and other independent variables. Also, it is shown that the correlation between the two is significant, so the model can be used. This paper provides reference for the actual transaction of second-hand housing in Beijing.",0.0,https://tns.ewapub.com/article/view/13430.pdf
d18409fb815d8fc73019639579734ed705b18a92,10.46501/ijmtst061236,Machine Learning House Price Prediction,2020.0,International Journal for Modern Trends in Science and Technology,"Manu Shahi, Abhay Singh, Amita Goel Vasudha Bahl and Nidhi Sengar","This document present the implementation of Machine Learning algorithms for the prediction of the house
and the real estate prices. As the house and real estate prices are subject to change with the market
conditions, so it become very difficult to predict the real estate prices with the conventional methods as it may
sometimes gives some exaggerated result that may incur losses. To predict the prices more accurately and
precisely we predict the prices based on the statics of that particular area which has all the trends and
factors on which the price is dependent. To analyse these data , several algorithms are used namely random
forest, linear regression , lasso regression etc. Use of these algorithms decreases the margin of error and
more precise result are achieved. So,we at this point recommend the real estate agents and house vendors as
well as the people to look into the model for better valuation of the house. This model can also be integrated
with the real estates websites to give better recommendation based on the prices using Machine Learning
Algorithms.",0.0,https://doi.org/10.46501/ijmtst061236
4607a6f6bacc8e2fda9ce2607ef5b9fe00368561,10.62051/ev013e77,Evaluating Machine Learning Models in Housing Price Forecasting,2025.0,Transactions on Computer Science and Intelligent Systems Research,Kai-Lin Wang,"This study aims to compare the performance of different machine learning algorithms in predicting housing prices and to construct an experimental process based on data preprocessing, feature selection, and comparative analysis of multiple regression models. Initially, a Random Forest will filter out the ten most significant variables. This variable will be utilized to build Multivariable Linear Regression (MLR). To find the best subset, lasso, best subset, and 5-fold Cross-Validation methods will be applied to find the final model. At the same time, this study incorporates training and testing using models such as K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Bagging, Random Forest (RF), Boosting, and Bayesian Additive Regression Trees (BART). By comparing the error performance of the model on the training set and the test set, the mean squared error (MSE) will be calculated to evaluate the strengths and weaknesses of each model in housing price prediction. The goal is to find the modeling method and variable combination that best suits the data set.",0.0,https://wepub.org/index.php/TCSISR/article/download/5497/6030
9330f4fd863e820130860fa10d2d3760e538a6b8,10.18074/ckuiibfd.1662815,Economic Determinants of Refugees and Asylum Seekers’ Work Intentions in Türkiye,2026.0,Çankırı Karatekin Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi,Muhittin Arkadaş; Serkan Dilek,"Since the beginning of the 21st century, political and social variables in countries such as Syria, Afghanistan, and Iraq have initiated a major wave of migration to Türkiye. This wave of migration is perceived to have caused various economic problems, such as increases in housing prices, rents, and employment challenges. However, it has also created an opportunity for Türkiye, whose population is starting to age, to meet its workforce needs and establish new enterprises. Some refugees and asylum seekers in Türkiye wish to migrate to Europe. The collapse of the Assad regime in Syria has also opened the possibility for some Syrians to return. This study aims to reveal the factors determining the intentions of refugees and asylum seekers to stay and work in Türkiye. For this purpose, a survey was conducted among refugees and asylum seekers in Türkiye. The results concluded that satisfaction with the economic conditions in Türkiye positively affects intentions to work here, while the economic attractiveness of other countries negatively impacts those intentions.",0.0,https://dergipark.org.tr/tr/download/article-file/4712845
83a07f61e608f535a4692e926903c538ed1611ba,10.54254/2754-1169/18/20230091,An Analysis of Factors Affecting the Housing Market of San Jose Using MLR Model,2023.0,"Advances in Economics, Management and Political Sciences",Bo Yang,"This article seeks to explain the unstable curve of housing prices in San Jose by analyzing the data of factors that may affect the housing market. By previous research conducted by other scholars, we believe there were five major factors which cause the housing prices to fluctuate, which are construction costs, total population, median income, mortgage rates and crime rates. Introducing multiple linear regression (MLR) as an approach to analyze and based on the monthly data of five-years period, from 2015 to 2019, we find an increase of mortgage rates and construction costs can lead to an increase in housing prices and other factors may not affect the housing prices as expected. However, due to lacking monthly data of certain factors like total population, we use other information associated with the factors to find an approximation of the real monthly data. Hence, while the conclusion provides certain explanations of housing prices for the buyers, it is built on many assumptions and may not perfectly fit the real behaviour of the housing market of San Jose.",0.0,https://aemps.ewapublishing.org/media/e1c6d3e3f59b4189be1e7b7fca6e7b5e.marked_FFFkWNz.pdf
92f940bea14d217c9b9060395cff5d8cbaf1ef29,10.54691/bcpbm.v32i.2945,The Influence of the COVID-19 on Hong Kong Housing Price,2022.0,BCP Business & Management,Shenjun Liu,"This article mainly discusses the impact of the epidemic on housing prices in Hong Kong. Today, COVID-19 is still a pandemic with a high impact on a global scale, affecting people's lives in many ways. Compared with before the epidemic, Hong Kong housing prices have a certain downward trend. The purpose of this study is to explore the proportion of the epidemic and the factors that are mainly affected by the epidemic. Through the correlation analysis and regression analysis of the house price index, the price index and the impact of real estate investment, it is found that the negative impact of the current epidemic on housing prices is relatively obvious, and its impact is gradually analyzed. Finally, it is concluded that the epidemic affects the supply and demand of real estate by affecting the number of people, and ultimately affects housing prices. However, because the government and real estate developers have introduced corresponding policies to deal with the epidemic, it is difficult for the future house price expectations to be significantly reduced.",0.0,https://bcpublication.org/index.php/BM/article/download/2945/2906
71977f92d0454f114374d8e7935fc5debd79713d,10.54254/2753-8818/2025.23005,Predicting Housing Price Using Regression Analysis: A Study Based on California Housing Price,2025.0,Theoretical and Natural Science,Yiting Gu,"The purpose of the essay is to examine the factors influencing housing prices in California, which can help people to obtain a perspective to observe the US economy. This paper uses the California House Price dataset to analyze the factors influencing house prices of blocks of California by performing correlation analysis and multiple linear regression. From the analyses, it is discovered that median income has the strongest correlation with median house price of blocks in California. A model predicting California house prices is also shown. It is observed that median income has the most significant correlation with median housing price in California from the correlation analysis. Additionally, the linear regression model is obtained to estimate the housing prices, with a good fit of the R2 value at 0.637. Though the issue of multicollinearity occurs, this model still provides an insight into explaining housing prices in California. For a more advanced housing price predicting model, this variable and other factors of blocks in California may be included.",0.0,https://www.ewadirect.com/proceedings/tns/article/view/23005/pdf
44517755c481953c8725d3d3d8d06b6fc14f1b6a,10.54097/hkgqcv31,Analysis of the Influencing Factors and Predictions of Poston house Prices based on a Multiple Linear Regression Model,2024.0,Highlights in Science Engineering and Technology,Liangyu Jiang,"In this study, the classic Boston house price data set is selected for the analysis of house price correlation. According to the variables in the Boston housing price data set, the linear regression model of Boston housing prices is established by using Python software. The regression equation and regression coefficient were tested for significance, excluding the variable of p >=0.5, multiple linear regression was carried out, and the regression equation with good fitting was obtained. It is found that there are too many variables after multiple linear regression, which is difficult to analyze and predict, so the correlation analysis of variables is carried out. This paper gets the percentage of lower status population, pupil-teacher ratio and average number of rooms per dwelling with medv (The median quoted price for an owner-occupied home, $1,000 per unit) has a significant relationship. Finally, a linear regression equation is established for the independent variable whose correlation coefficient is greater than 0.5, and the housing price is predicted.",0.0,http://dx.doi.org/10.54097/hkgqcv31
98d37d13904a710c80bd280e84d0c91e06a95ddb,10.54691/bcpbm.v38i.3766,Russian housing price forecast based on BP neural Network,2023.0,BCP Business & Management,Si-Di Du; Xi-Qing Liu; S. Shi; Guan-Chen Zhou,"Contemporarily, Russia's real estate market has huge potential for investors. The purpose of this paper is to investigated the impact of various factors on the real estate market price based on various statistical models. We collected past housing price data from the Internet. Subsequently, PCA model was adopted to reduce the dimension of the data to simplify the calculation. Finally, the BP model is implemented to predict the price changes in the real estate market. After calculation, our forecast data and the reality of housing prices are slightly different, but the forecast of the real estate market is consistent with the reality. In order to further find the influence of various factors on housing price, we also calculated the characteristic importance of different factors and found the most important influencing factor, i.e., the region. These results can provide investors with an idea to analyze the real estate market prices, and help policy makers find the real estate market prices in line with the market rules to avoid the occurrence of bubbles.",0.0,https://bcpublication.org/index.php/BM/article/download/3766/3677
8f96caf1524ec200bf310b65044454a6a4cf27c6,10.15439/2026f2863,Enhancing Automated Valuation Models with LLM-based Feature Engineering and Spatial Indices and a RAG-Integrated Web Application for Trójmiasto Residential Market,2026.0,Conference on Computer Science and Information Systems,Piotr Kłopotowski; Olgun Aydın,"This paper presents a methodology for building robust Automated Valuation Models (AVMs) for residential properties in the Tricity (Gdańsk, Gdynia, Sopot) metropolitan area. Utilising a dataset of over 54,000 listings scraped over a nine-month period. We proposed an enriched feature engineering pipeline that integrates spatial indices (Points of Interest and public transport proximity) with unstructured data extracted via Large Language Models (LLMs). We evaluated the performance of XGBoost and random forest algorithms for both sale and rental price prediction. Results indicate that while traditional features like size and location remain dominant, the inclusion of custom spatial indices and LLM-extracted variables, such as utility fees for rentals, provides measurable improvements in model precision. Additionally, the paper focuses on a web application for analysing the residential market and outlines a practical application of RAG implementation for enhanced residential listing search based on the description of listings through the web application.",0.0,https://annals-csis.org/Volume_47/drp/pdf/2863.pdf
8c8bc7e39e4a080c70755cc6826e0eb9ba14b7a6,10.33650/coreai.v7i1.13234,"Comparative Analysis of Decision Tree, Neural Network, K-NN, GBT, SVR and Random Forest Algorithms for House Price Prediction",2026.0,"COREAI: Jurnal Kecerdasan Buatan, Komputasi dan Teknologi Informasi",Sahal Abdillah; Mochamad Taufiqurrochman Abdul Aziz Zein; Edy Sulistiyanto,"This study aims to analyze and compare the performance of several machine learning algorithms for predicting house prices. The dataset was obtained from Kaggle with variables of house price, building area, land area, number of bedrooms, number of bathrooms, and garage. The algorithms used include Decision Tree, Neural Network, K-Nearest Neighbor, Gradient Boosted Trees, Support Vector Regression, and Random Forest. The study was conducted using Altair Studio through pre-processing, training, testing, and evaluation stages based on performance, computation time, and model complexity. The results showed that K-NN obtained the best RMSE value of 0.608, followed by Neural Network 0.630, Decision Tree 0.649, Random Forest 0.656, SVR 0.662, and GBT 0.747. Based on MAE, Neural Network obtained the best value of 0.464, followed by Random Forest 0.474, Decision Tree 0.478, K-NN 0.485, SVR 0.501, and GBT 0.589. Overall, K-NN was the best model because it had the lowest RMSE, the fastest training time of 0.004 seconds, and a relatively simple model complexity.",0.0,https://ejournal.unuja.ac.id/index.php/core/article/download/13234/pdf
cf36cd731aab85d756ca55c9fd1c888f7f35f22a,10.2991/icefs-17.2017.42,The Real Estate Market Simulation Experiment about the Urban Housing Destocking Strategies,2017.0,,Yan-Wen Xu,"To stabilize the urban housing market is one of the main contents of the China national economic work in 2016. This paper, taking the third-tier city Yichang as the research object, built a simulation model of the urban real estate market based on the urban characteristics and the historical data. With the aid of this simulation model, the paper analyzed the influence of the average housing price, the household per capita disposable income and the changes in the density of resident population in the city, to the housing inventory. Furthermore, quantitative tests and analysis were made, by ways of repeated experiments, on the mechanism of action and the strength of intervention from main policy factors on the market supply and demand; the long-term effects of the de-stocking policy tools of the city were predicted and corresponding policy suggestions were brought forward, which provided references for the local government to formulate and implement, by using the big data analysis tools, the market intervention policies applicable to local conditions.",0.0,https://download.atlantis-press.com/article/25871987.pdf
72e7e493ce04caee9a71609f72beaa04827b0340,10.54691/bcpbm.v30i.2497,How does the Macro Policy work in Housing Market of China?,2022.0,BCP Business & Management,Runnan Dai; Weiheng Lu; Chen-Jia Zhang; H. Deng,"China's housing industry is booming, but it is in its start-up stage, which, together with the complexity of the real estate market, has led to various problems in the real estate market, seriously affecting the sustainable, stable and health development of the real estate market. This study starts from defining the connotation of the health of real estate market, using quantitative analysis tools such as ITS regression analysis, referring to existing research results, and taking into account the characteristics of the domestic real estate market, to establish the concept of the health of real estate market, and to study the correlation between the health of real estate market and various macroeconomic influencing factors. The empirical results find that only housing policy and financial policy have substantial effects on housing prices in the short term. In the long run, none of the four major policies in the empirical results has a long-run effect on the selected dependent variable. Finally, policy recommendations are proposed for the government.",0.0,https://bcpublication.org/index.php/BM/article/download/2497/2470
a072fb43e67fcc553e457777f0c68324ace19eb7,10.54254/2753-8818/51/2024ch0174,Factors influencing housing prices: A comparative study using multiple linear regression and random forest,2024.0,Theoretical and Natural Science,Shutong Zhong,"Abstract. The method is to construct a multiple linear regression model to examine the variables that significantly affect US home prices. The dataset has 13 variables and 545 observations, and it was obtained via Kaggle. This paper also considers comparing the multiple linear regression models and random forest model for predicting house prices and thus concludes which model can most accurately predict house prices. The result indicates that the factors including area, quantity of bedrooms and bathrooms, the existence of a basement, and state of the furnishings, etc. significantly impact housing prices. By comparing Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE), the conclusion suggests that the multiple linear regression model marginally surpasses the random forest regarding the accuracy of the predictions, despite the fact that both models function similarly. This research offers practical applications for enhancing real estate market strategies and provides valuable insights into the factors influencing housing prices.",0.0,https://www.ewadirect.com/proceedings/tns/article/view/16390/pdf
b38db270009a661fd70f21af2f1aef85bff1b9a3,10.32920/ryerson.14644665.v1,Identifying the variance in the magnitude of landfill impacts on residential property values using multiple regression analysis,2021.0,,Jong-Seok Lim,"The economic advantage of constructing and operating large-scale landfills over small-scale landfills has been used to justify regional landfills as the solution to the municipal waste management problem. However, the availability of sufficient landfill capacity will have dampening effects on the social efforts to reduce waste and/or divert waste away from landfills, especially when external costs of landfills are not appropriately reflected in the estimation of total costs. In this study, the negative effects of a landfill that are capitalized in property values of houses located in the proximity of two landfill sites (""Britannia"" and ""Keele"" landfill sites representing a small and a large landfill respectively) in the Greater Toronto Area are examined in a single multiple regression equation. The results indicate that the large landfill has greater adverse impacts than the small landfill on property values. This study suggests further analysis in a model to which more independent variables that explain locational characteristics should be added.",0.0,https://rshare.library.ryerson.ca/articles/thesis/Identifying_the_variance_in_the_magnitude_of_landfill_impacts_on_residential_property_values_using_multiple_regression_analysis/14644665/1/files/28123641.pdf
9c5081d6866b460fbe9fb9ff7c1773f638932bea,10.5220/0013214400004568,Forecast Analysis of Urban Housing Prices in China Based on Multiple Models,2024.0,Proceedings of the 1st International Conference on E-commerce and Artificial Intelligence,Ze-Lin Qu,": Social attention has long been focused on the cost of housing in China. Rising urbanization and quick economic growth have made housing costs crucial to social stability and the standard of living for locals. This study compared the performance of four machine learning models - eXtreme Gradient Boosting (XGBoost), Support Vector Regression (SVR), Multi-Layer Perceptron (MLP), and Long Short-Term Memory network (LSTM) - in detail in order to increase the accuracy of housing price prediction. The models were then combined with nominal GDP data to forecast housing price. The experimental findings demonstrate that the XGBoost model, which is used to forecast future home prices, performs well across a range of evaluation indices. In addition, this study predicts that housing prices in Chinese cities will show a slight upward trend in 2024-2025. This study fills the gap of the existing research in comparing and integrating multiple models and provides a reference for the government to make more accurate real estate policies and investors' decisions.",0.0,https://doi.org/10.5220/0013214400004568
a3b90c148c9d865a1a19466cd292bb25b14e13e3,10.54254/2755-2721/2027.melb37705,A Data-Driven Analysis of Housing Consumption Patterns: Evidence from King County,2026.0,Applied and Computational Engineering,Zi-Han Huang,"Housing is one of the biggest expenses for most households, so changes in how people consume housing can tell us a lot about broader trends in consumption and upgrading. This paper uses a dataset of housing sales in King County, Washington, to explore what factors influence housing prices and what these patterns say about consumer behaviour. The analysis uses descriptive statistics, correlation analysis, and multiple linear regression to identify the key drivers of housing prices. The results show that living area (r = 0.702) and waterfront status are the strongest predictors of price, followed by property grade and view quality. However, the year the house was built does not have a strong effect on price once other factors are accounted for, which suggests that consumers care more about quality and location than about whether a property is brand new. These findings suggest that housing consumption upgrading is less about buying newer houses and more about buying better houses, which has more space, better views, and higher quality construction.",0.0,https://ace.ewapub.com/article/view/37705.pdf
9f976eb27a264362a24f0617056e6778161bf590,10.1109/agers67633.2025.11446448,Geospatial Modeling of House Price Using MGWRSAR: A Case Study in DKI Jakarta,2025.0,"2025 IEEE Asia-Pacific Conference on Geoscience, Electronics and Remote Sensing Technology (AGERS)",Yenro P Sagala; Sutikno; A. Choiruddin,"The dynamics of house prices in Jakarta are influenced by both spatial dependence and spatial heterogeneity. Conventional models, including the Spatial Autoregressive (SAR) and Geographically Weighted Regression (GWR), are only capable of partial capture of these effects, which often result in model misspecification. The present study employs the Mixed Geographically Weighted Regression-Spatial Autoregressive (MGWR-SAR) model to concurrently address the spatial dependence and heterogeneity in house price determinants. We used a dataset of houses listed in 2024, incorporating house and location characteristics. The construction of spatial dependence weight matrix was based on semi-variogram analysis, and optimal kernel bandwidths were selected using cross-validation method. The model is estimated using The Spatial Two-Stage Least Square (S2SLS) approach to address endogeneity in spatial lag component. The findings of the study indicate that the land and building area are the most significant price determinants, with spatial variation in their influence across Jakarta’s subregions. Jakarta Pusat exhibits stronger spatial spillovers, while Southern district demonstrates heightened sen",0.0,
aca827a44946c0dc878d8de333a8c36f6a9b1b9a,10.1145/3650215.3650228,Exploration of House Price Prediction Based on ICS-BP Neural Network,2023.0,ICMLCA,Dong Luo,"Since the real estate market is a complex, non-linear system with uncertainty and high complexity, house price forecasting is an important issue in the analysis and management of the real estate market. In house price forecasting, it is mainly faced with the complexity of the relationship between house price factors and the unsteadiness of house price data. In order to solve the above problems, the article adopts a BP (Back Propaganda) neural network model based on ICS (Improved Cuckoo Search). First, ICS is used to perform dimensionality reduction processing on house price factors, and then the dimensionality reduction house price factors are input into the BP neural network model, and the final prediction results are obtained by training and predicting the data. The results show that the accuracy of the model's prediction of house price data can reach an average of 92.54%, which is not only applicable to the prediction of actual data, but also provides an effective and feasible method for the analysis and management of the real estate market.",0.0,https://dl.acm.org/doi/pdf/10.1145/3650215.3650228
9f285e5d9b32487e96694c7e27eaff923c8f90a9,10.23977/ferm.2023.061020,Research on the Influencing Factors of House Prices in Beijing Based on Regression Analysis,2023.0,Financial Engineering and Risk Management,T. Mai,": China's housing prices have always fluctuated as the economy grows, especially in large cities. The fluctuation of housing prices is affected by many factors, and the housing problem is related to the national economy and people's livelihood. Therefore, housing prices are widely considered and studied by many scholars. In this paper, we take the average price of commercial housing in Beijing from 2010 to 2020 as the explanatory variable and the real disposable income of Beijing residents, the total population and the number of employed persons in all units as the explanatory variables and set up a linear regression model to analyze its effect on house prices. The study results show that real disposable income and the number of employed persons in all units will significantly and positively affect the average commercial housing sales price; the total population will significantly and negatively affect the average commercial housing sales price. Taking the above factors as a reference can help to predict the future fluctuation of house prices.",0.0,http://www.clausiuspress.com/assets/default/article/2023/11/19/article_1700391828.pdf
4bb533630c8e8706ca12a1311c21806870356f8e,10.20885/ajie.vol4.iss3.art6,PELUANG PEMILIKAN PERUMAHAN GRIYA PESONA ASRI DI KECAMATAN SIDOHARJO SRAGEN JAWA TENGAH,2015.0,,Unggul Priyadi; Fathya Rahmadhani Zainuri,"Sidoharjo Sragen is the entrance gate to the Capital District of Sragen. So many Access of the traders passing by in the district of sidoharjo cause of the increasing demand for houses and it also encourages the developers to build housing. This also happens to Griya Pesona Asri which is located at the gate of Sragen. This research is aimed to analyze the influence of housing price, comsumer income, facilities, and the types of jobs towards the opportunities of housing purchase in Griya Pesona Asri. The analytical tool which is used is LPM (Linear Probability Model) regression. The respondents in this study are the residents of Griya Pesona Asri. The results show that the price of the housing gives significant and negative effects towards the modest housing purchase opportunities or the other than modest in Griya Pesona Asri. The income of the customers has negative effect and significant on the modest housing purchase opportunities or the other than modest in Griya Pesona Asri. Keywords: LPM, Housing Purchase Opportunities, Griya Pesona Asri",0.0,https://doi.org/10.20885/ajie.vol4.iss3.art6
361adf3957fe909775ffd4f5ddfdcf17a1fc669d,10.11361/reportscpij.17.2_129,Fundamental Analysis of Assessment Formula for Business Improvement District,2018.0,Reports of the City Planning Institute of Japan,Tomoki Kitazaki,"The purpose of this paper is to clarify the details of assessment formula for Business Improvement District (BID) intended to promote a local economy and community. All BIDs in New York City set the levy on property owners, while some BIDs in Seattle City require the levy on business owners. The calculation of the individual levy is based on the square footage of a lot, an assessed property value, a lot size, a building floor area, or gross retail sales. Some BIDs calculate it by using multiple assessment factors. In addition, the types of assessment formula depend on the neighborhood characteristics, and the levy of BIDs in a central area or business area tends to be calculated by an assessed value, a building floor area, or a lot size. On the hand, BIDs in a commercial area or residential area often use the square footage of a lot. The burden level based on the square footage of a commercial area’s BID in New York City is slightly higher than others; however, there is no significant difference in the burden levels of BID among other areas.",0.0,https://www.jstage.jst.go.jp/article/reportscpij/17/2/17_129/_pdf
dce75a908baa43004c013241c9157a3060040eff,10.1038/s41597-026-07012-w,Large-scale modeling for housing condition prediction using machine learning algorithms,2026.0,Scientific Data,Kyusik Kim; T. Holmes; Emily Powell; C. Uejio,"While housing price prediction is well-studied, the prediction of large-scale housing conditions remains underexplored due to data limitations. This paper addresses this gap by developing a machine-learning model to predict housing conditions across the United States. We integrated property-level data from the Warren Group with neighborhood characteristics from the U.S. Census Bureau’s American Community Survey and trained three gradient-boosting algorithms: CatBoost, LightGBM, and XGBoost. Despite XGBoost’s slightly higher balanced accuracy, CatBoost was selected as the best model due to its superior resistance to overfitting. The final model’s predictions were aggregated to census tracts, ZIP code tabulation areas, and a 36.13 km2 resolution hexagonal grid for national-scale spatial analysis. The resulting comprehensive dataset can serve as a valuable resource for researchers and practitioners to analyze the geography of housing quality with applications in urban planning, disaster management, community resilience, public health, and more.",0.0,https://www.nature.com/articles/s41597-026-07012-w_reference.pdf
996b2020f7a48580738ba05aee16af6057ae4480,10.3390/buildings16030530,The Impact of Distorted Land Supply Structures on Green Economic Growth in Chinese Cities: The Moderating Role of Housing Prices,2026.0,Buildings,Ri-Ping Ling; Xiaoqi Liu; Chengdong Yi,"This study investigates the impact mechanism of distorted land supply structures on green economic efficiency in Chinese cities, with a particular focus on the mediating and moderating role of the real estate market. Innovatively, the study constructs a comprehensive index to measure land supply structure distortion and employs spatial econometric methods for empirical analysis using panel data from 285 prefecture-level and above cities in China from 2010 to 2022. The findings reveal that: (1) distortions in land supply structure significantly hinder the improvement of urban green economic efficiency (GEE); (2) this inhibitory effect exhibits a significant spatial spillover effect; (3) housing prices play a notable mediating and moderating role in the relationship between land supply structure distortion and green economic efficiency; (4) the impact mechanisms demonstrate significant regional heterogeneity. These findings offer important policy implications for optimizing urban land supply structures and promoting green economic development.",0.0,https://www.mdpi.com/2075-5309/16/3/530/pdf?version=1769594822
47ec3dc1307d848088ad86e8a14453fae05148f1,10.5055/jem.2008.0006,An examination of FEMA’s temporary emergency housing program and the criteria used to make site selections in post-Katrina New Orleans,2008.0,Journal of Emergency Management,M. Reams; P. Chandler,"The authors examine the Federal Emergency Management Agency’s (FEMA’s) emergency temporary housing program and its implementation in Orleans Parish during the first months after Hurricane Katrina. They identify environmental and demographic factors that may have influenced the selection of sites for temporary trailer parks. The environmental assessments for each of the sites considered for use were obtained directly from FEMA under the Freedom of Information Act. Socioeconomic characteristics of the communities near the proposed sites were gathered from the US Census Bureau. Using cross-tabulations and difference-of-means tests to make comparisons between the sites selected and those not selected, the authors identify several environmental and socioeconomic factors associated with site selection. None of the selected sites was found to be in an area designated as residential nor were any sites selected that possessed known hazardous wastes or materials or contained habitat critical to endangered species. Also, all of the selected developments involved the installation of fewer than one hundred trailers. The analysis suggests that the trailer parks tended to be built in zip-code are",0.0,
851446578631df506855b95d986da9829258f808,10.2139/ssrn.6660401,Banking Crises and Macroeconomic Forces: Global Perspectives,2026.0,Social Science Research Network,TR Timilsina,"This study examines the likelihood of banking crises employing the logistic regression approach. The data is sourced from the Global Macro Database, a comprehensive macroeconomic time series repository covering 243 countries and territories. The findings suggest that GDP growth reduces the probability of banking crises, and conversely, tight monetary policy increases the likelihood. Likewise, appreciation in housing prices in the current period lowers the risk; however, the housing price in the past increases the probability of crises. The other control variables are money supply, sustainable public finance, and favorable current account balance, which significantly lower the probability of a crisis. Policymakers should strive to balance fiscal and monetary measures for sustainable growth and implement macro-prudential regulations to prevent excessive speculation in the asset market. Timely consideration of short-term and long-term risk factors strengthens financial stability and minimizes the probability of banking crises in the future.",0.0,https://doi.org/10.2139/ssrn.6660401
797cf92743ec2a701534e459e6738ef4c06bdc89,10.2139/ssrn.6443200,Immigration and Regional House Prices in Iceland: Evidence from Transaction Data,2026.0,Social Science Research Network,Erlendur Jónsson,"This paper uses transaction-level data from Registers Iceland covering 225,000 residential sales across 60 Icelandic municipalities (58 retained in the merged panel) from 2006 to 2024, to examine the association between immigration and house prices. The central finding is a null result: in firstdifference panel regressions with year fixed effects, neither the capital region nor outside capital municipalities show a statistically significant association between changes in the immigrant share and changes in the price per square metre. A secondary finding is methodological: a positive and significant association found in aggregate regional price data disappears once year fixed effects absorb common time trends, illustrating how omitted variable bias from common time trends can produce spurious associations in aggregate regional data. One likely explanation is thin transaction markets outside the capital, where 63% of municipality-year cells contain fewer than ten sales, making annual mean prices too noisy to reveal a reliable price signal.",0.0,https://doi.org/10.2139/ssrn.6443200
a482b4f2dafe28ba25f09bae8deabba2d3a41599,10.54097/qywqx033,"Predicting House Prices with Machine Learning: A Comparative Study of Linear, Lasso, and Ridge Regression",2026.0,Academic Journal of Science and Technology,Han Hu,"Machine Learning has seen rapid advancements this decade, marked by daily innovations in applications and algorithms. One significant application is in the real estate sector, particularly in predicting house prices—a crucial task given the continual rise in property values. This project employs Linear Regression, Lasso Regression, and Ridge Regression, utilizing the Scikit-Learn tool to explore the potential of these models. By considering various factors such as the number of bedrooms, the age of the house, proximity to transportation hubs, local schools, and shopping centers, these models aim to assist potential buyers in identifying homes that best meet their requirements. Among the tested methods, the Lasso Regression emerged as the most effective, boasting the lowest root-mean-square error of 190,124.751, which notably outperformed both Ridge and Linear Regression. This outcome not only underscores the efficacy of Lasso Regression but also highlights the overall utility of regression models in accurately predicting house prices.",0.0,https://drpress.org/ojs/index.php/ajst/article/download/33361/32645
5c5c506192e9ac6e15bbe6d910ab1dddb0d215cd,10.54097/fh050a12,Investigating Factors Affecting House Prices - Chicago as an Example,2024.0,Highlights in Science Engineering and Technology,Chen Qian,"House is a very important necessity in human society and its price is also highly concerned. With the rapid development of the society, the house price is also rising rapidly, how to find some favourable ways to buy a house is very important for people. This paper will firstly analyse the relationship between house price and some factors by grouping them with box-and-line diagrams, then further calculate the correlation coefficients between the factors and house price, and further correlate the factors with house price. After that, this paper will use multiple linear regression to analyse the relationship using house price as y and other eight variables as x. After that, this paper will conclude that Space, Garage, Bathroom, Lot will have a substantial positive impact on the price. The price will have a significant negative effect due to the bedroom. But Room, Condition, Tax will not have any effect on Price. Finally, this paper will summaries the results of the analysis and provide some preferred methods for people to buy houses.",0.0,http://dx.doi.org/10.54097/fh050a12
f7586d7e21935e6b933a4f4b90eb2535663f4c78,10.2478/crebss-2022-0010,Tourism housing price nexus,2022.0,"Croatian Review of Economic, Business and Social Statistics",A. Č. Časni; Josipa Filić,"Abstract Tourism’s positive and negative externalities are of an extreme social and economic importance for the tourism dominant countries. In particular, studying tourism’s impact on housing prices has experienced increased interest over the past decade as it has a relevant influence on real estate economics and housing market development, which spills over the entire economy. Considering the limited existing literature, the objective of this paper is to provide an overview of the previous studies, which summarizes prevailing findings about the impact of tourism on housing prices with respect to three different streams: tourism activity, tourism accommodation capacity and tourism amenities. This paper offers a comprehensive theoretical background and clear-cut insight in tourism’s impact on housing prices, with a great attention to possible issues that may emerge due to tourism heterogeneity across countries. For the same reason, it is beneficiary not only to real estate agents but likewise to decision makers in tourism industry.",0.0,https://sciendo.com/pdf/10.2478/crebss-2022-0010
6a14de7af006fde7527e2580027767be030a1245,10.54097/hbem.v21i.14541,Enhancing Neural Network with Particle Swarm: A House Price Prediction Case,2023.0,"Highlights in Business, Economics and Management",Yaotong Liang,"This study delves into the utilization of the Particle Swarm Optimization (PSO) algorithm to discover the best parameters of Long Short-Term Memory (LSTM) model with the aim of housing price prediction. Employing the Ames Housing dataset, our investigation underscores the remarkable efficacy of PSO in mitigating prediction errors within the LSTM framework, thereby enhancing overall predictive performance. The symbiotic integration of PSO with LSTM facilitates the discernment of intricate data patterns, particularly in scenarios involving high-dimensional and nonlinear optimization conundrums. The findings illuminate PSO's ability to expediently traverse and identify global optima. The outcomes unequivocally underscore the PSO-LSTM model's superior attributes, characterized by accelerated convergence, diminished errors, and exceptional proficiency. In summation, this investigation underscores PSO's promise as a potent technique for optimizing machine learning models, notably exemplified by its integration with the LSTM framework.",0.0,https://drpress.org/ojs/index.php/HBEM/article/download/14541/14095
2565afc9ee2e15c0daf31480b06229279a91d815,10.54254/2754-1169/2024.19450,"Study of the Factors Influencing House Prices in California, USA",2025.0,"Advances in Economics, Management and Political Sciences",Shanchuan Zeng,"The world's population is growing at a rapid pace, which has raised concerns about the real estate market. This essay seeks to identify the factors that influence the cost of homes in California, USA. The findings can help individuals have a better grasp of home pricing and the variables that greatly affect a home's final cost. This article uses eight independent factors that have a significant impact on housing prices. The dataset is analyzed using the linear regression model. The location of the home, the number of bedrooms, and the median income are among the independent variables that were employed in this study and are critical to the model's outcomes. It is also explained how to make the model more multi-linear. The paper includes a correlation analysis that is utilized to enhance the prior model. The purpose of the comparison of the two models is to ascertain the benefits and drawbacks of each. The outcome suggests that the key elements pertaining to the median house value can be explained by four fundamental variables.",0.0,https://www.ewadirect.com/proceedings/aemps/article/view/19450/pdf
27e232eeffc58b8e0a75c04f2ceb3aa6848d2746,10.1108/pm-06-2023-0048,Exploring property orientation preferences and local variations,2023.0,Property Management,Changro Lee,"PurposeProperties with specific orientations are preferred in South Korea, depending on the real estate market. This preference is usually considered during property transactions and in designing buildings. Despite the importance of property orientation, the magnitude of preference for favored orientation has rarely been empirically estimated in the literature. This study attempts to estimate the value of favored orientation in a quantitative manner and interpret the results.Design/methodology/approachUsing a geographically weighted regression model, this study obtains nationwide property price data and estimates the strength of orientation preference, that is, the premium for favored orientation. Among the various property types, residential sites and forests were investigated because the orientation of these two property types is known to influence their sales prices in the Korean real estate market.FindingsThe results show that premiums for south-facing residential sites exist in the market, varying locally and ranging from zero to 13.2%, over residential sites with non-south orientations. The results for forests are mixed in that a south-facing forest commands a maximum of 33.1",0.0,
9e0670b378f7e6384baeef40d212142bf17182db,10.54097/2nz8xe97,Research on the Relationship between Influencing Factors and House Prices Changes,2024.0,Highlights in Science Engineering and Technology,Zixuan Lyu,"In recent years, the change in house prices has also become a main factor affecting economic changes. There are lot of research shows that the relationship between economics and house prices. This study focuses on how house prices change and what factors can lead to the change in house prices. The data from the Kaggle website, containing property prices in Delhi. By using the linear regression model, calculate 12 factors which are Price, Area, Bedrooms, Bathrooms, stories, main road, guestroom, basement, hotwaterheating, airconditioning, parking, prefarea, and furnishing status to study the degree and trend of impact on house prices changes. The results show that area, bathrooms, stories, guestroom, basement, hotwaterheating, airconditioning, parking, prefarea will have a significant positive impact on price, and furnishing status will have a significant negative impact on price. Bedrooms have no impact on price. This study opens a new perspective and giving society a new thinking angle for the study of housing prices changes.",0.0,http://dx.doi.org/10.54097/2nz8xe97
cd9a9cfb7de567cb8d678f3bfe4f9f7474ce4683,10.54097/6a5ewr46,Effects of Exchange Rate Changes on Real Estate Prices in Russia During the Russian-Ukrainian War,2024.0,"Highlights in Business, Economics and Management",Zhen Han,"As a result of the Russian-Ukrainian war which started at February 24, 2022, some of Russia's economic indicators have been affected, including the ruble's exchange rate, Russia's inflation rate, and GDP. With this in mind, this paper assumes that there is a linear relationship between real estate prices and the exchange rate, inflation rate, and GDP as follows: ln_repx = ß0 + ß1 ln_exr + ß2ln_inf + ß3ln_Y + c.c.. Based on the information collected, the StataSE 15.0 tool is used to perform regression operations to derive the correlation coefficients and to explore the relationship between house prices and each price factor. Afterwards, it was concluded that under the influence of the Russian-Ukrainian war, changes in the exchange rate of the Russian domestic currency against the US dollar would have some negative impact on real estate prices. Overall, these results shed light on guiding further exploration of continuous influence from war on Russia’s real estate market and pave a path for government to make efficient response.",0.0,http://dx.doi.org/10.54097/6a5ewr46
694b274c384e1551df1768c111a249b26fe684a1,10.5220/0014361300004718,Research on the Factors Contributing to Change in Housing Price in California,2025.0,"Proceedings of the 2nd International Conference on Engineering Management, Information Technology and Intelligence",Zi-Yu Li,": Housing price is always the popular topic in the current market. To predict the alternation in housing price, it is necessary to initially forecast the trend of those influencing factors. This article aims to investigate the potential factors that influence alternation in housing prices. 20,640 samples from a dataset of California’s housing group by 1990 will be conducted in this essay to complete further analysis. Then, this research will measure correlation coefficients and employ linear regression model based on the eight variables shown from the dataset. By searching for coefficient, unstandardized beta and variance inflation factor (VIF) value, this research can conclude the most significant causes to affect housing prices. Finally, the research indicates that income level is the main feature, other causes including housing ages, location as well as population can also affect prices in some aspects. The data and purpose outcomes can provide households and housing agencies direction regarding the trend of housing market.",0.0,https://doi.org/10.5220/0014361300004718
b28a50b59ffefc2b37d659a0ee7d39d51034c798,10.54097/gcmy5277,Research on the Influencing Factors of House Prices in Sydney,2024.0,"Highlights in Business, Economics and Management",Heng Xu,"Considering various factors that affect house prices, this study investigates whether housing prices in Sydney can maintain their value or even increase in the future. A multiple linear regression model was applied using a dataset obtained from Kaggle, which includes 11,161 real estate transactions in Sydney from 2016 to 2021. This paper uses it to explore the relationship between housing prices and 12 independent variables (originally 14 but some have to be abandoned), such as the number of bedrooms, property size, median suburban income, and distance to the central business district (CBD). The results indicate that some factors have a positive, negative, or no impact on house prices and that 39.6% of the real estate price is influenced by them, indicating a moderate level of predictability. These findings provide valuable insights for investors and policymakers interested in the dynamics of the Sydney real estate market, emphasizing the importance of geographic location and property attributes in determining housing prices.",0.0,https://drpress.org/ojs/index.php/HBEM/article/download/27407/26944
90b923037f1c4b5e6a9a71f19f2d15764f1ccbf6,10.2139/ssrn.6308901,Substitutability In The Demand For Housing Over Small Distances,2026.0,Social Science Research Network,Salim B. Furth,"Some pairs of residential locations are better substitutes for one another than others, perhaps even within two hundred meters' distance. As a result, rents and home prices can behave in ways that depart from the predictions of the most common urban economics models. The imperfect and varying substitutability between locations may arise due to preferences, information, or moving costs. Literatures in economics and complementary disciplines offer indirect evidence on the spatial substitutability of housing, homebuyers' housing search processes, and the information accessed by housing searchers. The available evidence suggests that spatial substitutability varies from place to place, is non-monotonic across space, and is endogenous to market conditions. Housing searchers vary widely, and their diversity can produce market outcomes that differ substantially from those predicted by models where all searchers are the same. Spatial substitutability has implications for policy debates around gentrification, market power, and zoning.",0.0,https://doi.org/10.2139/ssrn.6308901
2ef589a2560d5f43fe4591a742ca78c152a82db5,10.53894/ijirss.v8i3.6982,"Dynamic price estimation model for residential buildings per square meter in Surabaya: Analyzing the impact of construction costs, material quality, and Land Area",2025.0,International journal of innovative research and scientific studies,Kusnan Kusnan; Naniek Widayati; Dadang M. Ma’some,"This study develops a dynamic price estimation model for residential buildings per square meter in Surabaya, focusing on key variables such as construction costs, material quality, land area, and building size. Using multiple linear regression analysis and the backward elimination method, this research identifies the most significant factors that influence housing prices in urban and suburban areas. The results show that construction costs and material quality have a positive impact on housing prices, while land area exhibits an inverse relationship with the price per square meter, particularly in peripheral areas of the city. The final model achieved an R² value of 0.685, indicating strong explanatory power. The findings provide valuable insights for real estate developers, policymakers, and urban planners in optimizing housing development strategies, promoting affordable housing, and improving market transparency in rapidly urbanizing regions. This model can be applied in other emerging markets with similar urban dynamics.",0.0,http://www.ijirss.com/index.php/ijirss/article/download/6982/1423
6c8ab7d65de723a6251815cc009c423e1d770405,10.1109/i3ceet61722.2024.10994003,Data-Driven Home Price Prediction: Leveraging Machine Learning for Accurate Market Valuation,2024.0,"2024 International Conference on Communication, Computing and Energy Efficient Technologies (I3CEET)",Jaswinder Singh; S. Mishra,"This study combines machine learning algorithms with several real-count implementations to accurately anticipate the market value of residential properties. The dynamic nature of the freehold market and the complexity of variables influencing property values need sophisticated computational tools for educated, data-driven projections. The sophisticated method integrates a varied array of characteristics, including property qualities, location-based elements, economic metrics, and historical sales information, to provide a conceptual statistic for training and evaluation. Feature engineering techniques are used to derive significant insights from unprocessed data, improving the predictive efficacy of the model. Techniques for forecasting residential property values using machine learning methodologies, including linear regression, decision trees, random forests, gradient boosting, and neural networks, are examined and contrasted to choose the most effective model for precise forecasts. A stringent assessment procedure is used to appraise the models' efficacy, using measures such as mean absolute error (MAE), mean squared error (MSE), and R-squared (R2) to guarantee dependable outcom",0.0,
f450a9f901c1a5de07fbd7b3d0c24dafa5a06935,10.54097/hbem.v20i.13308,Study On Influencing Factors of Real Estate Price Fluctuation from The Perspective of Behavioral Economics,2023.0,"Highlights in Business, Economics and Management",Ruyu Huang,"Due to the dual attributes of investment attribute and consumption attribute of real estate, its price volatility is more complex than that of ordinary investment goods and consumer goods. It has always been the object of close attention of real estate market researchers, policy makers, investors and people who have the need to buy a house. Starting from the theory of behavioral economics, this paper analyzes the impact of investors' behavior difference on housing price fluctuation in the real estate market. This paper selects the monthly data of Nanjing, Suzhou, Changzhou and Wuxi from 2011 to 2020 and uses the heterogeneity expectation model for empirical analysis. The results show that, different from super first-tier cities such as Beijing, Shanghai, Guangzhou and Shenzhen, fundamental investors have the power to restore the housing price to the benchmark housing price, while trend investors will not push the housing price further offset. The fluctuation of housing prices are more dependent on fundamental investors.",0.0,https://drpress.org/ojs/index.php/HBEM/article/download/13308/12938
903af78176b3e67aa98ed7a3f41f59770eb46e54,10.1108/pm-08-2024-0088,"Dynamics of residential property values along rail line – a case of Kubwa station, Abuja, Nigeria",2025.0,Property Management,E. Komolafe; A. Oyetunji; Oyindamola 'Semilore Fawunmi,"PurposeUrbanization is transforming cities worldwide, with rapid growth and expansion being particularly evident in Nigerian cities like Abuja. The introduction of transportation infrastructure is a significant factor influencing rent dynamics. This paper is aimed at understanding the evolving patterns of rent at transportation hubs such as train stations, using the Abuja-Kaduna railway line in Nigeria as a representative case.Design/methodology/approachRental values of residential properties within a 3 km radius of the station before, during and after construction (between 2005 and 2023) were obtained from estate surveyors and valuers, who are property managers in Nigeria. Least squares regression and analysis of growth rate were used to analyze the data obtained.FindingsIt was found that the construction and operation of the Kubwa Train Station have led to substantial increases in the rental values of residential properties within its vicinity. Also, transportation infrastructure like rail stations leads to an increase in rental value.Practical implicationsThe study advises policymakers and urban planners to give precedence to investments in sustainable transportation infrastruct",0.0,
9fd1705c1b9e7c404cf28792e62c1ec15dde9998,10.1088/1757-899x/780/7/072054,Analysing the Differentiation of Housing Price Influence Based on PCA Clustering-Entropy Weight Method: A Case Study in Sichuan,2020.0,IOP Conference Series: Materials Science and Engineering,Xue-Dong Liang; Qian Lu,"The immobility of real estate products and the regional nature of the consumption of real estate products make the real estate industry have obvious regional characteristics. The current policy adjustments in the real estate market emphasize differentiation, that is, the regulation methods of each city are becoming more and more different, not only because of the policy of the city, but also the policy of the district. For exploring the basis of differential regulation, the article takes Sichuan Province of China as an example. Through the selection of four first-level indicators and thirteen secondary indicators, 21 cities (districts) are divided into four types of areas. Then the entropy method is used to obtain the factors that affect the housing prices in each category. Based on these, it is suggested to improve the real estate market related policies from the three aspects: promoting the construction of the housing rental market, guiding the rational expectations of buyers and correctly guiding the flow of people.",0.0,https://iopscience.iop.org/article/10.1088/1757-899X/780/7/072054/pdf
0a4bbb3c94d7c3cd33168581496411d487f86c81,10.1145/3677779.3677782,Topic Identification and Emotional Analysis of the Real Estate Favorable Policies Based on Text Mining,2024.0,"Proceedings of the International Conference on Modeling, Natural Language Processing and Machine Learning",Jiangnan Xu,"It is of great significance for the country's future policy designation and social development to explore the topic distribution and emotional tendency of people's comments on favorable real estate policies. Based on this, this paper first crawls the comments on the favorable policies of real estate on Weibo, uses the LDA topic model to identify the topics that people pay attention to, and reveals ten topics that people are mainly concerned about. After training the Naive Bayesian model, the positive and negative emotions under each LDA topic are analysed, and the statistical results of individuals’ emotional tendencies under different topics are displayed. This study finds that for some topics, such as stock market plate and individual stock analysis, the number of positive emotional texts is significantly greater than that of negative emotional texts, which indicates that people have a positive attitude towards the impact of favorable real estate policies in these aspects. However, in terms of topics such as real estate market trends and investment analysis, the number of negative texts is more than the number of positive texts, reflecting the public's concern about the current r",0.0,
c52e611665e6d95e655abca687626b44f8eaf37d,10.54254/2753-8818/52/2024ch0140,Research on housing prices prediction-take Boston as an example,2024.0,Theoretical and Natural Science,Bo-Xuan Liu,"The problem of predicting Boston housing prices belongs to the field of artificial intelligence, specifically in the domain of regression problems, which is a crucial area of study in machine learning. This article aims to get an accurate prediction model of Boston housing prices by comparing four regression models based on the datasets derived from StabLib library. Multiple Linear Regression model, Random Forest Regression model, Extreme Gradient Boosting Regression model and Support Vector Machine Regression model are taken into consideration. Five evaluation index R-squared, adjusted R-squared, mean absolute error, mean squared error and root mean squared error are compared in terms of generalization ability of model. Eventually, Extreme Gradient Boosting Regression model was found to be the most effective model when predicting housing prices in Boston. The model has certain positive applications in real life, which can help government formulate real estate policies and people make wiser house purchasing strategies.",0.0,https://tns.ewapub.com/article/view/15617.pdf
09311ef001f7b5c51f7c1244e5dd7cad09ed144b,10.35870/jemsi.v12i2.5804,Profitabilitas Skala: Analisis Komparatif Kinerja Keuangan Usaha Kost,2026.0,"JEMSI (Jurnal Ekonomi, Manajemen, dan Akuntansi)",Iman Putra Jaya Ndraha; K. S. Nugraheni,"The boarding house business is a rapidly growing residential rental property sector but has received minimal research from its financial management aspect. This study analyzes the financial performance of three boarding house business models in the Bawen-Ambarawa area using descriptive analysis and financial ratio calculations (NPM, OER, ROI). Data were collected through observation, interviews, and documentation of monthly financial reports for three months. The analysis shows a ""Profitability of Scale"" divided into two: the large-scale San Boarding House (33 rooms) with premium prices achieved the highest absolute profit and superior ROI (22.04%), while the smallest-scale Tri Boarding House (7 rooms) with the lowest price recorded the highest Net Profit Margin (NPM) (68.14%) due to extreme cost efficiency. These findings confirm that cost management efficiency (OER) is a determinant of margin, while the combination of large scale and premium pricing strategies determines profit volume and total return on investment.",0.0,https://doi.org/10.35870/jemsi.v12i2.5804
3fe9779bc5ed68ec00d0a7c7dcf3b20fe62799b5,10.36948/ijfmr.2026.v08i02.73152,Exploring House Prices and Features with Tableau,2026.0,International Journal For Multidisciplinary Research,Koppula Purna Venkateswara Rao; P. Sravani; Porumalla Gowthami; Chandragiri Veeraswamy; Mutyala Satish,"The real estate sector requires accurate housing price estimation for effective decision making. Traditional property valuation methods are often manual and inefficient. With the availability of large real estate datasets, data analytics and machine learning techniques can improve housing market analysis and price prediction.

This study proposes a housing price prediction and visualization system that integrates Tableau dashboards with machine learning models. Tableau is used to visualize housing market trends, while algorithms such as Linear Regression, KNN, and Random Forest are applied to predict housing prices. The dataset is preprocessed, and models are evaluated using MAE, RMSE, and R² Score.

The trained model is deployed using a Flask web application, where users can input property details and obtain predicted prices. The system also provides future price estimation and profit analysis based on growth rate. The proposed system enables effective housing market analysis and supports data-driven decision making.",0.0,https://www.ijfmr.com/papers/2026/2/73152.pdf
e516fc960cfa674d5a5e76753c21255c13f90eed,10.54254/2753-8818/38/20240542,Research on factors influencing housing price index-take the USA as an example,2024.0,Theoretical and Natural Science,Jun Yu; Min Zhan,"This article aims to identify the factors that have an impact on housing prices. The significance factors of 241 samples from the United States from 2003 to 2022 were analyzed using multiple linear regression method. Based on a hypothesis, the selected 5 variables are indeed related to housing prices. This article also collected a lot of other data related to the housing price index for multivariate judgment analysis, and used exploratory factors to test the research significance of each variable. To test the effectiveness of this operation, the study compared the VIF values and significance of these variables. The conclusion is that correlation analysis has been used to test the relationship between DATE and five variables: income, housing subsidies, unemployment rate, unsold or sold houses and total houses, as well as the magnitude of the impact of these factors on the housing price index. Overall, the volatility of the US housing price index can be considered based on the degree to which these factors affect it.",0.0,https://www.ewadirect.com/proceedings/tns/article/view/13302/pdf
60ac4b2aae16b336521c90133ede309c8e7a555b,10.2337/db25-1114-p,1114-P: Geospatial Analysis to Incorporate Neighborhood Characteristics and Socioeconomic Status into Diabetes Outcomes and Disparity Research,2025.0,Diabetes,Kibum Kim; Sodam Kim; A. Jalali,"Introduction and Objective: We explored the potential of geospatial analysis (GSA)-based socioeconomic status (SES) indicator for health disparity research in patients with type 2 diabetes (T2D).
 Methods: T2D patients receiving a treatment intensification (TI) after suboptimal glycemic control (HbA1c≥7.0%) on metformin were identified from the University of Illinois Hospital and Health Sciences System Electronic Healthcare Records (EHR). We summarized HbA1c change over 3 years after the TI using a mixed-effect regression model. Three SES indicators were tested as an independent variable interacting with the HbA1c trends: insurance status available from the EHR, neighborhood median household income within 20-minute walking distance from ArcGIS GSA, and neighborhood median home value from the GSA. Model performances were compared using the corrected Akaike criterion (AICC).
 Results: We analyzed 2535 HbA1c records from 1232 patients. The projected monthly HbA1c change was -0.02%, demonstrating glycemic control improvements after TI. While the performance in explaining HbA1c trajectory improved by including SES indicators, using GSA-populated neighborhood income and home value is pre",0.0,
aac7869c5e96506fc354b572a6188e5baf5e174a,10.54254/2755-2721/2025.bj27450,House Price Prediction Leveraging Feature Engineering and Model Comparison: A Case Study of Ames and Iowa Datasets,2025.0,Applied and Computational Engineering,Zixuan Wang,"Developing a precise prediction of house prices has been an unsettled task for many years. It is the social as well as economic need for the welfare and comfort of the citizens. The objective and aim of the research is to provide digital-based solutions to real estate prices, which focuses on economic, geographic, and demographic variables. The paper uses Advanced Regression Techniques on datasets from Ames, Iowa. The study identifies significant correlations between housing prices and 79 explanatory variables describing every aspect of residential homes. For example, the Lot configuration. Physical locations within Ames city limits, original construction date, and so on. The paper employs Lasso, Ridge, XGBoost and LightGBM to verify the most suitable model in practice in this field, offering insights for policymakers, investors, and homebuyers. This research contributes to the existing literature by providing a comparative analysis across different housing markets and suggesting strategies for price stabilisation.",0.0,https://www.ewadirect.com/proceedings/ace/article/view/27450/pdf
2b46d9b09216e682212a06d086a4b7673334eb12,10.20944/preprints202012.0715.v1,Impact of Macroeconomic Variables on Housing Prices in Saudi Arabia: A VAR Approach,2020.0,,Dirar Elmahi Elobaid Ahmed,"This paper examines how housing prices are determined by macroeconomic factors in Saudi Arabia, namely, Gross Domestic Product Per capita (GDPP), Consumer Prices Index (CPI), and Unemployment Rate (UNEMP). Quarterly data for a period (2014q1 – 2019q4) were collected from publications of Saudi Arabian Monetary Authority (SAMA). Vector Autoregression Analysis (VAR) is employed to capture the dynamic effect of the variables on housing prices. Granger Causality, Variance Decomposition and Impulse response function are also used. The results show that housing prices are insignificantly and positively related to GDPP, whereas it is negatively related to both (CPI & UNEMP). Only CPI has a significant relationship. The three variables, jointly, have Granger causality on HPI. Variance decompositions show that CPI is the variable with the highest explanatory power over the variation of housing prices, followed by GDPP and the UNEMP respectively indicating that CPI is the most influential determinants for housing prices.",0.0,https://www.preprints.org/manuscript/202012.0715/v1/download
de894a1faa1d4e6d8ce0a852457b30f75094f11f,10.35631/ijemp.831038,FACTORS INFLUENCING THE UNITED STATES HOUSE PRICE INDEX: A MULTIPLE LINEAR REGRESSION APPROACH,2025.0,International Journal of Entrepreneurship and Management Practices,Nor Azriani Mohamad Nor; Wan Nurshazelin Wan Shahidan; Wan Syaidatul Izzati Wan Abdul Rahman,"This study aims to develop a robust model for predicting the House Price Index (HPI) by analyzing its key determinants within the U.S. housing market. Utilizing a Multiple Linear Regression (MLR) approach, the analysis using R software. The findings indicate that several macroeconomic factors significantly impact the HPI. Through a stepwise selection process, Model 4, which includes the Stock Price Index, Consumer Price Index, Unemployment Rate, and Mortgage Rate, was identified as the best-fitted model. Despite the presence of some multicollinearity, this model demonstrated superior predictive power and a significantly higher Adjusted R-squared value of 0.9585 compared to alternative models. The results underscore the importance of a comprehensive analytical framework for understanding housing market dynamics. This research provides valuable insights for policymakers and investors, offering a reliable tool for anticipating HPI trends and informing decision-making to enhance market stability and affordability.",0.0,https://gaexcellence.com/ijemp/article/download/6091/5581
f5cf563b2af5b51bf69bcee7659fe9634d3b261a,10.46799/ijssr.v5i2.1175,"ANALYSIS OF THE ECONOMIC AND SOCIAL VISIBILITY OF THE CONSTRUCTION OF SIMPLE HOUSES IN EAST JAVA COMMUNITIES (CASE STUDY OF BANGKALAN REGENCY, MADURA)",2025.0,International Journal of Social Service and Research,Helsa Ade Ayu Kumala Putri; Andi Patriadi; Sajiyo Sajiyo,"This study explores the perspectives of developers and residents regarding the economic and social visibility of simple housing construction in Bangkalan Regency, East Java. The study seeks to assess the visibility of affordable housing prices and analyze the social conditions associated with simple housing. The results indicate that there is a gap between reality and community expectations of housing adjacent to industrial sites in increasing employment opportunities for the surrounding community. Public transportation, educational facilities, healthcare services, and proximity to employment centers must be incorporated into housing planning to create sustainable and livable communities that meet both the expectations and realities of low-income populations. In addition, the authors developed indicators for the visibility analysis of simple residential buildings in Bang Kalan regency. This research is expected to provide insights into housing affordability and its impact on the social dynamics of the region.",0.0,https://doi.org/10.46799/ijssr.v5i2.1175
93146d3bddf257d7022e254036ddf165f5d00734,10.61173/wv98zg20,Research on the Prediction of the Housing Pricing in China,2024.0,"Science and Technology of Engineering, Chemistry and Environmental Protection",Xin-Yi Hu,"As an important cornerstone of industrial development, real estate has been widely concerned by people. A house can not only provide a place of peace for people, but also provide a certain source of income for many people. A stable house price will give people confidence in their economy. After 2007, there have been obvious changes in house prices, which further increase the difficulty of forecasting and reduce the accuracy of forecasting. As a typical forecasting model, linear regression is favored by scholars all over the world for its accuracy and adaptability. This paper will use this model to forecast the house price in the next year. The conclusion is as follows: In the coming year, the overall trend will show a more obvious upward trend. Therefore, it is recommended to invest in real estate in the short term. At the same time, this paper believes that ensuring the stability of domestic housing prices can improve people’s quality of life and enhance the status of the country in the hearts of the people.",0.0,https://www.deanfrancispress.com/index.php/te/article/download/1715/TE003302.pdf
c570370f1a5b898b91d3be6cfb8286287a39dded,10.1109/iccnct68477.2026.11589953,"Learning from Numbers, Text, and Place to Improve House Price Prediction",2026.0,International conference Computer Networks and Inventive Communication Technologies,Suvarna Sunil Kumar; Varun Vemulapalli; V. S. N. Murthy; K. Bhavani; K. Saranya; Sriharsha Vikruthi,"Accurate real estate price estimation is critically important for financial stability, urban planning, and individual investment decisions. However, property values depend on a diverse set of factors, and while machine learning has advanced the field, most existing models treat numerical data, listing descriptions, and location information as homogeneous inputs, thereby losing the unique value hidden in each modality. This paper introduces the Heterogeneous Data Fusion Network (HDFNet) a deep learning system designed to explicitly recognize and exploit the differences between data types when predicting house prices. HDFNet employs separate neural pathways for each input type: one processes structured data (e.g., square footage, number of bedrooms), another extracts semantic features from textual property listings, and a third encodes spatial information (coordinates, points of interest). These representations are then fused into a unified prediction. Evaluated on a real-world dataset, HDFNet outperforms strong baselines such as Random Forest and XGBoost, reducing Root Mean Squared Error (RMSE) by 13% and achieving an R2 score of 0.914. Ablation experiments confirm that spatial and ",0.0,
c2f7fc257e72a44a5592fa57114c96f9f84a31ce,10.54254/2753-8818/26/20241019,Machine learning on USA house price prediction,2023.0,Theoretical and Natural Science,Zirong Jin,"Nowadays, an increasing number of students are opting to study abroad in order to acquire more advanced knowledge and pursue a superior educational environment. In many foreign countries, the option to apply for school dormitories is only available during the first year of university or graduate school. At other times, international students have to search for rented apartments or apply to stay with local host families. However, when studying abroad for an extended period, purchasing a property can potentially result in significant savings compared to renting. Therefore, this study focuses on comparing three types of machine learning techniques: multiple linear regression, Random Forest, and XGboost in predicting house prices in the United States. This research could provide reference for families studying abroad or property investors. Based on the preliminary findings of this study so far, it can be concluded that the XG-boost model demonstrates the highest accuracy and stability among these three methods.",0.0,https://doi.org/10.54254/2753-8818/26/20241019
5e50d65206fc3885d2ca0a06b556c908cced5d20,10.1109/cyberc62439.2024.00045,Predicting China's Marriage Rate using Machine Learning Models and Cross-Validation Evaluation,2024.0,International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery,Deyu Zhang; Thanaruk Theeramunkong; Nirattaya Khamsemanan,"After China's accession to the WTO, the country has experienced rapid development over the past 20 years, but the marriage rate has been declining. This study aims to analyze marriage data using machine learning, identify the factors influencing the marriage rate, and make predictions. The data covers seven variables including GDP, housing prices, fertility rate, and education level in 31 regions of China from 2003 to 2022. The study employed five machine learning algorithms with five models: Ridge, Lasso, Elastic Net, Polynomial, and Weighted Least Squares, along with three types of Cross-Validation techniques – Holdout, LOOCV, and K-Fold. By comparing the five regression models and evaluating the marriage rate models through Holdout, LOOCV, and K-Fold Cross-Validation, the results show that the Polynomial regression exhibits higher predictive accuracy, with MSE of 3.473 for Holdout, 3.001 for LOOCV, and 3.018 for K-Fold. Following closely is Ridge regression with MSE of 3.565 for Holdout, 3.326 for LOOCV, and 3.334 for K-Fold. These two models outperform the less performing Lasso and Elastic Net regressions. Weighted Least Squares show stable but slightly inferior performance. By",0.0,
194bb26329f6e0f4a5047cb786631b279bb418a6,10.1057/s41300-026-00242-5,Neighborhood change and crime across stages of gentrification in Los Angeles,2026.0,Crime Prevention & Community Safety,Rustu Deryol; Lyndsay N. Boggess; Alyssa W. Chamberlain,"This study examines the relationship between different stages of gentrification and changes in property and violent crime between 2000 and 2018. We use the Urban Displacement Project’s typology of neighborhood transformations to identify four specific stages of the gentrification process and estimate spatial-errors models, controlling for changes in other neighborhood characteristics. We use residual change scores to estimate greater- or less-than-anticipated changes in neighborhood characteristics. Our findings uncover nuanced differences across the gentrification stages and crime type, with the largest effects at the earlier disinvestment or gentrification stage, and mostly for violent crime. Marginal effect models reveal gentrification stage condition the relationship between changes in poverty, female-headed households, and racial/ethnic composition and crime change. These findings underscore the importance of examining gentrification as a conditioning process when studying neighborhood crime dynamics.",0.0,https://link.springer.com/content/pdf/10.1057/s41300-026-00242-5.pdf
36820f9c13234f15591d546bbe1bbfc9b2893c6e,10.1007/s11146-025-10025-8,Racial Disparity in Appraisals: Evidence from Private-Label Refinance Mortgages,2025.0,Journal of real estate finance and economics,Shengwei Guo,"Do minorities receive lower appraisals for similar housing compared to whites? I examine this question using a novel dataset that tracks the longitudinal refinancing history of US residential properties from 2002 to 2007. The analysis applies a “repeat refinances” framework, analogous to the repeat sales method, to control for time-invariant unobserved housing quality. Contrary to recent findings, I do not find evidence that the appraisals received by minority homeowners are lower than those received by white homeowners for houses of similar quality. The results are robust after controlling for the owners’ financial conditions and lender-specific factors. Additionally, I benchmark the appraisal value to the market value predicted from a hedonic pricing model and find that appraisals are not more likely to be below the market values for black-owned homes than for white-owned homes. These findings highlight the importance of unobserved housing quality when studying racial differences in housing valuation.",0.0,https://link.springer.com/content/pdf/10.1007/s11146-025-10025-8.pdf
30d1a9fe422c65401a58046acf97688e83246640,10.54097/s7vs1247,Analysis of the Factors Influencing Housing Prices in Yunnan and Guizhou Based on Linear Regression,2024.0,"Highlights in Business, Economics and Management",Yuan Fang,"The real estate industry contributes significantly to the national economy. In reality, it has a significant impact on the lives of residents. It is of great significance to study the factors that affect the housing price for the development of the real estate industry. Based on the real estate data of Yunnan Province and Guizhou Province from January 2012 to December 2022, this study will analyze the factors influencing the housing prices of Yunnan Province and Guizhou Province. In addition to SPSS research, multiple regression analysis will be used in this paper. According to the analysis, housing prices in Yunnan and Guizhou provinces will rise with the decline of long-term loan interest rates. Besides, the residential consumer price index negatively affects housing prices in Yunnan and Guizhou provinces. Moreover, an increase in the amount of real estate investment will lead to an increase in housing prices. On this basis, the completed real estate area has a negative relationship with house prices.",0.0,http://dx.doi.org/10.54097/s7vs1247
172e6d161dd134cbbe4f6ab5aec9a486f2683348,10.26470/jcssed.2025.16.2.131,"A Study on the CPTED Guidelines and Case of Netherlands, Austria for Crime Safety in Residential Area",2025.0,Korea CPTED Association,Min-jin Seo; Ha-Neul Oh; Seungyeon Park; Seokjin Kang,"This study aims to alleviate the negative perception of probation offices within local communities by analyzing both conflict and resolution cases related to such facilities. A perception survey was conducted with probation office staff to examine institutional and spatial awareness. The key findings are as follows. First, the negative perception of probation offices stems from concerns about crime, social prejudice against probationers, and fears of declining property values. These concerns were particularly pronounced when probation offices were located near schools, daycare centers, or multi-family housing, leading to concentrated opposition. Second, the survey results revealed that the main sources of conflict with local residents were “vague negative images” and “fear of crime.” Although the necessity of spatial improvement was widely recognized, its feasibility was considered low due to budget constraints and a lack of precedents. Third, there was a high level of agreement on the need for a CPTED-based manual and the importance of improving crime-prone environments through its application. Based on these findings, the study proposes spatial improvement strategies for both the",0.0,
09e9bfc3ba67fcb9b1cce6ad30df73a09cc9b657,10.54097/2vq1wq81,House Price Prediction in Boston Based on BP Neural Network,2025.0,Highlights in Science Engineering and Technology,Zuxin Chen,"House is a basic demand for living. It is directly related to people's happiness. Affected by many factors such as the economy condition and the policy, house prices are always dynamic. House price prediction can provide decision support for investors, so it is important to optimize the prediction model. Many machine learning methods are applied to house price prediction, such as support vector machine and random forest. This paper predicts the house price of Boston. To solve the multicollinearity problem in the dataset, this paper builds a BP neural network model using Bayesian regularization. The fitting analysis of the data samples shows the total R-value is 0.9824. The loss function converges to the global minimum within 100 epochs. The experiment indicates that the model is both efficient and reliable in forecasting house prices. This research provides a method to deal with the multicollinearity problem in the dataset, which improves the generalization ability and predictive accuracy of the model.",0.0,https://drpress.org/ojs/index.php/HSET/article/download/28760/28235
29ce2045a8b41ca2314a2b80fea6fdc3b22ab75f,10.54254/2753-8818/2025.gl24068,Research on the Factors Influencing Housing Prices,2025.0,Theoretical and Natural Science,Suqi Chen,"This paper aims to investigate and demonstrate the factors affecting housing prices. The method used to analyze 1,000 samples for determining these factors is multiple linear regression. After preliminary analysis, some less relevant factors were excluded, such as built year, and finally, seven key influencing factors were selected for the study. The research employs various intuitive charts and clear tables to present the results. A linear relationship between housing prices and the following factors was established: square footage, number of bedrooms, neighborhood quality, number of bathrooms, parking space size, house age, and lot size. This allows for a clear understanding of how much each factor contributes to price changes, as well as the individual impact of each variable. Behind the influence of each of these factors, this paper further analyzes other possible practical factors. In conclusion, this study provides useful reference value for real estate investment and home-buying budget planning.",0.0,https://www.ewadirect.com/proceedings/tns/article/view/24068/pdf
8f91b7d2b11f385d856d0e09b6c1a93c1f333cfb,10.56409/kreis.2026.9.2.219,A Study on Housing Choices and Satisfaction of Workers in the Metropolitan Area,2026.0,KOREA REAL ESTATE INDUSTRY SOCIETY,Seong-Woo Ban; Jin-Hyeong Seo,"Housing is a crucial element, as it is one of the three primary necessities of human life: food, clothing, and shelter. The role of housing can be divided into satisfying basic needs, enhancing quality of life, and contributing to social and economic value. Furthermore, housing serves as an important indicator of an individual’s economic status and social standing. Therefore, this study aimed to investigate which factors among the housing choice characteristics of workers residing in the metropolitan area influence their satisfaction with their housing choices. 
The results of this study are as follows. First, Hypothesis 1, which states, “Among housing choice characteristics, distance from work will significantly influence satisfaction with housing choices across regions, income classes, and life stages,” was accepted. Second, Hypothesis 2, which states, “Among housing choice characteristics, educational environment will significantly influence satisfaction with housing choices across regions, income classes, and life stages,” was accepted. Third, Hypothesis 3, which states, “Among housing choice characteristics, low housing prices will significantly influence satisfaction with hou",0.0,
9d3c19e8632a684b81cce60be45ee47e8672a3c9,10.22214/ijraset.2023.53273,House Price Prediction and Recommendation,2023.0,International Journal for Research in Applied Science and Engineering Technology,Poonam Patekar,"Abstract: Determining how much a house will sell for in a city is still a challenging and time-consuming task. This article's goal is to make predictions about the coherence of non-housing prices. A crucial method to ease the challenging design is to use machine learning, which can intelligently optimize the best pipeline fit for a task or dataset. For individuals who will be residing in a home for an extended period of time but not permanently, it is essential to predict the selling price. Real estate forecasting is a crucial part of the industry. From historical real estate market data, the literature seeks to extract pertinent information. Land price bubbles grow as a result of real estate prices, which leads to macroeconomic instability. The government should look into the variables that drive up real estate prices so that it can use them as a guide to assist stabilize the area. There are many economic circumstances that are in play at the time also have an impact on the selling price of a home.",0.0,http://dx.doi.org/10.22214/ijraset.2023.53273
b9842709ff1a40e89ba44eb283e16742423afb92,10.54097/5f1c9014,Housing Prices in Fujian Province: A Linear Regression Analysis of Fuzhou,2026.0,Mathematical Modeling and Algorithm Application,Hanyu Zhuang,"This study used multiple linear regression to investigate the key points affecting housing prices in Fuzhou, Fujian Province. According to data from 20 residential communities, 5 variables are examined: building area, building age, distance to the nearest metro station, distance to the central business district (CBD), and proximity to key schools. The results show that metro distance has the strongest effect: one kilometer closer to a metro station increases price by 4,856 RMB/m². School proximity adds 8,923 RMB/m², while each additional year of building age reduces price by 413 RMB/m². The model explains 71.2% of price variation (R² = 0.712), and all variables are statistically significant. These findings support land value capture for metro funding and education equity policies to reduce housing pressure. Limitations include a small sample size (20 communities) and cross-sectional data. Future research should expand the number of the samples and include more detailed values especially variables.",0.0,https://drpress.org/ojs/index.php/mmaa/article/download/35419/34603
74daa585b5ad16d9c158b1614d10cc39af98af9f,10.2991/assehr.k.211209.299,The Effect of Wealth Increase on Education and Entertainment Consumption in China,2022.0,Proceedings of the 2021 3rd International Conference on Economic Management and Cultural Industry (ICEMCI 2021),R. Liu,"Entertainment and education consumption partly reflects people’s living standards. In order to study the influential factors of entertainment and education consumption of Chinese people in the second decade of the 21st century, this paper uses the data from 2010 to 2018 in China Family Panel Studies (CFPS) and the multiple linear regression analysis in econometrics to evaluate the impact of the increase of total household assets on the consumption of entertainment and education in China through Stata software. The results show that the increase in household assets promotes entertainment and education consumption. However, the promoting effect gradually decreased from 2010 to 2018. In addition, high housing price took in a large amount of family income and impeded the consumption of entertainment and education. The decline in people’s preference for entertainment and education consumption in recent years, to some extent, means a rise in living pressure and a decline in the quality of life in China.",0.0,https://doi.org/10.2991/assehr.k.211209.299
cd52ae08c0cbcde80229ce7490da89a6d4454576,10.2139/ssrn.5021705,Applying Seasonal Adjustments to Housing Markets,2025.0,Social Science Research Network,W. Doerner; WEN-CHUN Lin,"House price seasonality has been increasing over the last decade, but adjustments have remained largely unchanged in commonly used public data. This paper shows how seasonal adjustments work—both theoretically and applied to observed transactions—when constructing house price indices (HPIs). In this paper, we find the seasonality in the housing market is not uniform across geographies. Evidence is provided about where adjustments are more necessary, how often they should be recalculated, and how the weather-related variables, social and industry characteristics impact difference between adjusted and non-adjusted HPI. Using the Federal Housing Finance Agency’s (FHFA’s) entire suite of public indices, we update adjustments that have been provided by the FHFA and offer new adjustments for over 400 metropolitan areas and other geographies, which haven’t been provided before. We find the difference between previous and updated adjusted indices are relatively small, with slight improvement in recent years.",0.0,https://doi.org/10.2139/ssrn.5021705
4c7766d489bda2e0b0a082bef19df655a7908dc0,10.56397/jwe.2024.09.05,The Impact of Housing Price Volatility on Household Consumption in Northeast China Across Different Demographic Profiles,2024.0,Journal of World Economy,Zi-Yi Li; Zhong-Hao Li; Yuyang Wang,"Amidst the backdrop of an economic downturn, urban housing prices in China have exhibited substantial volatility, significantly impacting domestic demand and household consumption. Demographic characteristics of households have played a pivotal moderating role in this dynamic. Due to economic stagnation and population outflow, Northeast China has garnered heightened attention. This study employs microdata from households in Liaoning and Heilongjiang provinces, spanning from 1989 to 2015, to conduct an empirical examination. The findings indicate that rising housing prices exert a pronounced positive influence on household consumption, particularly among households with children and those headed by elderly individuals. Conversely, the educational attainment of the household head does not exhibit a statistically significant impact on the real estate wealth effect. The study concludes with policy recommendations aimed at stimulating domestic demand and stabilizing housing prices in Northeast China.",0.0,https://www.pioneerpublisher.com/jwe/article/download/931/846
3aa6e6343d15846f5bed9ba55f447d945302c332,10.1177/297765702022s213,"Environmental Impact of Real Estate Development on Urban Fringe Areas: A Case of Tathawade, Maharashtra",2022.0,"Journal of Real Estate, Construction & Management",Shruti Vaishampayan; A. Naphade; Vini Khatri,": Urban fringe areas are outside city limits that display a mix of rural and urban characteristics in terms of development. Fringe areas typically present a high demand for real estate due to proximity to urban centres and potential for growth in terms of social, cultural, infrastructural aspects along with comparatively lower property values than the urban centres. Research shows that construction and development activities in fringe areas have long term impacts on environment owing to lack of proper planning and guidelines. Haphazard development in peri-urban areas leads to serious environmental impacts on land, air, surface and ground water, along with increased load on sanitation and waste management facilities. Agricultural land rapidly gets converted to non-agricultural uses such as residential and industrial, along with road infrastructure affecting air quality, water demand and demand of landfill sites. The present study is an attempt to investigate environmental impacts of real estate development in case of the rapidly developing fringe area of Tathawade in Pimpri Chinchwad, Maharashtra. Select parameters, namely change in land use, sustainability of built environment, sol",0.0,
453ccf7574264eb512bc3ee1dee8613994c4f96f,10.61173/s6sryj03,Analysis of house price forecast based on New Haven housing market,2024.0,Finance & Economics,Sha Jiang; Yu-Qi He; Chunhui Song; Xue-Yao Sun; Zhi-Cheng Wang; Zhi-Yang Wang,"



The fluctuation of residential housing values hinges upon a variety of factors, but this paper postulates that the most important ones are related to the geographics and the size of land area. Further, this report aims to provide a regression model to analyze variables affecting residential properties in the city of New Haven, CT based on a selection of housing variables. The raw data are directly sourced from the New Haven Tax official database and are filtered to contain determinants of only residential houses or condominiums. The construction of a linear regression model attests to the efficacy of each selected variable and indicates the positive relationship between the properties of the houses with a complex of variables including the proposed ones. The model can further make predictions regarding the values of each property. On the other hand, the model itself has intrinsic limitations, but this project works to outline an optimistic research direction into other practical areas.



",0.0,https://fe.deanfrancis.press/article/download/790/791
4997de0249d225ed6359b594e140ec07dd191b5f,10.54097/hqzskw61,The Research on Factors Influencing Housing Prices-Taking California for Example,2024.0,"Highlights in Business, Economics and Management",Zi-Han Lu,"This article is about something on impacting factors of house prices. In this research, multiple linear regression is used as a method. Regression method is a scientific tool that provides insights into the dynamics of how a dependent X factor responds to changes in one or more independent variables. This research finds that there are many factors and Indies do influence on the housing prices, including GDP, CPI, Income, Urban population, Delinquency rate, etc. Most of those factors or Indies have positive correlation with housing price. And through further analysis selection and analysis, research find that CPI and GDP has positive relation vs housing price and its correlation degree is most highly in those factors. And then GDP and CPI working as independent variables in multi linear regression come to a model. For this model, T test, R-squared test, F test and practical test have been done to proof this model is reasonable. And this model can be used in practical housing price analysis.",0.0,https://drpress.org/ojs/index.php/HBEM/article/download/27594/27122
eb65b1864e2361e4e5710c497b2965ed0c6df59e,10.48175/ijarsct-4845,House Price Prediction using a Machine Learning,2022.0,"International Journal of Advanced Research in Science, Communication and Technology",Akshit Kathait,"Data mining is now widely used in the real estate market. The ability to extract data to extract relevant information from raw data makes it very useful to predict house prices, important housing features, and much more. Studies have shown that fluctuations in housing prices often affect homeowners and the housing market. A literature review was conducted to determine the appropriate characteristics and most effective models for real estate forecasting. The findings of this analysis confirmed the use of Artificial Neural Network, Support Vector Regression and XGBoost as the most efficient models compared to others. In addition, our findings also suggest that local agents and real estate agents are key to predicting real estate prices. This research will be of great benefit, especially to housing developers and researchers, to find the most important indicators for determining housing prices and to identify the best machine learning model that will be used to conduct research in this field.",0.0,https://doi.org/10.48175/ijarsct-4845
3369ad0bf58661d98bc8d4f05508972c69d0f664,10.54097/cjaf8x11,Comparison Of Linear and Nonlinear Models in Predicting House Prices,2025.0,"Highlights in Business, Economics and Management",Zuyu Lin,"Nowadays, the increase in housing prices has led to a heavier financial burden on ordinary citizens, affecting their quality of life. This research used linear regression, random forest, and Support Vector Machine (SVM) to predict housing prices using the Boston housing price dataset, and compared the advantages and disadvantages of them. The paper compares the performance of linear and nonlinear models in predicting housing prices to reflect the importance and magnitude of various factors that affect housing prices. The overall research demonstrates that nonlinear models have unique advantages over linear models in multi-factor impact problems such as predicting housing prices. This is due to the comprehensive examination of multiple factors by nonlinear models, which linear models do not possess. The project still has many shortcomings in many aspects, such as not tuning the parameters of the SVM. There is also no addition of cross-validation, and a lack of visualization of the results.",0.0,https://hbem.org/index.php/OJS/article/download/546/510
b775745c362b7402da1f59900fa7afa1a1b3133b,10.18077/chss.2013.58..005,중국의 신곡(神曲) 초탐(初探),2013.0,,영은 안,"There is a word that mirrors the mentality of Chinese people today: ``tan te(탄터)``. The shape of the word looks like a mind going up and down, which represents anxiety that many people feel. It is widely used in the form of a phrase: ``tan te bu an(탄터不安)``. The word, ``tan te(탄터)``that people have used for centuries, however, suddenly drew attention in China in 2010. ``tan te(탄터) syndrome`` comes from the Chinese collective anxiety. Rapid inflation, surge in house prices, and a natural disaster like the great earthquake in Si Chuan, have implications for individual anxiety to grow into a social phenomenon. , the music by Gong lin na describes such mentality of Chinese people through a symbol. This study aims to investigate ``tan te(탄터) syndrome`` in China along with several characteristics found in the distribution and reproduction of that became signifier by using a variety of cultural codes, such as ``s general code, various storytelling based on trans media, and new ideological codes.",0.0,https://doi.org/10.18077/chss.2013.58..005
e71ce2026d1fbc32e3d889d7afb917ace603f641,10.54097/wcqvdh81,GIS-based Analysis of Distribution Characteristics and Driving Factors of House Prices in Nanjing's Central District,2024.0,"Frontiers in Business, Economics and Management",Xiao-Lin Gong,"This study aims to investigate the spatial distribution characteristics of house prices and their driving factors in the central area of Nanjing by using Geographic Information System (GIS) technology, combined with kernel density analysis, Moran index and geodetic detector method. The results show that: (1) The high values of house prices in central Nanjing have significant spatial aggregation characteristics, mainly concentrated in Qinhuai District, Gulou District and its border areas, and the house prices have significant spatial autocorrelation; (2) The results of the geo-detector show that the degree of traffic access and settlement characteristics have the greatest influence on house prices, while the influence of the construction of ancillary facilities is relatively weaker; (3) There are significant interactions between different factors, especially between transport accessibility and the construction of ancillary facilities, which play a crucial role in influencing house prices.",0.0,https://drpress.org/ojs/index.php/fbem/article/download/28229/27722
531764a0361dace77dcb005ccdb968e339960edd,10.54254/2754-1169/85/20240870,House Price Prediction Based on Machine Learning Algorithms - Taking Ames as an Example,2024.0,"Advances in Economics, Management and Political Sciences",Keying Ren,"This study delves into the significance and methods of predicting housing prices. Utilizing a dataset from Kaggle, the author selected 10 variables highly correlated with housing prices, including OverallQual, GrLivArea, and GarageCars. Various models such as random forest and multiple linear regression were employed for prediction and comparison. Results indicate that for data with strong linear relationships, the predictive performance of the multiple linear regression model surpasses that of the random forest model. The paper emphasizes the importance of data preprocessing on model accuracy and suggests that model selection should align with data characteristics and problem requirements. While providing a preliminary exploration of housing price prediction, the study acknowledges shortcomings such as incomplete variable selection and insufficient data processing, suggesting avenues for future research to address these limitations and enhance the predictive capabilities in this domain.",0.0,https://doi.org/10.54254/2754-1169/85/20240870
463632ff33917e97f63707a1c0c219e50bb6c435,10.54254/2754-1169/2025.bl25997,Singapore House Price Forecasting Using Machine Learning,2025.0,"Advances in Economics, Management and Political Sciences",Yu Hu,"Real estate valuation, particularly predicting house prices, is a critical aspect of the real estate industry. This paper provides a comprehensive overview of the application of various machine learning models for predicting house expenses. Four distinct models are evaluated: Back Propagation neural network (BP), random forest (RF), seagull optimization algorithm (SOA), and lion swarm optimization-based algorithm (SLSO-BP). This research aims to identify the most effective machine learning algorithm for accurately predicting house prices, utilizing the mean square error (MSE) and R-squared (R2) as the evaluation metric. Through a comparative analysis, our findings reveal that the SLSO-BP algorithm demonstrates superiority over other predictive tools, showcasing the lowest MSE. This study contributes to the advancement of predictive modeling in real estate, offering valuable insights for practitioners, researchers, and policymakers involved in housing market analysis and decision-making.",0.0,https://aemps.ewapub.com/article/view/25997.pdf
8dbff7a40283e1638b469220e9b2cb8d53734648,10.54254/2754-1169/97/20231551,Analysis and Prediction of Influencing Factors of American Real Estate Price Based on Machine Learning,2024.0,"Advances in Economics, Management and Political Sciences",Ting He,"The American real estate market has always been a subject of widespread interest, with its price fluctuations impacting not only the lives of millions of American households but also exerting profound effects on the nation's overall economic health. This paper focuses on analyzing which factors are more significant in influencing the American real estate market in order to gain a better understanding of the factors influencing this market and to offer insightful information for stakeholders, policymakers, and investors navigating this dynamic market. We apply linear regression model, lasso regression model and random forest regression model to United States real estate data to explore variables that influence the U.S. housing price and find that PPI, M3, and population are the critical variables impacting the housing price most. By comparing the performance of three regression models, we identify the random forest regression model as the optimal model for predicting real estate prices.",0.0,https://doi.org/10.54254/2754-1169/97/20231551
fb0bb7b7a9854f81b204c6e83e767d212219379c,10.35603/sws.iscss.2025/s02.17,HOUSING AVAILABILITY IN SLOVAKIA AND THE IMPACT OF SOCIO-ECONOMIC FACTORS,2025.0,International Symposium on Computer Science and Society,Miroslav Panik; Julius Golej,"The current turbulent development in the real estate market, not only in Slovakia but throughout Europe, is caused by several crises that have a global impact and partially resemble the situation in the market 15 years ago. One factor that negatively affects the real estate market in Slovakia is the lack of residential real estate. In the long term, the demand for housing significantly exceeds the supply of apartments. This article analyzes the prices of real estate intended for housing in Slovakia. It defines economic, demographic and social factors that have a significant impact on the development of real estate prices. The methodology of statistical data collection differs considerably in the developed countries of the EU. Central banks establish a base interest rate, serving as a benchmark for commercial banks to set their lending rates. While short-term interest rates are closely tied to central bank decisions, long-term interest rates are influenced by market expectations regarding economic conditions and inflation. Rising prices reduce the affordability of housing. If housing prices rise faster than incomes, fewer people can afford to buy or rent property. The average Slovak",0.0,
f4e9835b3e35a02b36267a048e186e141de4edc2,10.1111/grow.70073,Understanding Migration Dynamics in Taiwan's New Town Development: The Role of Housing Affordability and Infrastructure,2025.0,Growth and Change,Chien-Wen Peng; Yong Tu; Chien-Hao Fu,"As suburbanization accelerates globally, large‐scale developments—such as new towns and redevelopment zones—are increasingly used by policymakers to alleviate urban congestion and promote spatially balanced growth. While theoretically offering superior infrastructure and living environments, such projects are complex, capital‐intensive, and exposed to political and market uncertainties that can lead to misalignment between planning goals and outcomes. This study offers the first empirical analysis of population migration dynamics within the context of a large‐scale new town development project. Focusing on Taiwan's National Taipei University Special District (NTPUSD), this study examines inter‐district migration patterns using administrative data, with particular attention to the role of housing prices, commute times, and infrastructure access. The findings show that lower housing prices—especially when combined with shorter commutes—are significant drivers of migration. High‐income households are more sensitive to price differences, while middle‐income households move from moderately priced areas to upgrade housing. The price effect is minimal in low‐income districts. Migration pa",0.0,
9b877d5155c94cecd3be6c05086525d85ea23f71,10.56409/kreis.2024.7.1.1,An Analysis of the Impact of Single-person Household Characteristics on Housing Occupancy,2024.0,KOREA REAL ESTATE INDUSTRY SOCIETY,Jongseop Sim; Munsu Park,"Single-person households are closely associated with the social issue of housing poverty. The purpose of this study is to present policy alternatives for addressing the challenges faced by single-person households by examining the influence of socio-economic and locational characteristics on occupancy patterns. The results of this study are as follows. The results of the binary logistic regression analysis are as follows. The results revealed that bereavement, increased management costs, residing in the Seoul metropolitan area, being employed in labor, sales, or service occupations, living in officetels or one-room apartments, and owning a car showed statistically significant associations with self-probability. Ragarding of regional characteristics, it was observed that the closer people reside to the metropolitan area, the higher the probability of leasing. Specifically, Gyeonggi-do Province has a higher likelihood of leasing than Seoul. This suggests that tenants may be moving to Gyeonggi Province due to the steep monthly rent increase in Seoul, which they cannot afford. Based on the results of this study, housing support measures and policy implications are presented. The younge",0.0,
5a743b5ff6803a3dde0e2f0263a04818521a2997,10.5296/ijrd.v2i2.8102,A Recent Development of the Spatial Disparity of Housing Prices in Iceland and Its Underlying Economic Causes,2015.0,,Vífill Karlsson,"In this paper, the author examines the development of the spatial distribution of housing prices. Due to consumer preferences for access over amenity value, there is a spatial disparity of housing prices. According to Alonsoi¯s extension of von T¨¹neni¯s theory, the relationship between housing prices in urban and rural areas tends to follow certain principles. This relationship is more often negative than positive, i.e. the price of a standardized unit of housing declines with increasing distance from a central business district (CBD). It has been documented that this relationship is negative for Iceland, as well as in many regions of other countries. It is argued here that this relationship has become increasingly marked in Iceland, most likely due to the altered household preferences and structural changes. A macro panel data set from Iceland will be used, representing several essential variables of the residential housing market for 79 municipalities in Iceland from 1981 to 2006.",0.0,http://www.macrothink.org/journal/index.php/ijrd/article/download/8102/6876
70793a0bc598a94039324af156e1d111fc796e7b,10.1093/geroni/igaa057.2418,The Long-Term Care Financing Challenge: What Role for Home Equity?,2020.0,Innovation in aging,Jane Tavares; Marc Cohen; L. Popham,"Abstract With increasing longevity comes the need for support in activities of daily living. This growing demand for long-term services and supports (LTSS) threatens older adult financial security. About 25 million adults aged 65 and older will have a significant LTSS need that will cost up to $140,000 out-of-pocket plus an estimated $120,000 from public payers like Medicaid; the total public and private costs of care exceeding $250,000. Home equity, the most valuable financial asset owned by Americans, offers one solution to this financing challenge. While seniors boast $7 trillion in collective home equity, opportunities to annuitize this asset vary and the distributions of home ownership and value are highly skewed. Using the 2016 wave of the HRS, this paper explores the relationship between socio-demographic/health characteristics and the annuitized home value. We determine which individuals with LTSS needs might benefit from the annuitization of home equity and to what extent.",0.0,https://academic.oup.com/innovateage/article-pdf/4/Supplement_1/691/34920392/igaa057.2418.pdf
26d337e294b50eb0104584b3ca5fd06d12fe8af6,10.54091/krepa.2024.25.2.30,An Exploratory Study on Changes in the Built Environment Before and After Public Rental Housing Development,2024.0,Korea Real Estate Policy Association,Dongha Park; Gyuho Lee; Jaewoong Won,"This study aims to address the variability in empirical analyses regarding the impact of PRH(Public Rental Housing) on surrounding housing prices by investigating the environmental diversity of PRH from an urban design perspective. We analyzed the characteristics of 183 Happy Housing complexes in Seoul using maps and street views, examining the complexes' attributes, adjacent infrastructure, and neighboring buildings. Additionally, an in-depth analysis was conducted on 11 Happy Housing complexes used in previous empirical studies. The results showed that 69% of the areas with Happy Housing experienced changes in neighborhood facilities, 66% saw improvements in roads and sidewalks, and 79% had enhancements in green spaces. These findings suggest that the supply of Happy Housing can positively influence the local environment, although the impact may vary in areas without infrastructure improvements. Furthermore, the relationship between Happy Housing supply and adjacent building development exhibited relatively low statistical significance, and the in-depth analysis also found it difficult to establish a consistent relationship between the two factors. These outcomes highlight the im",0.0,
79ef2b5c97af212a2651b0df761a0e38797c7254,10.62051/4r609702,Investigation Upon Factors Contributing to Housing Price Variations-Specifically Sydney for Reference,2024.0,"Transactions on Economics, Business and Management Research",H. Pang,"The purpose of the article is to determine the small aspects that can affect the overall housing prices around the globe. It will be established by looking into one specific area and finding the relationship between them. This research will be using a multiple linear regression model to find the connection. The study used 300 samples and 9 variables each, all are possible variables that can influence overall house price. The data are from Sydney Urban areas collected during the 2020-2021 house market. For the outcome to be valuable, this research will be comparing the significance and VIF value for those variables to find out the biggest connection. Through this process, the null data was deleted as much as possible. As a result, this article discovered that Safety and Median house rent are the biggest influencing factors to the house price. The two factors are the most considered during a house purchase. And the price of Sydney urban houses can be determined by those two factors.",0.0,https://wepub.org/index.php/TEBMR/article/download/3075/3359
4941782b5b0f72edd1a30f2daf9fb60fbce23f3d,10.22313/reik.2022.20.4.233,A Study on the Effects of Changes in the Housing Purchasing Power Index on the Housing Market in Seoul,2022.0,Residential Environment Institute Of Korea,Jung-A Park,"This study attempted to derive the effect of changes in the Seoul Housing Purchasing Power Index on apartment prices in Jeonju, one of the representative non-metropolitan base cities, and to understand its meaning. The analysis method used VECM in consideration of the characteristics of the variables measured in time series. The summary and implications of the results of this study are as follows. 
First, the change in housing purchasing power in Seoul was found to be one of the main variables affecting apartment prices in Jeonju, a local hub city, and in particular, it was found to have a significant impact on the lag behind. In other words, if housing prices in the Seoul metropolitan area soar and housing investors' ability to invest in the Seoul metropolitan housing market decreases, it is interpreted that they are interested in the apartment market in local hub cities with relatively high price advantages over some time difference. Second, it was found that the change in the population had the greatest effect on apartment prices in Jeonju. Finally, unlike research results on housing prices in Seoul and the metropolitan area, changes in major macroeconomic environments such as t",0.0,
679eb1ffdabfdc5ad0a70fec885c007ea991eb7c,10.54254/2754-1169/2024.24972,Airbnb Optimization of Pricing Strategy: A Study on the Static Pricing Model of Housing Resources Based on the Characteristic Price Theory,2025.0,"Advances in Economics, Management and Political Sciences",Hang Liu; Ruo-Lin Zhang; Peiyuan Song; Zixuan Bu,"With the surge of tourism and the rapid development of the global homestay market, Airbnb has achieved a significant leap forward in development, among which pricing strategy has become the focus of research. Based on the characteristic price theory, this paper constructs an accurate static pricing model through the linear model algorithm and makes an objective evaluation. The study found that the characteristics of house specifications, cancellation policies, whether to provide cleaning fees and so on have an important impact on the Airbnb housing price. At the same time, the evaluation scores and booking situation also have a certain influence on pricing by integrating a large number of characteristic data, establishing the housing static pricing model, providing a powerful tool for homestay facility pricing, for existing rental records through the evaluation data for pricing maintenance of special research, provides the reference for people host optimization pricing strategy.",0.0,https://www.ewadirect.com/proceedings/aemps/article/view/24972/pdf
6e0723a28de038c1f39063b4c5e595c7222c2d8e,10.24818/mer/2022.02-01,Economic Development through Mortgage Loan Distribution in Indonesia,2022.0,Management and Economics Review,,"The growing population of Indonesia is increasing every year, which also leads to the growing need for people's residences. Of course, this affects the financial sector in terms of mortgage loans. Therefore, this paper is a study of the factors that affect the distribution of mortgage loans in Indonesia. This study uses multiple linear regression with ordinary least square analysis with the variables Residential Property Price Index, Lending Rate Credit, and Gross Domestic Product as the independent variable (X) and distribution of mortgages as the dependent variable (Y). The data used in this study are the quarterly time series from 2009 to 2021. Based on the results, the variables Residential Property Price Index, Lending Rate Credit, and Gross Domestic Product have a significant influence on mortgage loan distribution in Indonesia. So, the hope is that the government and the banks can wisely set Lending Rate Credit based on the Gross Domestic Product level of their territory.",0.0,https://doi.org/10.24818/mer/2022.02-01
3281c9d1cd314ad7924664c8d60a7b35b8d5a597,10.54254/2753-8818/52/2024ch0146,Research on house price prediction in UK based on linear regression model,2024.0,Theoretical and Natural Science,Meng-Xuan He,"This paper aims to analyze the factors that affect housing prices and predict the trend of housing prices through a linear regression model. This article will use a linear regression model to analyze data on UK house prices from 1952 to 2022. And selected 12 different factors that affect housing prices, using a linear regression model to predict the fluctuations of housing prices. At the same time, a multiple prior regression model was used to explore the importance of each factor in affecting house prices. And the significance of these variables was also compared. The results show that the location of the house, per capita income, housing environment, immigration rate, actual deposit rate and actual loan rate have a significant linear relationship with house price changes, while per capita productivity and house type after the epidemic do not have a significant linear relationship with house price changes. Therefore, UK house prices can be predicted based on the above factors.",0.0,https://tns.ewapub.com/article/view/15618.pdf
6b7a05e8894d2882e537186846a0fa4fb9e24016,10.22158/jepf.v9n2p48,The Formation Mechanism of House Price Differences in China’s Urban Area in the Same City—Based on Lasso Bayesian Model Averaging Method,2023.0,Journal of Economics and Public Finance,Jiayao Pan; Shaoling Ding,"With the development of economy and the expansion of urban scale, the variation of housing prices within Chinese cities has gradually become significant. Based on the housing prices of 79 districts in Chengdu, this paper analyzes the reasons for such differences. With an index system of the price difference of locational housing, a semi-log linear regression Lasso Bayesian average model is constructed, which can realize variable selection while estimating coefficients. Empirical evidence shows that the inequality of social-economic resources and the imbalance of housing supply and demand in the area are important internal factors that lead to the difference in housing prices between areas within the city; the related housing prices have an extremely significant positive impact, showing that the mobility of the place of purchase and the contagion of the house price are the main reasons for housing price; in addition, influential factors have strong positive interaction effects.",0.0,http://www.scholink.org/ojs/index.php/jepf/article/download/15758/6906
4542e688786256d39af1cf316b6fd83b6cedae0f,10.15849/ijasca.v18i1.42,Predicting Apartment Prices in Jordan Using Ensemble Machine Learning Algorithms to Support Investment and Urban Planning Decisions,2026.0,International journal of advances in soft computing and its applications,N.F.S Thalji; Mohammad Alwadi,"The housing market is of great significance to the development and advancement of cities, but customary forms of property valuation are frequently biased, time-consuming, and not always effective. This paper focuses on the city of Irbid in Jordan, aiming to collect all the information on apartments and houses, predict the prices of properties, and clarify the key factors influencing the prices. Following the comprehensive cleaning process of the data and exploratory analysis, three ensemble machine learning models were trained and optimized to achieve accurate price predictions. The performance of all three models demonstrated excellent and consistent predictions, highlighting the efficiency of ensemble methods in predicting property prices. SHAP analysis indicated that the size of the house, the number of bedrooms, the number of lounges as well as the location are the most significant factors influencing the prices in Irbid. This reflects the functioning of the local market.",0.0,https://ijasca.zuj.edu.jo/index.php/IJASCA/article/download/42/28
4c75e55c883af8793808fdccec8c6f7963bed0dc,10.37355/kd-2023-10,Why House Prices Increased in the COVID-19 Recession: Evidence from Germany,2023.0,Konference doktorandů na Vysoké škole finanční a správní 2023: Prezentace výsledků společenskovědního výzkumu s ekonomickými a finančními efekty (10. ročník) = Doctoral Student Conference at the University of Finance and Administration 2023: Results presentation of social science research with econo,Frederik Schröder,"After the outbreak of the COVID-19 pandemic, real estate prices in Germany have risen significantly. This happened unexpectedly because several macroeconomic determinants pointed to a fall in property prices during this period. This provides an extraordinary opportunity to empirically investigate the particular connection between interest rates and real estate prices. The aim of the contribution is to verify the real interest rate hypothesis. This study performs a time series regression analysis to test the hypothesis. The time series ranges from 2017Q1 to 2021Q1. The results confirm that the long-term real interest rate might have a negative and significant impact on the growth rate of property prices after the factors of economic growth and unemployment have been controlled. The endogeneity is largely eliminated through an experimental design. The results have far-reaching practical implications for housing policy and for ways to solve the problem of housing affordability.",0.0,http://dx.doi.org/10.37355/kd-2023-10
c2578597a056d5df04c590f43cf0c0ba6466a520,10.1093/geroni/igaf122.1413,Mortgage Borrowing and Chronic Disease Outcomes in Older Age: Evidence From Biomarker Data in the HRS,2025.0,Innovation in aging,Cäzilia Loibl; Alec P. Rhodes; Stephanie Moulton; Donald R. Haurin; Matthew T. Pesavento; Madison Hyer; Joshua J. Joseph,"Abstract The medical diagnosis of a disease is common in older age and can carry significant financial costs. For many older adults, equity in a home is their primary component of wealth; however, housing wealth is illiquid. We analyze the relationship between the liquidation of housing wealth through mortgage borrowing on older homeowners’ ability to successfully control a disease. We use data on homeowners aged 65 and older from the 1998–2016 waves of the Health and Retirement Study (N = 3,457). We use biomarkers and physical health indicators to measure disease control following a medical diagnosis of diabetes, heart condition, high blood pressure, lung disease, or cancer. Descriptively, 28% of older homeowners who borrow against home equity are not controlled on their disease, compared to 33% of non-borrowers. Panel data instrumental variable regressions show that each $10,000 borrowed from home equity after diagnosis is associated with a 17-percentage-point reduction in the probability of the disease not being controlled. Many older adults are not able or willing to liquidate housing wealth, and the ability to borrow also depends on changes in home values. Thus, housing wealth",0.0,
cc4e9f217dbac07b4b73c8b633af8dfec0f75eb1,10.3846/ijspm.2025.23983,Property price and anti-social behaviour: An empirical study of Northern Ireland,2025.0,International Journal of Strategic Property Management,D. Lo; Yao-Xuan Huang; Michael McCord; Y. Yau; John McCord; Tariq Aziz; M. Haran; Lara Al-haddad,"This study examines the impact of anti-social behaviour (ASB) on property prices. By analysing over 14,500 market transactions in Northern Ireland, we find that the prevalence of ASB within a neighbourhood exerts a direct and negative influence on house prices, albeit with diminishing effect at the margin. Furthermore, the dampening effects of ASB are more pronounced in districts characterised by higher population density, proximity to the capital city (Belfast), and lower property values. A thorough analysis of district-level data across a wide range of statistical indicators further indicates that the adverse impact of ASB on property prices is most acute in areas marked by social and economic deprivation, including factors such as income, employment, education, and access to services. Lastly, our submarket analysis suggests that the apartment sector and public housing are disproportionately affected by ASB in terms of price depreciation compared to other property types.",0.0,https://journals.vilniustech.lt/index.php/IJSPM/article/download/23983/12911
b6a7d18d0b97b718c79d196f843a2d209f959ad1,10.54254/2753-8818/26/20241026,Forecast the house price index for California using different forecasting methods,2023.0,Theoretical and Natural Science,Qian Zhang,"Forecasting house price index is a useful and classic problem in real estate and investment fields. Predicting house price index in a region not only helps investors make sensible decisions but also aids the government in promulgating policy. This paper will use some simple forecasting models (mean model, nave model, drift model, linear model and ARIMA model) in forecast test part and by seeing the average value of their residuals and checking whether the distribution of the residuals approximates the normal distribution, select the one with the highest accuracy among them for the final prediction. Multiple linear regression is also used to find if there is relationship between predicted data and possible influencing factors (such as income, unemployment rate and population) and then use the factors that have strong correlation with predicted data to optimize our forecasts and provide a more accurate prediction for the house price index in California in the next few years.",0.0,https://doi.org/10.54254/2753-8818/26/20241026
4326e33d5aa8be80e2f1d1ae91adb42331da513d,10.1007/s11146-026-10055-w,E-Grocery and Housing Markets: Evidence from the Amenity Effect of Amazon Fresh as a Digital Amenity,2026.0,Journal of real estate finance and economics,Jamie Chung; Liuming Yang,"
 
 This paper examines the impact of e-grocery entry on the housing market, focusing on Amazon Fresh, which provides grocery items and delivery services without a physical store. We find that areas receiving Amazon Fresh services experience a 2.5% increase in housing prices compared to areas within the same metropolitan region but do not receive such services. Local households show increased online consumption following Amazon Fresh’s entry, highlighting its amenity effect. Furthermore, the price effect is stronger in areas where households are more inclined to use online platforms and in socio-economically disadvantaged areas, including those with lower income, less education, higher rental occupancy, higher minority populations, lower vehicle ownership, and limited retail access. These patterns have policy implications for alleviating the ""
 Food Desert
 "" issue in urban areas through technological advancements in grocery markets by leveraging digital grocery services.
",0.0,https://link.springer.com/content/pdf/10.1007/s11146-026-10055-w.pdf
cf5a7ca657bb720f24d15cb2d4e27beb0cf79607,10.54097/hset.v39i.6680,Analysis of Various Models for House Price Prediction based on Machine Learning,2023.0,Highlights in Science Engineering and Technology,Yu-Han Wu,"The real estate prices prediction is a relatively popular data analysis problem. With the gradual increase in the competitiveness of the housing trading platform in recent years, and the basic model of house prices predicted is different from the factual transaction price. Therefore, it is necessary to design more accurate house prices prediction models. This article will adopt different linear regression models and machine learning models. By training these models of training Set, through the accuracy algorithm of Kaggle, the accuracy of each model is obtained. According to the analysis, this article finally discovered that the accuracy of the new model is improved than the accuracy of the basic model (i.e., new model predicts house price more precision), but it can be improved in the case of less data in the real environment. The reason may be related to economic and public opinion effects. Overall, these results shed light on guiding further exploration of house price.",0.0,https://drpress.org/ojs/index.php/HSET/article/download/6680/6474
72f43fd553dee8862ef9637601670e194c8819c3,10.1109/iciics63763.2024.10859514,Assessing Machine Learning Models for Predictive Analytics in Urban Rental Markets: Rent Price Forecasting in India,2024.0,2024 International Conference on Integrated Intelligence and Communication Systems (ICIICS),Abhishek Maheshwari; Monica Ranka; Amit Malhotra; R. Mishra; M. Basha,"This research marks a groundbreaking application of a diverse array of machine learning techniques to predict rental house prices specifically in the major Indian cities of Pune, Delhi, and Mumbai. These urban areas are known for their rapid economic growth and complex demographic shifts, which introduce significant variability into the rental market. Moving beyond the conventional focus on property sales, this study explores the rental market using advanced machine learning models such as Linear Regression, Ridge, Lasso, ElasticNet, Random Forest, Gradient Boosting, K-Neighbors, Decision Tree, Support Vector Machines, and Polynomial Regression. This novel approach is tailored to meet the unique challenges of the Indian rental landscape, offering a detailed examination that transcends traditional analytic methods. By meticulously adapting these models to the nuanced dynamics of rental prices in Pune, Delhi, and Mumbai, the study fills a crucial gap in existing real estate research. Our results highlight the varied performance of these models, with non-linear methods like K-Neighbors and Random Forest emerging as particularly effective in capturing the complex interplays affecting r",0.0,
3433dec51e1dd4b7d016d77c4edce24a246a0500,10.61173/hz6jyf42,The Research on Factors Influencing Housing Price in Shanghai,2025.0,"Science and Technology of Engineering, Chemistry and Environmental Protection",Zi-Yi She,"This article aims to identify the factors that may influence housing prices in Shanghai. A multiple linear regression model is used to analyse significant factors based on a sample of 300 from Shanghai in 2021. Under certain assumptions, eleven factors were found to be correlated with housing prices. To assess the data's effectiveness, this study compares the Variance Inflation Factor (VIF) and tolerance levels of these variables. It also considers the incident relations using a scatter diagram and screens for abnormal data through box plots to illustrate the data distribution situation. The findings suggest that loft floor heating and the number of bathrooms may affect housing rental prices; however, the number of bedrooms, living and dining rooms, WIFI, outdoor space area, square meters, use type, and balcony did not show a linear relationship. Overall, fluctuations in housing rental prices in Shanghai can be attributed to the varying influence of these factors.",0.0,https://lseee.net/index.php/te/article/download/1124/TE011472.pdf
80cbd52eeab6ebbcfa291facc83720df360a56b4,10.20472/iac.2018.043.001,Different Property Sectors of Japanese REIT Market: Comparative Analysis of Determinants under Non-Traditional Monetary Policy Regimes,2018.0,,Takayasu Ito,"Stock price has a positive impact on the REIT (Real Estate Investment Trust) Property Sector Index Series (Office, Residential, and Retail & Logistics) in all three sample periods. Interest rate has no significant impact on any of the sectors in the REIT Property Sector Index Series under the comprehensive easing policy regime. On the other hand, interest rate has a negative impact on each of the sectors in the REIT Property Sector Index Series under the quantitative and qualitative easing and the negative interest rate policy regimes. The negative impact of interest rate on the REIT market is larger under the quantitative and qualitative policy regime than it is under the negative interest rate policy regime. As regards the sensitivity of the three REIT property sectors to stock price and interest rate, no significant differences are found in any of the samples; the three different sectors are almost equally influenced by stock price and long-term interest rate.",0.0,http://iises.net/proceedings/43rd-international-academic-conference-lisbon/table-of-content?cid=73&iid=001&rid=9364
271d398b056cc47386cb005650534bc50687c3cc,10.1109/intech64186.2025.11198475,House Rent Prediction Using Machine Learning Approach,2025.0,InTech,K. Balaji; G. Anurag; M. Nawaz; R. S.; Shanmugasundaram Hariharan; Karuppiah Natarajan,"This research explores the use of machine learning techniques to deliver precise predictions of house prices. The objective is to aid stakeholders in making well-informed property investment decisions and planning strategies. The methodologies utilized include multiple linear regression and random forest algorithms. Initially, the data underwent extensive preprocessing and visualization to ensure reliability and clarity. Subsequently, predictive modeling was performed using the aforementioned algorithms, and their effectiveness was evaluated. The multiple linear regression model achieved an R2 score of 0.73, indicating that it explained 73% of the variance in house prices, though it demonstrated errors in certain scenarios, pointing to areas for improvement. Random forest had a somewhat poorer R2 equal to 0.69, but it performed better when it comes to recognizing the non-linear associations between the variables. The factors that affect the prices of houses put into consideration include size of the house, number of bathrooms, number of floors, parking space, and air conditioning. This paper provides a good foundation for the use of machine learning in modelling the price of houses",0.0,
e3792d5053b765b061de1f786734ecbeb62016f1,10.54254/2754-1169/2024.ld19010,The Research on Factors Influencing the Fertility Rate-Take the United States as an Example,2025.0,"Advances in Economics, Management and Political Sciences",Yuyue Gao,"This study examines the impact of different education levels of parents, income, and housing prices on the number of births in various states in the United States from 2016 to 2021. The data was collected from Kaggle on the number of births and education levels, the historical housing price data from Zillow, and the average income data from Federal Reserve Economics Data (FRED). The number of births was used as the response variable, while average income, housing price, and education level were set as the explanatory variables. The article will apply a multiple linear regression model to analyze the data, and this paper also considers the interaction effect between income and the prices of housing by adding an interaction term in the model. The major findings indicate that housing prices and people with less than a high school education have little or no impact on fertility rates, while higher education levels and income show a strong correlation with fertility.",0.0,https://www.ewadirect.com/proceedings/aemps/article/view/19010/pdf
2e2e6cdb4285e8172b031d001e9b47c38917af54,10.31303/krear.2023.92.21,A Study on the External Effects of the Price Ceiling System on Private Housing Sites: Focusing on the regulated areas of Gyeonggi-do using the double-difference method,2023.0,Korea Real Estate Academy,Hye Yeon Kim; Tae Yang Kim; Yougha Park,"1. CONTENTS (1) RESEARCH OBJECTIVES This study attempted to analyze external effects on Hana Mimi, Gwangmyeong City, Gwangmyeong-si, Gwangmyeong-si, Gwangmyeong City and Gwacheon City, and Gwacheon City, Gyeonggi-do Province. (2) RESEARCH METHOD Panel analysis was used as the analysis method in consideration of the characteristics of the data used, and the double-difference method was applied to understand the policy effect of the sale price ceiling. The analysis tool utilized the open statistical package R, which is recognized as the most efficient analysis tool in panel analysis. (3) RESEARCH FINDINGS As a result of analysis, the total model, the price of nearby housing market, light, the price of the nearby housing market has been analyzed that there is an external effect of stabilization housing prices, and the upper limitations. 2. RESULTS According to the analysis, the implementation of the ceiling on the sale price applied to the three regions of Gyeonggi-do has the effect of lowering inventory housing prices in Hanam and Gwangmyeong, excluding Gwacheon. Policy proposals for institutional supplementation so that the sale price ceiling can operate as originally intended are a",0.0,
a33e87e08f5352946b6ca86f418d09212ce1b232,10.5220/0013055900004601,The Study on the Influencing Factors of Housing Price,2024.0,"Proceedings of the 1st International Conference on Innovations in Applied Mathematics, Physics and Astronomy",Zhiyi Chen,": This paper aims to find out the factors that affect the housing price. Multiple Linear Regression method was used to analyze the significant factors between May 2014 and May 2015 in King County. Through the graph test, 13 of the 15 variables selected are related to house prices. In the model analysis, the p values and the VIF values of these variables were compared, and the accuracy of the model was confirmed. The results showed that the number of bedrooms, number of bathrooms, living area, waterfront, view level, overall condition, building grade, above ground area, below ground area, year of renovation, there is a significant linear relationship between the living area and lot size of neighbors and the housing price, and there is no significance test between the number of floors of the building and the housing price. In general, the fluctuation of home prices in King County can be considered by the extent to which these factors affect home prices.",0.0,http://dx.doi.org/10.5220/0013055900004601
be97b7f99a884fa95708ab89a2924d42dc1034ff,10.1109/icadcs70036.2026.11583665,"An Empirical Analysis of Regression and Ensemble Learning Models (LR, DTR, RFC, GBR) for Robust and Accurate House Price Prediction Using Structured Data",2026.0,"2026 1st International Conference on AI, Data Science, Cyber Security and Smart Manufacturing for Sustainable Development (ICADCS)",Juhi Kamakoty; Sita Ram Seervi; Anshita Shukla; Jyoti; K. Kiran; Ravi Kumar,"Housing price prediction has become more important to buyers, sellers and investors in the new age of the real estate market. Over the past few years, the accessibility of large-scale datasets, combined with major innovations in machine learning (ML) methods, has become accessible, allowing the creation of extremely accurate predictive models. This paper introduces a house price prediction model that uses a data set of residential houses in the United States to train and test various machine learning algorithms. The suggested framework combines the data preprocessing techniques with the sophisticated regression algorithms to predict the prices of the property basing on different determining characteristics, including the number of bedrooms and bathrooms, location, kitchen specifications, garden presence, and other appropriate characteristics. Various models, such as Linear Regression (LR), Decision Tree Regression (DTR), Random Forest Classifier (RFC) and Gradient Boosting Regression (GBR), are applied and compared to each other to identify the best model. The results prove that the techniques related to ensembles are more efficient at prediction compared to the traditional ones. T",0.0,
52a54db78675fdb118fe70499143a376e45cd764,10.1109/iatmsi68868.2026.11465591,TrustSignLion: A Trust-Adaptive Sign-Based Optimizer for Robust Deep Learning in Noisy Environments,2026.0,2026 IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI),Priyanshi Shukla; A. Rasool; A. Jadhav,"Deep learning has a major role of optimization, in which the optimizer determines the rate of convergence, stabilization, and generalization. Recently, Lion is an empirically well-performing, low-memory-cost lightweight sign-based optimizer. It can however, become unstable under noisy and small-batch regimes (batch size of 8-32), where irregular gradient estimates do not allow convergence. In order to address this weakness, we suggest TrustSignLion, which is a trust-adaptive version of Lion, which adds a per-parameter trust mechanism that can monitor historical consistency of gradient signs. The adaptive scaling of trust score deemphasizes updates as the gradients vary (which reduces the degree of instability) and enhances it as the signs match each other, thus enhancing stability without incurring extra computational cost. To ensure that Lion retains its efficiency, TrustSignLion needs only two additional scalars per parameter, which makes it stronger. We compare it with various tasks, such as EEG-based emotion recognition, tabular regression (House Prices), and classification (Iris, Glass, and Pima Indians Diabetes). Findings show that TrustSignLion converges faster, is more accu",0.0,
775ae2ba679336578ba3a6291416be93858c8f93,10.33203/mfy.1769769,The Presence and Determinants of Price Bubbles in the Housing Markets: Empirical Findings from Türkiye,2026.0,Maliye Finans Yazıları,Ayşegül Toy; Adalet Hazar; Şenol Babuşçu,"The study examines the formation of bubbles in the housing market using monthly data from 2010 to 2024 for Istanbul, Ankara, Izmir, and Türkiye. To investigate the existence of price bubbles, the SADF (Supremum Augmented Dickey-Fuller) and GSADF (Generalized SADF) tests were applied. The findings show that housing price bubbles formed across Türkiye and in three major cities between 2017 and 2018, and that these bubbles did not deflate in the relevant years. In this study, Probit regression analysis was performed to determine the variables affecting the likelihood of housing bubbles forming in Türkiye. While the dates of bubble formation were taken as the dependent variable, the Central Bank Leading Indicators Index (CBLI), Central Bank Policy Interest Rates (CBPI) and VIX fear index were included in the model as independent variables. It was determined that increases in the CBLI, CBPI and the VIX Index increase the likelihood of bubble formation.",0.0,https://doi.org/10.33203/mfy.1769769
4d4ccb11f7771ceed4206afb8b103ef4ae4800f5,10.46632/daai/3/1/2,Residential Property Price Estimation Using Machine Learning,2023.0,Data Analytics and Artificial Intelligence,S. Kavitha; P. Brinda; J. Sowmiya; P. Kishorekumar; S. Kailasanath; T. Jayanthan,": Property sales is not much straightforward in the country. Property pricing kept on changing day by day and at times that are being hyped rather than being based on valuation. Our system's key component is its ability to estimate property prices using actual variables. This article describes multiple regression algorithms that can be used with the Python library to estimate housing expenses. The suggested approach yields a more precise forecast by accounting for the complex factors employed in calculating home prices. The house price model and the datasets utilized in the suggested model are explained by this system using machine learning. In this system, we had used the linear regression algorithm. In cities like Mumbai, predictive models are still used to estimate residential sales prices due to factors more than just challenging and complex tasks. In cities like Mumbai, the cost of real estate for sale is influenced by a number of variables.",0.0,https://doi.org/10.46632/daai/3/1/2
6f0082caaaa5accd461cf2763da88d9acd44f0b3,10.3390/jrfm17030130,Empirical Distribution of the U.S. Housing Market during the Great Recession: Nonlinear Scaling Behavior after a Major Crash,2024.0,Journal of Risk and Financial Management,Fotios Siokis,"This study focuses on the real estate bubble burst in the US housing market during 2007–2008. We analyze the dynamics of the housing market crash and the after-crash sequence during the Great Recession. When a complex system deviates away from its typical path by the occurrence of an extreme event, its behavior is strongly characterized as nonstationary with higher volatility. With the utilization of a robust method, we present the characteristics of the aftershock period and provide useful information about the spatial distribution and the decay process of the aftershock sequence in terms of time. The returns of the housing price indices are well approximated by the empirics of a power law. Although we deal with low-frequency data, a time power-law relaxation pattern is identified. Our findings align with those in geophysics, indicating that the value of the relaxation parameter typically hovers around one and varies across different thresholds.",0.0,https://www.mdpi.com/1911-8074/17/3/130/pdf
05a94b6009a8b91ba6b4d88a3c8e2bb4d2fe7a9c,10.63620/mkssjer.2024.1025,Unraveling the Complexity: The Nexus Between Homelessness and Housing Prices in the San Francisco Bay Area and Throughout State of California (A Comprehensive Research Study),2024.0,Science Set Journal of Economics Research,Bahman Zohuri,"This research investigates the intricate relationship between homelessness and housing prices, unraveling the complexities prevalent in both the localized context of the San Francisco Bay Area and the broader scope of the entire state of California. Employing a multi-faceted approach, the study combines traditional research methodologies with advanced Artificial Intelligence (AI) and Machine Learning (ML) tools. Through comprehensive data analysis, the research explores the dynamics of homelessness and housing prices, identifying patterns and trends at both the regional and statewide levels. The study incorporates predictive modeling to discern future trends, spatial analytics to understand geographic variations, and natural language processing to gauge public sentiment. 
By evaluating the impact of policies on homelessness rates, the research seeks to provide actionable insights for policymakers. Ethical considerations guide the implementation of AI, ensuring the responsible handling of sensitive data. Stakeholder collaboration and community engagement are integral components of this research, fostering a nuanced understanding of the challenges faced by diverse communities across ",0.0,
848d3800b8b309ac857451209f1b55f82b38da47,10.37407/kres.2022.40.2.113,"An Empirical Study on the Determinants of Housing Sales Price in Korea, the United States, and Japan",2022.0,Korea Real Estate Society,Chasoon Choi,"This paper empirically examines the determinants of housing sales prices in Korea, the United States, and Japan using the Markov regime switching model. Independent variables are set as stock price index and CD interest rate, the uncertainty index of moneytary policy, Which is an uncertainty indicator of economics policy. The analysis period is from June 1993 to December 2021 in consideration of data acquisition. The results of Markov regime switching model are as follows. First, it is significantly found that state 2(contraction period) is longer than state 1(expansion period) in the housing market in Korea, the United States, and Japan. Second, in state 1(boom period) in Korea, the United States, Japan, it was revealed that interest rates influence on housing price with a positive effect. This means that interest rates cannot be an effective policy tool to stabilize the housing market during the expansion period when housing prices rise. Third, the unemployment rate is found to have a negative effect on housing prices in Korea and the United States, but Japan is found to have no significance. We find that the effects of macroeconmic factors on the housing price volatility are dif",0.0,
d16b0907998476a459e090c4110e7811d0ce5d4d,10.13060/23362839.2025.12.1.585,Very Long-Term International Housing Price Trends,2025.0,Critical Housing Analysis,Dasom Hong; Danny Dorling,"Against the backdrop of recent global house price inflation, this paper addresses the question commonly asked about asset price booms and crises: ‘Is this time different?’ To identify the distinctive characteristics of today’s house price booms, we examined the long-term history of housing prices in five capital cities: Amsterdam, London, Beijing, Seoul, and Tokyo. Specifically, we employed house price, annual income, and average expenditure data to estimate real house price indices from the 1620s to the 2020s. The findings indicate that recent house price inflation is distinct not in severity but in synchronicity. The amplitude of house price booms and busts has remained consistent. However, house price cycles that historically moved independently have, in recent decades, more often shown similar variations both regionally and internationally. Now, prices tend to rise and fall together, but do not rise above the historical peaks of the past.",0.0,https://www.housing-critical.com/data/USR_057_DEFAULT/04_Very_Long_Term_International_Housing_Price_Trends(1).pdf
67c0cc6b53ecb39625d225e0ec44320ea42cc61a,10.22214/ijraset.2022.40272,House Price Prediction Using Regression,2022.0,International Journal for Research in Applied Science and Engineering Technology,Meha Shukla,"Abstract: The housing sector is the second largest employment provider after agriculture sector in India and is estimated to grow at 30% over the next decade. Housing is one of the major sectors of real estate and is well complemented by the growth of the urban and semi-urban accommodations. Ambiguity among the prices of houses makes it difficult for the buyer to select their dream house. The interest of both buyers and sellers should be satisfied so that they do not overestimate or underestimate price. Our system provides a decisive housing price prediction model to benefit a buyer and seller or a real estate agent to make a better-informed decision system on multiple features. To achieve this, various features are selected as input from feature set and various approaches can be taken such as Regression Models or ANN. Keywords: Machine Learning, Artificial Intelligence, Supervised Machine Learning, Regression, Artificial Neural Network (ANN)",0.0,https://doi.org/10.22214/ijraset.2022.40272
309364b6d8361dba9a9e751b55ade4c452cd784b,10.54254/2753-8818/14/20240926,The research of influence factors that possibly lead to the change in house prices,2023.0,Theoretical and Natural Science,Yi-Xiao Huang,"With the significant increase in housing prices, more research on the factors that influence housing prices is urgently needed. Most of the previous research focuses on the number data, such as the average disposable income of the population, property management fees, and the total number of the population in specific areas. In this research, the multiple linear regression model is used to judge the relationship between 10 independent variables (Carpet area, Floor, Total floor, Transaction, Furnishing, Facing, Bathrooms, Balconies, Car parking, and Ownership) and the amount of housing prices based on 910 cases. It is concluded that the ten independent variables all have strong linear relationship with the Amount. With the factors that were studied before, like the ages of the house and the policy for buying homes, these studies indeed give some ideas for the government to come up with the approach to control the increase in housing prices.",0.0,https://www.ewadirect.com/proceedings/tns/article/view/7959/pdf
466453a0acb823acd777ace6ef870a5a22aee178,10.71097/ijsat.v16.i2.6130,Approaches and comparison of valuation of Residential properties by using Deep Learning Technique.,2025.0,International Journal for Sciences and Technology,Shrinath Zine; Sharan Kori,"This study presents an integrated approach to real estate price prediction and property valuation by combining advanced deep learning models with traditional regression techniques. The research leverages machine learning algorithms, including Artificial Neural Networks (ANNs) and Long Short-Term Memory (LSTM) networks, to improve the accuracy and efficiency of predicting residential property prices. A comparative analysis of valuation techniques such as the income approach, sales comparison method, and cost method is also conducted using a case study focused on residential properties in Pune City. The study explores spatial, temporal, and economic variables influencing market trends and integrates them into a hybrid model framework. By combining modern AI-driven predictive tools with traditional real estate valuation practices, this work aims to enhance decision-making for stakeholders such as investors, developers, and urban planners.",0.0,https://www.ijsat.org/papers/2025/2/6130.pdf
9751ca55d97b5d952b12ad09021f2ead76cfdcca,10.38027/iccaua2026tr0046,An Empirical Study on Residential Users' Preferences in Home Purchasing,2026.0,Proceedings of the international conference of contemporary affairs in architecture and urbanism-ICCAUA,Yusuf Akyol; M. Dural; M. Akbulut,"Housing, in addition to fulfilling a basic need like shelter, is a multifaceted phenomenon that directly affects the quality of life of individuals through its economic, social, and spatial dimensions. In Turkey, rising housing prices, accessibility issues, earthquake risk, and changing lifestyles have made housing purchase decisions more complex and multifaceted. This study examines, from a user perspective, the criteria that participants living in the Yenimahalle district of Ankara prioritize in the housing purchase process, through questions posed via an online survey. The results reveal that earthquake safety and structural integrity, location, price/budget suitability, and security criteria are the primary determinants in housing purchase decisions for housing users. It is believed that these findings will contribute to the development of user-oriented housing production processes for housing producers, planners, and policymakers.",0.0,https://journal.iccaua.com/jiccaua/article/download/915/854
ec758e613e1fdd06ae002ac951dbd3d1a7c117a7,10.62510/gca.gcbme113th.05,The Impact f The Current Global Economy on Ghana’s Real Estate,2026.0,Proceedings of the 113th Global Conference on Business Management and Economics,Eugene Owusu Afriyie,"The Impact of the current global economy on Ghana's real estate is huge when it comes to inflation and exchange rates in the country. Real estate affects Ghana's economy because of the amount of household savings that goes into housing. The impact of the current global economy on real estate business in the country has exposed the weaknesses of price determinants in the market. For instance, home prices that are listed in foreign currencies remain stable while properties listed in local currency are subjected to daily changes because of the fluctuations in exchange rates. As a result, homebuyers remain vulnerable in the market because of the current economic distress world economies are facing. In the United States, for example, mortgage rates keep on rising while people continue to leave apartments in search of homes to buy. Home demand continues to increase while supply trails, making it a seller's market. The current inflation rate in the country is reported to be 15.7 percent on a year-on-year basis. This indicates that prices of goods and services increased over the period by 15.7 percent for the month of February. No doubt that the current state of the country's economy is da",0.0,
cfb85be7726797a4a6ede15a05762ddec4f538f5,10.30902/jrea.2020.6.3.21,"A Comparative Study on the Time Series Characteristics of Korea’s
 Housing Prices by Cyclical Phases",2020.0,Journal of Real Estate Analysis,Young-Soo Lee,"This study analyzes how the time series characteristics of two phases (upwards and downwards) in Korea’s housing price cycle are different. Two phases are identified by the algorithm suggested by Bry and Boschan. The minimum period of each phase is set to 6 months. The target data are the Korea National House Price Index and the house price index of seven metropolitan cities. Data was collected from November 2003 to June 2020. The findings are as follows; First, the whole country and the seven metropolitan cities have their own distinctive cyclical features. Second, statistical properties, such as high volatility, skewness, kurtosis, and no n-normality, are getting prominent in the upwards phase. Third, the estimated AR coefficients indicates that dynamic effects of market shocks on the housing price changes are stronger and longer in the upward phase. Fourth, the volatility clustering mainly emerges in the period of the upward phase.",0.0,https://doi.org/10.30902/jrea.2020.6.3.21
479b5c07dc9d0ed224169e0869b2feef78a015b0,10.12783/dtetr/tmcm2017/12647,Multi-model Combination Housing Price Forecasting Based on Web Search Data,2017.0,,Tian-Bao Xie; Jia-Li Gao; Mengjiao Zhao,"In the background of large data, taking the housing price in Xi'an as an example, this paper extracts the relevant search words data from Baidu Index and builds the neural network, support vector machine and random forests model, according to the purchase information inquired by the consumers in Baidu. The gradient boosting decision tree model is established by forecast results of the three single model to achieve a combination of housing prices forecast to determine the final residential sales price index forecast. The result shows that the fitting degree of the combined model is 0.995, and the prediction accuracy is 10.4% higher than the optimal single forecasting model. This method can calculate the new commodity housing price index two weeks in advance than the National Bureau of Statistics. In future studies, this approach will be applied to many types of market forecasts to help companies and consumers make the best decisions.",0.0,https://doi.org/10.12783/dtetr/tmcm2017/12647
3c69b28f68110d604d51f6e30fc2f309d1411cfc,10.2478/amns-2024-0474,Suggestions for Promoting a Better Public Service System under the Low Fertility Dilemma Based on VAR Modeling,2024.0,Applied Mathematics and Nonlinear Sciences,Xiu-Qing Liu; Lixin Xu; Weiwei Chen; Qing-Shan Wu,"Abstract This paper provides an in-depth analysis of the rapid decline in fertility and population aging. Using LASSO penalized Poisson regression and TVP-VAR model improved by MCMC algorithm based on Bayesian network, the factors affecting the fertility level and their interrelationships are studied. It is found that fertility and education levels affect each other with probabilities of 0.0806 and 0.0825 respectively at 10% significance level. The positive shock of social security level on fertility level increases the response value of fertility level from −1.5 to about 7.5 in 10 lags, showing a positive effect. In contrast, the response of fertility level to house prices gradually decreases from 5 in period 1 to −2.5 in period 10, indicating a negative impact. These analyses provide a scientific basis for constructing a public service fertility support system that can help mitigate the current challenges of low fertility levels.",0.0,https://sciendo.com/pdf/10.2478/amns-2024-0474
bef6a612825c7689b0ce8d1af1bbc724e8a7c529,10.26562/irjcs.2023.v1005.29,Real Estate Price Prediction Using Artificial Intelligence,2023.0,International Research Journal of Computer Science,N. Kalyani; B. Shankar; Bharat Lekkihal; Vinod Kumar,"The sales of houses are influenced by various factors such as location, area, population, and other relevant information. Predicting individual housing prices can be instrumental in estimating future real estate prices. This study employs the Random Forest algorithm, a machine learning technique, as the primary methodology for developing a housing price prediction model. By focusing on the Random Forest algorithm, this project aims to optimize prediction accuracy and consistency, considering it as the best model for price prediction. The implementation of this project involves using Python (AI/ML) for coding the Random Forest algorithm, while HTML, CSS, and JS are employed for designing the system's frontend. Ultimately, the House Price Prediction system proves to be a valuable tool for accurately assessing property prices and maintaining a record of price fluctuations, promoting transparency and discouraging fraudulent activities.",0.0,https://doi.org/10.26562/irjcs.2023.v1005.29
7cfff0a4b539f95c912c49c45903cc7b405ccc49,10.1002/hec.70098,Health Preferences and Sorting in the City.,2026.0,Health Economics,Manuela Puente-Beccar,"There are large health inequalities between neighborhoods in many cities of the world. This paper studies individuals' sorting based on health amenities and exposes an important connection between health preferences and the housing market. I estimate a neighborhood choice model using geolocated data from a health survey in New York City and neighborhood characteristics from different data sources. I find that individuals with higher preferences for being healthy are more likely to choose neighborhoods close to health amenities such as parks, and this sorting explains a large part of observed geographical inequalities in health behaviors. Moreover, the model predicts that a higher demand for health amenities capitalizes into house prices and displaces poor individuals to neighborhoods further from these amenities. This implies that health awareness campaigns might actually worsen the inequality in access to public health amenities.",0.0,https://doi.org/10.1002/hec.70098
9a552ff602ee40e8158f5661ab222d977227142a,10.54097/meqajy98,The Research on Factors Influencing Housing Prices -Take Kansas City as an Example,2024.0,"Highlights in Business, Economics and Management",Muqi Li,"This article aims to identify those factors that have an impact in housing prices. The sample of the study is 15 variables, including 19554 pieces of data. Among the 15 variables, there are both factors of the house itself and some external influencing factors. The method of Multiple Linear Regression is used to analyze the significant factors with the housing prices of Kansas City. Based on these 15 variables it does correlate with house prices. The 19554 data substituted into Multiple Linear Regression Model. The result shows that grade, latitude, years of built, waterfront, view, square of basement, square of above, zip code, bathrooms and condition have a significant linear relationship with prices, while the id, date, bedrooms, square of lot, floors and year of renovating fail the significance test. In totally, the volatility of housing prices in Kansas City can be considered by the extent to which these factors affect them.",0.0,https://drpress.org/ojs/index.php/HBEM/article/download/27600/27131
ba46f693643852d3929f18a12745e56eff4a2421,10.54097/92raxz19,Forecast of Housing Prices in Beijing and Analysis of Influencing Factors,2024.0,Highlights in Science Engineering and Technology,Yuxi Liu,"Real estate is an important part of China's real economy, and housing prices are one of the basic elements in the entire real estate market. This paper analyzes the housing price data of Beijing, China, and firstly uses a multiple linear regression model to determine whether the factors that have an important impact on China's housing prices also play an effect on Beijing's housing prices. And then this paper analyzes how much each factor has an impact on Beijing's housing prices. Additionally, the ARIMA model is used to predict the trend of housing prices in Beijing in the next 10 months according to the monthly data of the past 10 years. Finally, the change point analysis method is used to study the effect of the Corona Virus Disease 2019 (COVID-19) on housing prices in Beijing. It aims to understand the operating mechanism behind housing prices and give policymakers, investors and home buyers more suggestions and instruction.",0.0,http://dx.doi.org/10.54097/92raxz19
6927ee2814dc88855faef41002779b2fa6f834fb,10.54097/ezaycc33,Effect of Housing Factors on Price in Seattle During the COVID-19 Pandemic,2024.0,Highlights in Science Engineering and Technology,Hao-Quan Hu,"Due to the influence of the COVID-19 pandemic, global economic trends have faced an immense change. The major difficulty experienced by workers, laborers, and households are the tremendous changes in housing prices in every part of the world which are both hard to bear and almost impossible to forecast from current factors. With a particular dataset based on the housing price in Seattle, Oregon, USA. This research will use a multiple linear regression model to predict the housing price through various housing factors and to compare the accuracy of the prediction and the relationship between variables by contrasting the train and test set whilst also constructing a residual graph. The result ends up with a moderate accuracy due to the influence of multicollinearity between the factors, this can be seen through the variance Inflation Factor. The process requires the standardization of the data in order to make the test legitimate.",0.0,http://dx.doi.org/10.54097/ezaycc33
4d30985c66e8084d09e60c972c248db703edc235,10.5539/ijef.v9n11p118,A Comparative Analysis on the Wealth Effect between in the Stock Market and in the Housing Market in China,2017.0,,Lin Liu; K. Shi,"In this article, a threshold cointegration test within the framework of Autoregressive Distributed Lag model suggested by Li and Lee (2010) was employed to quantify the wealth effects in Chinese stock market and domestic housing market. The time-varying features of wealth effects in these two markets were investigated through rolling regression test. The empirical results show that the substitute effect exists in the status of strong market while the wealth effect exists in the status of weak market. It is noteworthy that the wealth effect in the stock market shows an increasing trend while the wealth effect in the housing market reveals a stable trend. The policy implication is that the authority should properly strengthen the regulation in the stock market and curb the rise of housing price when the markets are in the strong status while should increase the disposable income for residents if the markets are in the weak status.",0.0,https://doi.org/10.5539/ijef.v9n11p118
4afbef4121e3f94688609b0a4aab3b20ec3927e2,10.54097/rr66k248,An Empirical Study on the Influencing Factors of Second-Hand Housing Prices Based on the OLS-WLS Model,2026.0,Journal of Innovation and Development,Shuohan Jiang; Linjie Chang; Guang-Chun Lu,"This study investigates the second-hand housing market in Beijing, focusing on building area and school district status as the core variables, while controlling for housing features such as renovation level, heating type, and elevator availability. The effects of these factors on housing prices are quantified by using a multiple linear regression model. After conducting normality and heteroscedasticity tests on the residuals, and applying weighted least squares (WLS) correction, the results indicate that building area and school district status have significant positive impacts on housing prices. Elevator availability increases prices, centralized heating has a negative effect, and high-end renovation is not statistically significant. The adjusted of the model is 0.687, indicating a good overall fit. The findings of this study provide practical guidance for buyers and offer a reference for government housing market regulation.",0.0,https://drpress.org/ojs/index.php/jid/article/download/35007/34206
24c898db0280ed27b83fec434fc31363de05ba6c,10.54254/2754-1169/2025.29736,Study on the Influencing Factors of Boston Housing Price,2025.0,"Advances in Economics, Management and Political Sciences",Haoran Hua,"This paper presents a thorough analysis of the Boston Housing Dataset, specifically examining how median house prices (medv) relate to several key factors, with a primary focus on the per capita crime rate (crim). The Boston Housing Dataset serves as a foundational framework for applied data science projects. Through rigorous statistical methods and insightful figures, we aim to uncover the significant influences these factors may have on housing prices. This article explores the factors that may influence housing prices, examines their characteristics and impacts, and provides predictions regarding future housing price trends. Analyses reveal that rising crime rates often have a negative impact on the median housing values within a community.While rising crime rates can lead to a decline in median housing values, the extent of the impact and the underlying mechanisms may differ depending on the region and local circumstances.",0.0,https://www.ewadirect.com/proceedings/aemps/article/view/29736/pdf
f56d7d4780d15d2ba7a052ebeff827ad26ae1063,10.54254/2755-2721/13/20230724,Predicting houses price by deep learning neural network,2023.0,Applied and Computational Engineering,Zi-Dong Xu,"Deep learning is widely used in various fields, the article proposed a deep learning method to predict house prices through different characteristics of real estate, establish a prediction model, and carry out simulation experiments. First, extracting data from property transactions records, it is difficult to directly input the raw-data into the deep learning model, and there may be overfitting in the model training, so data will be pretreated. Second, Fully-Connected Neural Network is used to model different features influences to price. The sample data will be randomly divided into a training set and a validation set, of which 70% of the samples are used for building and training the model, and the remaining 30% are used for model accuracy verification. Experimental results show that the model can achieve a high accuracy in predicting houses price. The model can be used as a reference for the evaluation of housing prices.",0.0,https://www.ewadirect.com/proceedings/ace/article/view/4500/pdf
9cc2e42d1b09ec3f20900f6397673719c8f77f7f,10.54097/d82db373,Research on the Price Prediction of Commercial Housing in Beijing,2024.0,"Highlights in Business, Economics and Management",Yiyang Zhou; Xin-Ping Liu; Min Sun,"In order to determine the best appropriate housing price prediction model, this study constructs a linear regression model, a BP neural network model, and a time series model based on data on commercial housing prices and their affecting variables in Beijing during the past 23 years. A set of 12 independent factors that impact the cost of commercial housing is selected first. Then, three models are created, and their fitting effects are compared and analyzed to forecast the average cost of commercial real estate in Shandong Province. It is shown that the multiple linear regression model is more appropriate for long-term prediction and that the time series model predicts data more recently than the BP neural network model; Therefore, it can be used if the prediction period is longer. Although home prices can be predicted theoretically using these three approaches, more work has to be done to fine-tune the applicable models.",0.0,http://dx.doi.org/10.54097/d82db373
f665cafc2c3808b037de53e17cb1c1e29d8f0993,10.54822/qvhm1662,The Utrecht Housing dataset: A housing appraisal dataset,2025.0,Computers and Society Research Journal,S. van Otterloo; Pavlo Burda,"This paper introduces a real-world dataset for analysing and predicting house prices. The dataset consists of actual data on the Dutch housing market collected in 2024 for a total of 153 houses in one city (Utrecht in The Netherlands). The dataset incorporates diverse variables on individual houses, includ- ing property characteristics (e.g., house type, build year, geolocation, area, energy label) and market metrics (e.g., asking price, final price). The data was collected from two public sources. The dataset has been created to help researchers and educators to demonstrate machine learning principles on several problem types. It can be used for classification (energy label and energy efficiency) and regression/ price estimation. There are ten original input features and one derived feature. The dataset can be freely used without restrictions under a Creative Commons license and is available via open data platform Kaggle.",0.0,https://research.vu.nl/en/publications/85957385-94ac-4204-ae69-ce2e2dd38571
570aaf50b40f8aa4b41c1b73f3e257712bfc09cf,10.1109/icfts62006.2025.11031771,House Price Prediction Using Regression in Machine Learning,2025.0,2025 International Conference on Frontier Technologies and Solutions (ICFTS),G. Madhuri; A. Kumar; Mahmoud A. Hussain; N S S S Girish Kumar; M. Jabbar,"The house pricing projection is crucial to the financial services industry and real estate sector. People are researching market techniques and attempting to purchase a new property within their means. However, the primary drawback of the current method is that it does not determine a home's price based on the essential forecast of future market trends, which results in an increase in price. Therefore, our paper's goal is to accurately forecast a home's price with minimal loss. For predicting house prices several factors need to be considered including location, size, amenities and economic indicators. There are very great techniques that machine learning offers for modelling and house price prediction. Regression algorithms are really valuable for predicting continuous values, like house prices by computing the association between data features and target values. The base tool in this direction is simply a basic linear approach, which fits best when discovering simple, linear trends. Decision trees and random forests add flexibility for modelling much more complicated and non-linear relationships. More advanced techniques like gradient boosting and XGBoost improve the accuracy in ",0.0,
bd67f9facc8e24437e1d0329dcaba4cebdc4e484,10.31629/bi.v4i2.3433,Elastisitas Permintaan Rumah Sederhana Tipe 36 di Kota Padang Provinsi Sumatera Barat,2021.0,,B. Paramita,"This research aims to analyze type 36 house demand elasticity in Padang City, West Sumatera Province. It used secondary data collected from 32 units of sample observation. The variables were 36-type housing price, distance to CBD, district density, number of household, and GDP per capita. The instruments of analysis were data panel regression using OLS approach, fixed effect , and random effect. The analysis results show that fixed method gives the best result of regression among the three approaches in the data panel. The variable of house price has a negative and significant correlation with the demand in Padang City with an elasticity level of 1.56%; the distance to CBD has a negative and correlation with demand with an elasticity level of 1.73%. The research results give a picture that the demand for simple houses in Padang city, West Sumatera Province is elastic toward the price of type 36 house, and distance to CBD.",0.0,https://doi.org/10.31629/bi.v4i2.3433
8fd1a903a1b48fedf4fec2447b29bb6c3dbdab5b,10.25236/ajcis.2024.070401,The Xgboost-Bagging Approach of Predicting House Prices,2024.0,Academic Journal of Computing & Information Science,Xin-Chao Wu,": In this paper we aim to establish appropriate models to predict housing prices that are affected by multiple factors and we use various machine learning methods to predict house prices. Boosting methods often aim to reduce the bias of a model but can increase its variance. Conversely, bagging methods tend to decrease the variance of a model. Therefore, we attempted to combine these two algorithms to improve the model's capability for predicting house prices. After comparing different methods, we combined the XGBoost and Bagging to construct a novel model for predicting house prices. The experimental results demonstrate that among all the methods, the proposed approach achieves the best prediction performance for housing prices. Furthermore, when compared to using XGBoost alone, our integrated model exhibits improved precision, indicating its efficacy in addressing the challenges associated with housing price prediction.",0.0,http://francis-press.com/uploads/papers/TK3pWobwuoqC0AWINgZl1T7CMpnPUt0yOs1KFjKS.pdf
e8599af6eb800df4353596ffebf7e076df2aa479,10.54691/bcpbm.v32i.2956,Research on the Prediction of US House Prices Based on Machine Learning,2022.0,BCP Business & Management,Yun-Ling He,"With the increase in the standard, houses have become an indispensable part of people’s lives. However, purchasing houses needs to consider the prices. Therefore, this paper uses machine learning to predict US house prices. Based on the random forest and linear regression method used in this research. It is found that the use of the former has a good effect on predicting multivariate nonlinear relationships in house prices. After comparing the results of actual prices and predicting prices, residents can select different room structures by contrasting them with experimental types as the numerical results are basically accurate. This research provides theoretical value to the literature on housing price prediction and brings different enlightenment to policymakers, regulators, and investors. As a result, this research plays a key role in maintaining the order of the real estate market and helping people make good choices.",0.0,https://bcpublication.org/index.php/BM/article/download/2956/2918
fb5183981e725691995dd9c6147fa08225de7143,10.56294/la2025153,Revolutionizing Home Price Forecasting Through Machine Learning,2025.0,Land and Architecture,Awais Azam; S. Rai,"Introduction; This study develops a data-driven framework for accurate house price prediction using machine learning techniques. Method; We implement a comprehensive methodology involving rigorous data preprocessing, exploratory visualization through multiple chart types, and comparative evaluation of predictive models. Our approach demonstrates the effectiveness of combining analytical visualization with algorithmic modeling for real estate valuation. Result; The research contributes to both academic discourse and practical applications by establishing robust data cleaning protocols and validating model performance. Results indicate significant improvements in prediction accuracy, offering valuable insights for homeowners, investors, and urban planners. Conclusion; This work advances the field of property analytics while providing a replicable methodology for housing market analysis in different socioeconomic contexts.",0.0,https://la.ageditor.ar/index.php/la/article/download/153/44
cadcc9e5dd524318f427b334b892f61cfd3fe419,10.52344/hfr.2021.4.0.111,Long-Term Demand Estimation for Reverse Mortgage Considering Changes in Population Structure and House Price Prospect,2020.0,Housing Finance Research,Jonghoon Lee,"For the stable operation of the Home Pension(Korean public reverse mortgage) system, policy establishment and risk management should be made based on demand estimates that reflects the main characteristics of reverse mortgage. In this study, changes in population structure and house price prospect were selected as the main factors that affect Home Pension subscriptions to estimate demand through the Bass diffusion model. The trend of cumulative number of surviving subscribers in Home Pension was investigated to reflect changes in population structure in the diffusion model. In addition, a comparative analysis was conducted to examine the impact of house price forecasts on new Home Pension subscriptions. The analysis shows that the number of new Home Pension subscribers will peak from the mid-2030s to 2040, after which the total number of new subscribers will remain stable with a long-term balance with the death toll.",0.0,http://www.e-hfr.org/download/download_pdf?pid=hfr-4-0-111
be8b17039c5a3340c4d548e38963a1683392d361,10.1145/3749566.3749594,Predicting New York City Rent through Machine Learning —— Based on Airbnb Data,2025.0,Proceedings of the 2025 5th International Conference on Internet of Things and Machine Learning,Youzhe Gong,"This research aims to predict the rent of Airbnb listings in New York City through machine learning models and analyze the key factors may influence the prices. Utilizing Airbnb data from New York City for the year 2024, the study employs four models: Ridge Regression, Decision Tree, Random Forest, and XGBoost. Through feature engineering and parameter tuning, the models’ performances were optimized and compared. The Random Forest model was determined to perform the best, achieving the lowest test set RMSE of 29.6926. Additionally, the study reveals the impacts of key variables such as the number of rooms, location, number of amenities, and minimum stay requirements on rent prediction, based on feature importance ranking and OLS regression results. The significance of this study lies in providing an effective method for housing price prediction and offering a reference for hosts to set reasonable pricing mechanisms.",0.0,https://dl.acm.org/doi/pdf/10.1145/3749566.3749594
a20aa8b7e160e4efca4095b649340eab5e5fcdcf,10.3390/economies14090388,Macroeconomic Determinants of Housing Prices in Malaysia: Evidence from Time-Series Econometric Analysis,2026.0,Economies,Jin-Sheng Chang; Evan Lau; N. Bintoro,"This study examines the effects of population, unemployment rate, construction costs, income per capita, and interest rates on housing prices using annual data from 1990 to 2024. Adopting time series econometric analyses, including stationarity, the ARDL model, VAR, Granger causality and dynamic estimation of VDC and IRF. The results confirm a long-run equilibrium relationship between housing prices and the selected macroeconomic variables. Income per capita and construction costs positively influence housing prices, whereas interest rates have a significant negative effect. In the short run, only income per capita is significant. The findings provide important policy insights for improving housing affordability through sustainable income growth, prudent monetary policy, and efficient housing development. Future studies should incorporate regional and institutional factors to better explain housing price dynamics.",0.0,https://doi.org/10.3390/economies14090388
4d69550518ff9b0f7ce57b5a5cf020f6d43b5a5d,10.22313/reik.2023.21.3.101,A Study on the Determinants of Row House Sale price in Jeju-do,2023.0,Residential Environment Institute Of Korea,Young-Jun Yang; S. Lee,"In this study, the current status of houses in Jeju-do was examined, and the determinants of row house prices were analyzed using actual transaction price data of row houses traded from 2019 to 2022. 
To summarize the analysis results focusing on Jeju-do, the price of small sized row house is higher than that of large sized. The higher the number of floors, the higher the price, and the higher the land area, the higher the price. Over time, prices have been shown to fall and then rise. The gross floor area, the number of parking per household, and the remaining building to land ratio have a positive effect on the price, and the larger the width of the road facing the land, the higher the price. By region, prices are high in the order of Eup·Myeon area of Seogwipo-si, Dong area of Jeju-si, Eup·Myeon area of Jeju-si and Dong area of Seogwipo-si, and by special-purpose area, residential area, green area, and control area are in the order. The higher the distance between elementary schools and the market, the higher the price, and the lower the distance between middle schools and government offices. One of the purposes of this study, the further away the row housing complex from the ap",0.0,
28d7d0e2158a32ae7b12b56229e2ede6fd95c7fe,10.56028/aetr.6.1.549.2023,Determining the Best Model among Candidate Machine Learning Models for Chicago Suburb House Price Data,2023.0,Advances in Engineering Technology Research,Rui Zhang,"With the development of the society, there is an increasing need of predicting the house price in order to purchase properties economically. Myriads of machine learning methods have been developed to achieve this goal. In this paper, we narrow our focus on three types of machine learning methods-Linear Regression, Polynomial Regression, and Neural Network (Multilayer Perceptron Regressor)  and train all of them on Chicago suburb house price dataset and employ all of them to make predictions. Performance is evaluated using mean squared error (MSE) and R square (R2) metrics. Preliminary experimental results demostrate that Neural Network outperforms the other candidate methods in all cases. Polynomial Regression of degree 2 outperforms Linear Regression in most cases but performs arbitrarily bad in worst cases. Therefore, Neural Network (MLP Regressor) is the best method for predicting Chicago suburb house price.",0.0,https://madison-proceedings.com/index.php/aetr/article/download/1356/1353
88e19a7cf222cd85cb0e6389b23e07e5926f36a0,10.12962/jaree.v7i1.328,House Price Prediction using Multiple Linear Regression and KNN,2023.0,JAREE (Journal on Advanced Research in Electrical Engineering),F. Febriyanto; E. Endroyono; Yoyon Kusnendar,"The transition of BPHTB management from central taxes to regional taxes is a continuation of the regional autonomy policy. The difference between the market value and the prevailing NJOP poses a challenge for the Sintang District Government in determining the Tax Object Acquisition Value (NPOP) as the basis for imposing BPHTB. Machine learning has been extensively explored for predictions and can be an alternative that can help predict NPOP, especially house prices. This study uses backward elimination and forward selection methods to select the features used in this study and multiple linear regression and K-Nearest Neighbor methods to make house price prediction models. The results of model performance measurement using RMSE, Multiple Linear Regression method with feature selection using backward elimination resulted in a better model with an RMSE value of 44.02 (million rupiahs) and an R2 value of 0.707.",0.0,http://jaree.its.ac.id/index.php/jaree/article/download/328/142
2532531a5396139931802327eeb3c6d55011bf3a,10.1145/3724154.3724162,A Novel Graph based Deep Learning Model for Real Estate Finance,2024.0,Proceedings of the 2024 5th International Conference on Big Data Economy and Information Management,Linfeng Cao; Size Hou,"We aim to explore how urban green spaces, particularly parks, influence house prices in Guangzhou City by examining the association mechanism. With the advancement of urbanization, green Spaces are becoming increasingly important in urban development, especially due to their significant impact on property values. We collected data on green space and house prices in Tianhe, Guangzhou, including 12 parks and 1082 house price samples. We proposed a graph convolution network-based method for regression analysis and relationship extraction. The experiment shows that our model is the state-of-the-art model in home values regression task. We have shown that the larger the area of green space and the closer it is to green space, the higher the house price. By examining the complex relationship between urban green space and property values, this study provides valuable resources for urban planning and development.",0.0,https://dl.acm.org/doi/pdf/10.1145/3724154.3724162
5d5481f1bdb4441dc2691f3437c1456c28db4354,10.31235/osf.io/nt2yq,A Grid Based Approach to Analysing Spatial Weighting Matrix Specification,2019.0,,C. Rahal,"We outline a grid-based approach to provide further evidence against the misconception that the results of spatial econometric models are sensitive to the exact specification of the exogenously set weighting matrix (otherwise known as the 'biggest myth in spatial econometrics'). Our application estimates three large sets of specifications using an original dataset which contains information on the Prime Central London housing market. We show that while posterior model probabilities may indicate a strong preference for an extremely small number of models, and while the spatial autocorrelation parameter varies substantially, median direct effects remain stable across the entire permissible spatial weighting matrix space. We argue that spatial econometric models should be estimated across this entire space, as opposed to the current convention of merely estimating a cursory number of points for robustness.",0.0,https://osf.io/nt2yq/download
b00384dc005ab599f3a2e3db9e1ae46093a9588c,10.36347/sjahss.2024.v12i08.001,Research on Jinhua City Sports Facilities Planning and Urban Spatial Structure Optimization,2024.0,Scholars Journal of Arts Humanities and Social Sciences,Ningning Wei; Lingfeng Hu; Chengxiang Fan,"With the increasing awareness of national fitness, the planning and management of sports venues has become the key to improving the level of urban public services. Taking the POI data of sports venues in Jinhua City as the research object, this paper analyzes the spatial distribution characteristics of sports venues in Jinhua City, traffic accessibility and its relationship with housing prices. The study found that all the sports venues in Jinhua have good traffic accessibility, and there is a positive correlation with housing prices. Among them, the average housing prices in urban public sports venues and commercial fitness and leisure venues are higher. The research results provide a scientific basis for the planning and management of sports venues in Jinhua City, and are of great significance for promoting the balanced development of sports facilities and improving the quality of life of residents.",0.0,https://doi.org/10.36347/sjahss.2024.v12i08.001
42eae452911fa468bf9b79f4ee0d1fca2626910d,10.12677/mse.2021.102019,CiteSpace-Based Knowledge Map Analysis of the Influence of Urban Rail Transit on the Housing Price along the Route,2021.0,Management Science and Engineering,",-Zhan-Ran Cheng; ,-Ceng-Hua Jun; ,-Chen-Yi Fan; Jun Xie; Rancheng Zhan; Huajun Zeng; Yifan Chen; X. Ou","With the continuous increase of urban population and the increasing pressure of urban traffic, public transport similar to rail transit has become the main way for citizens to travel, and the convenience of rail transit also deeply affects the housing prices along the line. In recent years, relevant scholars have carried out a lot of research work on the impact of rail transit on housing prices along the line, and achieved a series of research results. Based on the CiteSpace literature analysis tool, this paper analyzes the CNKI literature and explores the theme, content system, research characteristics and development trend of housing prices along the rail transit line in a visual way. The results show that: 1) The systematic research content of housing prices along rail transit has gradually evolved from the original scattered content, weak connection and single analysis method to the main research subject; 2) Rail transit has a small impact on housing price in the city center. The further away from the city center, the greater the impact on housing price. The influence radius of station location on the real estate along the line is about 500~800 m; 3) Generally, before and after",0.0,
33cb5779c89ee55439004ba1ece30754ef9b21e5,10.1145/3745133.3745148,A Study on Housing Price Forecasts Based on Web Search Indices,2025.0,Proceedings of the 2025 International Conference on Digital Economy and Information Systems,Jia Huo; Chia-Wei Chu; Chunglun Wei,"With the development of the Internet, the web search index has become an important data source for economic and market forecasting. This paper investigates the prediction of new residential price index in Nanjing based on web search index. Keywords are extracted from news text, keyword expansion and screening are performed, and Baidu index is used to obtain search data, which is modeled by combining differential autoregressive moving average model (ARIMA), random forest, and long-short-term memory neural network (LSTM) model. The experimental results show that the web search data are significantly associated with the house prices in Nanjing, and the prediction model constructed using the search index performs well, with the best fitting effect of the random forest model. This study proves the feasibility of web search index in house price prediction and provides a new perspective for market analysis.",0.0,https://dl.acm.org/doi/pdf/10.1145/3745133.3745148
a21a5a2bf56bc06f87bdd643ec59d32508619718,10.1080/23754931.2024.2402781,The Fiscal Capitalization of Public Spending: Does Municipal Operating and Capital Spending Increase Property Values?,2024.0,Papers in applied geography,Valencia Prentice; Mohamad Bamanie; Umesh Jaiswal,"Abstract This study investigates the impact of local public spending on property values. The theory of fiscal capitalization, first proposed by Charles Tiebout and Wallace Oates, holds that a positive relationship exists between local public spending and property values. The theory posits that individuals and businesses make locational decisions based on their preferences for a community’s mix of taxes and spending on services. Although an extensive literature exists supporting fiscal capitalization, studies rarely investigate the separate effects of operating versus capital expenditures. Furthermore, few studies have investigated whether a distinct capitalization effect exists between the signal created by ongoing capital expenditures and a longer term amenity effect realized once projects are completed. This article extends the fiscal capitalization theory by assessing these distinctive effects on property values. The study uses a border discontinuity research design, limiting the sample to residential properties near municipal boundaries. The results show capital and operating expenditures have different effects on property values. In addition, the spending on capital improvemen",0.0,
8b6c495557f66917d5732408eb392d503d05091f,10.1109/incet64471.2025.11140248,Ensemble Machine Learning Models Used for Forecasting in Rental Apartment Price Prediction of Metro City in India,2025.0,2025 6th International Conference for Emerging Technology (INCET),J. M. Shanthi; P. S. Rao; V. R. Kumar; G. Nithya; J. Kartigeyan; Amit Gupta,"In order to help stakeholders make well-informed real estate decisions, this study assesses two classes of machine learning algorithms to forecast rental home prices in India. The goal is to determine which models are the most accurate. The study examines a large dataset with characteristics including home type, size, location, and cost across major Indian cities using a quantitative research approach. A great deal of preprocessing was done, which included feature selection, dimensionality reduction, encoding categorical variables, and managing missing data.Its thorough assessment of a variety of machine learning models using a specially assembled dataset of rental properties in India is what makes the study distinctive. By concentrating exclusively on rental price prediction, this paper fills a need in the Indian market and adds to the body of previous material. The results show that the models' performance varied significantly, with the K-Neighbors Regressor surpassing the others by a little margin in terms of MAE. By demonstrating how machine learning may improve real estate market analysis and decision-making, this study makes a theoretical and practical contribution. A vital t",0.0,
bd2935078a67122e5b83f14951f3e0fe69398596,10.22313/reik.2024.22.2.81,The impact of “Introduction of Smart Store Technology” on sales and satisfaction of small business stores: Around customer communication,2024.0,Residential Environment Institute Of Korea,Chong-Ho Chang; Hee-Soon Jang,"This study decomposes the local gap through the oaxaca factor analysis to find out how differences in housing prices affect the management costs with data the average value of three-year management costs between 2014 and 2016 to 536 complexes in three Gangnam and Gangbuk districts in Seoul. The results of the analysis of 290 complexes in three Gangnam and 246 complexes in three Gangbuk districts are as follows. First, housing prices did not affect administrative costs within the region, but were variables that affected data pooling. Second, when compared with the three Gangnam districts, the results of the characteristic coefficient, which can be explained by the characteristics of the complex and the external environment, showed that the gap in the management cost increased when the number of security personnel, repair and maintenance costs, elevator maintenance cost, floor area ratio, and 60m2 or more to 85m2. Third, the factors behind the gap between Gangnam 3 districts, which have higher housing prices than Gangbuk 3 districts, were confirmed to be the number of security personnel, repair costs, floor area ratio and elevator maintenance costs, and the higher the size and income",0.0,
e99b094a95364d4f1856333aa636f1ddd269c866,10.48081/bgqf1884,HOUSING PRICE DYNAMICS USING ONLINE LISTINGS AND MACROECONOMIC INDICATORS IN KAZAKHSTAN,2026.0,Bulletin of Toraighyrov University. Physics & Mathematics series,R. N. Yestebek; A. Adamova,"Understanding the dynamics of housing prices is important for analyzing real estate markets, especially in emerging economies, where official statistics are often limited or published with significant delays. This study provides an empirical basis for modeling housing price dynamics by combining online real estate quotation data with macroeconomic indicators based on the example of the housing market in Kazakhstan. The housing price index is calculated based on the average price per square meter obtained from online ads and normalized to the general base period to ensure time comparability. Key macroeconomic variables, including consumer price inflation and the exchange rate of the US dollar against the tenge, are taken into account along with their lagging values to account for the delayed market reaction. Several time-validated machine learning models are used to analyze the relationship between macroeconomic conditions and housing price dynamics. The results show that nonlinear ensemble methods provide higher efficiency in assessing the short-term dynamics of the housing market. The results demonstrate the practical value of online listing data for building housing price indices",0.0,
89ca73e341fb243ec97c565b4db5c5b25941b66d,10.21837/pm.v19i17.988,RESIDENTIAL BUILDING QUALITY MEASUREMENT AND THE RELATIONSHIP WITH HOUSE PRICES: A STUDY OF HOUSES IN KLANG,2021.0,PLANNING MALAYSIA,Muhamad Hilmi Mohamad@Masri; M. Sa’ad; Najma Azman; M. H. H. Aliasak,"This research focuses on the particular aspect of residential building quality and aims to measure the relationship that affects houses prices in Klang. The researcher through the problem statement and literature review has noted that respondents have knowledge in measuring the quality of their own house, but measurement must be conducted on an empirical basis with evidence. The main research objectives were to identify residential building quality and to measure the residential building quality effect on houses prices. The sampling of the research was conducted on fifty houses, and the measurement was conducted with the help of Regression Analysis. The results obtained show a significant relationship between higher quality of residential buildings and higher prices that can be commanded. The findings also could help to improve the estimation of value for new and older houses in the sampled areas.",0.0,https://doi.org/10.21837/pm.v19i17.988
63d8fc684efdabf1d275a2c98c1884247709018a,10.32468/be.1005,I know what you did during the last bubble: Determinants of housing bubbles' duration in OECD countries,2017.0,,J. S. Amador-Torres; J. Gómez-González; Sebastián Sanín-Restrepo,"We use hazard models to study the determinants of housing price bubbles’ duration. We answer two related questions: i). Does prolonged domestic monetary policy easing increase the duration of housing price bubbles? And, ii). Does prolonged monetary policy easing in the US influences housing bubbles’ duration in other OECD countries? Our results suggest that the answer to the first question is a clear yes, while the answer to the second question is an indirect yes. Other variables that are also good predictors of the duration of bubbles are GDP growth and the degree of financial market development. Bubbles in developed financial markets tend to last longer. Other institutional variables, such as loan-to-value caps and limits to banking leverage, population growth and the consumer confidence index, have no effect on the probability of ending a bubble. Our results have relevant policy implications.",0.0,http://doi.org/10.32468/be.1005
b44b6ce256aa963caa5123c0f7d3a96cb91d462a,10.17762/ijritcc.v11i9.8321,House Price Prediction using Machine Learning Algorithms,2023.0,International Journal on Recent and Innovation Trends in Computing and Communication,Angulakshmi M; D. M; M. I; Thilagavathi M; A. P,"House prices are a major financial decision for everyone involved in the housing market, including potential home buyers. A major part of the real estate industry is housing. An accurate housing price prediction is a valuable tool for buyer and seller as well as real estate agents. The study is done for the purpose of knowledge among the people to understand and estimate the pricing of their houses. The prediction will be made using four machine learning algorithms such as linear regression, polynomial regression, random forest, decision tree. Linear Regression has good interpretability. Decision tree is a graphical representation of all possible solutions. Polynomial regression can be easily fitted to a wide variety of curves. Regression and classification issues are resolved with random forests .Among the given algorithm, Random forest provides better accuracy of about 89% for given dataset.",0.0,https://ijritcc.org/index.php/ijritcc/article/download/8321/6598
e3794aa857842b6b19d82a27205df61f9be77801,10.1111/acfi.70222,"EPA
 Enforcement Actions and Property Prices",2026.0,Accounting & Finance,Van Le; My Nguyen; A. Pham,"
 This study examines the effects of Environmental Protection Agency (EPA) enforcement actions on property prices in the United States. Using data on EPA enforcement cases, we assess how investors and homeowners react to regulatory actions to curb environmental violations. Our analysis reveals that residential properties in proximity to EPA enforcement sites experience a significant short‐term decline in value, with more pronounced effects for enforcement cases related to hazardous waste and for properties located closer to the enforcement sites. However, the price reversal 3 months post‐enforcement suggests that market overreaction plays a role in the initial decline. Our findings underscore the importance of environmental regulation enforcement in shaping real estate market dynamics, highlighting the economic impact of environmental pollution and regulatory measures on local property values.",0.0,https://doi.org/10.1111/acfi.70222
e43415eb9e17057ba41c6f1ab5d9de17ac56f13e,10.54091/krepa.2023.24.3.137,A study on the Factors Influencing Disposable Income of Self-employed Households : Focusing on Comparison with Workers' Households before and after COVID-19,2023.0,Korea Real Estate Policy Association,D. D,"This study used data from the Household financial welfare survey to conduct a regression analysis on the factors affecting disposable income of self-employed households and compared them with the analysis results of workers' households before, and after COVID-19. As a result of the analysis, gender, number of household members, less than 132.2㎡, residential housing prices, and financial assets had a positive effect on disposable income in common before and after COVID-19, regardless of the distinction between self-employed and worker households, and on the contrary, ‘jeonse’ all had a negative effect. The age of the head of the household had the opposite negative effect in self-employed and worker households, respectively. All but self-employed households showed a positive effect on 132.2㎡ in 2019. Apartments showed a positive effect in 2022 except for self-employed households. Monthly rent was negatively affected only in 2019 for both self-employed and worker households. Mortgage loans were positive in 2019 for self-employed households and negative in 2022 for worker households. Housing expenditure showed a positive effect only on self-employed households in 2019. This study is si",0.0,
e97464d7b94e3a22ca82cfa41c41b38e7334f091,10.54097/7qwr3t88,The Spatial Pattern of Entertainment Service Places in Hong Kong,2025.0,Academic Journal of Science and Technology,Dan-Ling Chen,"Leisure and entertainment are one of the basic functions of a city. The leisure and entertainment services of urban residents have become an important symbol of the city and the driving force of social and economic development, and the quality of leisure life has become an important indicator for urban residents to measure their living environment and happiness. In order to explore the relationship of spatial patterns of entertainment service places in Hong Kong between residents' income and regional housing prices, this project studied the layout characteristics of entertainment service places in Hong Kong using R programming and investigated its relationship with residents' income and regional housing prices in the aspects of descriptive statistics, point pattern and area pattern analysis to provide references for entertainment service places planning in the process of urban development. ",0.0,https://doi.org/10.54097/7qwr3t88
a87950d9c9751192a7cbd08f6900735515569f22,10.47611/jsr.v13i1.2425,Unaffordable Taiwan: An Economic Analysis of High Housing Prices and Low Wages,2024.0,Journal of student-scientists' research,Yu-An Chen; Ting-Yang Weng,"This paper examines the issue of housing unaffordability in Taiwan, with the high rising housing price and stagnated salaries. The paper first analyzes the current situation of Taiwan’s housing market and salary, showing the issue that presents in the system. Moreover, by comparing to countries of similar economic condition, this paper further identifies this prolonged issue that is present in Taiwan’s housing market. Through the usage of housing index, median wage and housing price to income ratio from the Taiwanese government database, this paper further creates machine learning models to analyze the situation of the housing market and how severe the problem is. Finally, the paper uses a regression model to predict the housing price to income ratio in the future, showing the emergence of the issue, and how it requires government interventions to the housing market to resolve the issue. ",0.0,https://www.jsr.org/index.php/path/article/download/2425/1457
e5c1344d955c77d6128aa887bd866305be98cd8e,10.36378/jtos.v8i2.4829,House Price Prediction in Surabaya Using Backpropagation Neural Network,2025.0,JURNAL TEKNOLOGI DAN OPEN SOURCE,Dimas Fajri Pamungkas; Abdul Rezha Efrat Najaf; Reisa Permatasari,"This research develops a house price prediction system in Surabaya using the Backpropagation Neural Network (BPNN) method. The dataset was obtained through web scraping of property listings, resulting in 3,435 records with 52 attributes. To improve stability, the target variable (house price) was transformed using natural logarithms. Several neural network architectures were tested, and the best configuration [32, 64, 32] achieved Mean Absolute Error (MAE) of 0.3125, Root Mean Squared Error (RMSE) of 0.4201, R² of 0.7138, and Mean Absolute Percentage Error (MAPE) of 1.46%. A multi-run evaluation of 20 iterations confirmed consistency of results. The model was implemented as a web-based application using Flask, allowing users to predict house prices in real-time. This research shows that BPNN is reliable for property price forecasting and can support decision-making in the housing market.",0.0,https://ejournal.uniks.ac.id/index.php/JTOS/article/download/4829/3467
486034dcf3047d4284291ae47f309fff740ead97,10.1109/isas66241.2025.11101915,Interpretable House Price Prediction Using Ensemble Learning and Explainable AI Techniques,2025.0,International Service Availability Symposium,Burçak Asal,"This study presents a ensemble learning based machine learning approach for predicting house prices on a structured tabular dataset. Within the scope of the study, four regression models are investigated, which are Bayesian Ridge Regression, Elastic Net Regression, Stochastic Gradient Descent (SGD) Regression and a Voting Regression model combining the previous three models. Experimental results demonstrate that Bayesian Ridge and SGD Regression achieved the highest predictive accuracy, while the Voting Regression model provides robust yet slightly lower performance. Additionally two Explainable Artificial Intelligence (XAI) techniques, SHAP and LIME, are employed to interpret the Voting Regression model’s predictions, revealing that Square_Footage is the most influential feature, followed by Lot_Size and Year_Built features and with minimal contributions from Neighborhood_Quality feature. The alignment between global and local interpretability methods further validates the model’s decision-making transparency and robustness. Consequently, this study indicates the effectiveness of combining traditional regression models with ensemble strategies and explainability techniques for bui",0.0,
76fb8d9ff6a4ec7822c172b3ef7ad53a19912562,10.22423/kreus.2024.16.2.25,Study on the Impact of Social Infrastructure on Apartment Prices: Focusing on the Case of Seoripul Tunnel in Seoul,2024.0,Konkuk Research Institute of Real Estate and Urban Studies,Won-Joon Choi; Seong-won Lee; Yeon-Jae Lee,"This study aimed to understand the impact of social infrastructure investment on apartment prices. Using a difference-in-differences(DID) regression analysis, we empirically analyzed the impact of the new establishment of infrastructure on apartment prices in Bangbae-dong, Seoul by the commencement and completion of the Seoripul Tunnel, examining the effects step-by-step and by distance from the street using buffer analysis. Our findings revealed that the influence on apartment prices varied depending on the commencement and completion stages. For the commencement phase, a significant increase in actual transaction prices was observed within 500m when comparing 6 to 9 months before and after the construction started. On the other hand, during the completion phase, no significant influence was observed at the exact time of completion. However, when considering three months before completion, statistically significant positive changes were observed in both the subsequent 9 months and within distances of both 500m and 1km. This research provides an empirical evidence of the actual fluctuations in apartment prices due to large-scale social infrastructure investments in the area. The ef",0.0,
8f764cba81aa32ee066fa160b025eca873816e65,10.35175/krs.2025.26.1.5,The Effect of the Status of Housing Property Rights on Residential Satisfaction and Preferences among Newlyweds,2025.0,Korean Association of Regional Sociology,Hyungjun Suh,"This study examines whether residential satisfaction and residential preferences vary by housing property rights, an individual-level variable, beyond the household-level variable of homeownership. This study uses the data that came from the newlywed module of the 2014-16 Korea Housing Survey and linear and logistic regression as methods. The results showed that, even after controlling for relevant variables, owner-occupied households had higher residential satisfaction than renter-occupied households, and individual property owners had higher residential satisfaction than respondents without property rights (family property owners). In terms of residential preferences, owner-occupied households were more likely than renter-occupied households to consider housing tenure and house price fluctuations important, and individual property owners were more likely than family property owners to consider housing tenure and house price fluctuations as important. It is intriguing to note that individual property owners and family property owners have similar housing quality, living space, and living environment at the household level, but the outcome variables differ due to the difference in ",0.0,
375ab5fc9cae6574189fbc1cb3a92cb80f7ef9b5,10.1016/j.regsciurbeco.2026.104265,Housing market pressures and post-earthquake displacement: Evidence from the 2023 Türkiye earthquakes,2026.0,Regional Science and Urban Economics,Muhammed Hamza Kayrici; Y. Akgündüz,"This paper investigates the impact of the February 2023 T¨urkiye earthquakes on housing markets in unaffected regions using online real estate listings and a time-based Regression Discontinuity Design. We document a sharp post-disaster demand shock driven by large-scale population displacement, with effects concentrated in the residential rental market. Consistent with a residential displacement shock, no significant effects are detected in commercial property markets. Price increases were highly segmented: pressures were strongest for multi-room units, reflecting the larger family structures of displaced households, and for newly constructed units, indicating a post-disaster flight-to-safety. Cross-sectional province-level and difference-in-differences estimates show that pre-existing migration networks and geographic distance are the primary determinants of rental price pressures.",0.0,https://doi.org/10.1016/j.regsciurbeco.2026.104265
ce44c3a994d9510cbd59681326e259a7fa8425a7,10.1088/1742-6596/1941/1/012019,Extraction and analysis of spatial divergence features of residence space,2021.0,,Li-Shuang Sun; Xinyu Wu; Zhi-Wei Xie; Yifan Wu,"Reasonable planning of urban residential spaces is important for urban development. This article used the population spatial distribution data and house price data to extract and analyze the characteristics of urban residential space differentiation in Shenyang and Wuhan. The results showed that: (1) There was a phenomenon of residential space differentiation in Shenyang and Wuhan. Compared with Shenyang, the phenomenon of residential space differentiation in Wuhan was more serious;(2) The proportion of people living in low, medium and high housing price areas in Shenyang and Wuhan showed the primary form of olive structure. Research conclusions: Combined with the data of population spatial distribution and house price, the study of urban social space was conducive to building a fair, just and harmonious urban social space, which was valuable not only in theory but also in practice.",0.0,https://iopscience.iop.org/article/10.1088/1742-6596/1941/1/012019/pdf
2d2585fda5f7017c4b629df07e90b2a29785d6ef,10.37407/kres.2024.42.2.5,A Study on the Effect of Changes in Macroeconomics and Population Characteristics on the Housing Sales Market in the Metropolitan Area and Non-metropolitan Area,2024.0,Korea Real Estate Society,Jeong-ae Park; H. Hwang; Jae Song,"This study attempted to compare and derive the impact on the housing sales market in the metropolitan area and local cities and to present implications in terms of the real estate brokerage market. The Vector Error Correction Model was used as the analysis method in consideration of the time series characteristics and cointegration relationship of the used macroeconomic and demographic variables. The analysis results and implications are summarized as follows. 
In the case of the metropolitan area model, interest rates, consumer price indices, population growth rates, and fertility rates were the main factors influencing the housing sales market. The five metropolitan city models are the main factors influencing interest rates, economic growth rates, and consumer price indices, while the explanatory power of the fertility rate is very low. Considering these results, housing can be classified as an investment product in the metropolitan area, and local cities can be classified as a housing sales market with strong characteristics as a consumer product. Long-term housing sales are not expected to increase significantly due to the recent decline in investment and real demand due to th",0.0,
c9c3a3c0150d0d7566987965f30c1a97ab78d511,10.54097/fbem.v5i1.1574,W Real Estate Company Project Tracking Audit Research,2022.0,"Frontiers in Business, Economics and Management",Meng-Nan Hao,"Since the early 21st century, the real estate industry has developed rapidly and has become an important pillar of China's economy.But so far, whether from the industry report or the market situation, it is not difficult to find that the real estate industry has appeared a lot of problems, behind the soaring housing prices is the increase in costs.To address the surge in housing prices, the first priority is to reduce costs.This paper selects F construction project as the research object, with the implementation of the whole process of tracking audit as the breakthrough point, the construction project is divided into five important stages, according to the different characteristics of each stage, put forward more targeted audit implementation and control content, in order to the development of tracking audit for construction project industry provides certain experience reference.",0.0,https://doi.org/10.54097/fbem.v5i1.1574
349058fc6307665248a1e81921a0426eb197d24e,10.15396/eres2019_91,Italian auction market: investigating forced sale value,2019.0,26th Annual European Real Estate Society Conference,M. Mariani; P. Amoruso,"The present work focuses on the considerable amount of real estate non-performing loans in Italy, not favored by the state of judicial proceedings. In this view various governmental initiatives intended to facilitate a more efficient liquidation of underlying real estate assets. In this regard, it could be useful better understand main causes of discount between market value and forced sale price with the primary aim of a more comprehensive determination of the value of mortgages ‘underlying guarantees and not least in order to improve further valorization processes of assets intended to get a higher selling price; starting from results of existing literature, an analysis of main determinants of the gap between the estimated listing price and forced sale value has been conducted, sampling 225 cases of forced residential property sales between 2014 and 2018 in the South of Italy.",0.0,https://eres.architexturez.net/system/files/P_20190718115348_3761.pdf
8595fe109eada7ded46f7be8f43ecff9898ed9ec,10.24957/hsr.2022.30.4.113,A Study on the Effect of Resale Characteristics of Apartment Presale Rights on Apartment Sales Price,2022.0,Korean Association for Housing Policy Studies,J. Park; Han Sung Joo,"The government implemented a real estate policy regulating Finsens in units of each region by designating overheated speculation districts and areas to be adjusted according to the rise in housing prices. These regulated areas include consumer restraint policies. The purpose of this study was to examine the real estate policies related to the characteristics of pre-sale of apartments over a period of 6 years from January 2016 to December 2021, and to examine how these policies affected apartment sale prices by region. For the research method, the Hausmann fixed effect was used to examine the factors that have influence as well the changes according to the characteristics of real estate, macroeconomic characteristics, policy characteristics, and resale characteristics of real estate based on on nationwide and metropolitan area models, specifically the Daegu/Gyeongbuk, Booulgyeong, Chungcheong/Daejeon, and Gwangju/Jeonla models. For the statistical analysis, the model was assessed using the STATA17 version. Results showed it was possible to examine the policies affecting housing price stabilization among various government real estate policies, and to further examine the policies tha",0.0,
de210f053c94accaffc57e4c3c619e5ad21c441d,10.24908/cpp-apc.v2025i1.19006,Housing Prices in British Columbia: Quantifying the Zoning Effect,2025.0,Canadian Planning and Policy / Aménagement et politique au Canada,N. Zemp,"British Columbia (B.C.)’s housing prices have increased dramatically in recent times, and one potential explanation is municipal zoning bylaws limiting housing supply. However, the effect of zoning on housing prices in aggregate has not yet been studied in B.C. In this study, I use a regression analysis, adapted from an Australian study, to estimate the “zoning effect”: the extent to which zoning controls increase the sale prices of dwellings. I calculate this effect for detached homes in 30 of B.C.’s largest cities and towns, and for apartments in the Metro Vancouver region. I look at how home prices changed between 2016 and 2022, and the extent to which the zoning effect influenced this trend. Finally, I evaluate the potential of government initiatives aimed at decreasing the cost of housing through the lens of the zoning effect, and suggest possible future courses of action.",0.0,https://doi.org/10.24908/cpp-apc.v2025i1.19006
307fcece1735a69f376a239262adb7ce91789e69,10.1109/iconat61936.2024.10774967,Property Price Prediction,2024.0,2024 3rd International Conference for Advancement in Technology (ICONAT),Aleena Anna Robin; G. Prasad; Jyothsna Jiji; Sanjay Raajesh; K. V. Sheena,"This data analytics project is designed for the real estate industry, with the primary aim of predicting property prices, including lands, buildings, and houses linear regression model and also by carefully analyzing and interpreting current market trends. Although numerous existing systems share the common objective of property price prediction, our proposed system brings distinct advantages. One of them is its ability to explore rental options for rooms and buildings. What truly sets our system apart is its comprehensive approach to property valuation. It achieves this by incorporating a user-specific data analysis component, which considers critical factors like user loan availability. Essentially, it bridges the gap between the realm of property investment and the realm of financial planning, equipping users with essential insights to make sound financial decisions in the context of real estate. This project has been meticulously designed with the unique needs of the real estate industry in mind, offering a transformative tool that assists individuals in making smarter choices concerning property investments, rentals, and loans. By providing a comprehensive, user-focused approa",0.0,
784e397fc77e1719dd6a26964a4bd0b9c79884e2,10.48175/ijarsct-709,House Price Forecasting Using Ml and RPA,2021.0,,Pradnya Patil; T. Patil,"In today’s world, every individual wish for a house that suits their lifestyle and provides amenities according to their needs and budget. On today’s world prices of houses are keep on changing very frequently which proves that house prices are often overstated. There are various factors that must be taken into deliberation for predicting house prices such as number of rooms, carpet area, and other basic local amenities. By using XGBoost, Light GBM and CatBoost Boosting algorithm to predict house prices based on real-time data which is extracted using Robotic Process Automation. Automate the tasks of data extraction can be done by Robotic Process Automation. The data generated by RPA is inconsistent, hence data is get cleaned and made consistent before feeding to appropriate Machine Learning model. After data cleaning process model is created and accuracy is get achieved [1].",0.0,https://doi.org/10.48175/ijarsct-709
637b35b7958860a21e85feb713bca477838bb5ea,10.22423/kreus.2024.17.1.35,Analysis of Policy Effects of Designation of Housing Speculation Area: Focusing on the Designations of Housing Speculation Areas in Years 2017 and 2018,2024.0,Konkuk Research Institute of Real Estate and Urban Studies,,"In a situation where regulations have become redundant and complex due to the revision of the policy of designating regulatory districts, this study examined the policy characteristics of the designation of housing speculation areas and empirically analyzed the individual policy effects of housing speculation areas. In order to estimate the time-varying policy effects and heterogeneous policy effects according to price levels, the difference-in-differences method that considers time-varying policy effects was used for submarkets classified by price levels of KRW 900,000,000. As a result of the analysis of Seoul, the designation of housing speculation areas in 2017 had the effect of increasing apartment prices, but the designation in 2018 played a role in stabilizing apartment prices, showing mixed policy effects. This suggests that it is difficult to predict the policy effect of designation of housing speculation areas. In addition, it was confirmed that the designation of speculation areas can have effects different from the policy intention depending on the subsequent real estate policy implemented after the designation, and can play a role in stabilizing housing prices depending",0.0,
3bc52646e9e1a3d85ecf3df12738ffd5f2c10457,10.54254/2754-1169/48/20230425,The Impact of Benchmark Interest Rate towards Loan for the Housing Price A Case in Beijing and Shanghai from 2011 to 2015,2023.0,"Advances in Economics, Management and Political Sciences",Yi Wang,"The housing market in China has been booming for two recent decades, and housing issues gradually become one of the most important concerns of the residents in China as the housing price was rising dramatically. This paper would analyze the influences between the housing price and the benchmark interest rate in two major first-tier cities of China, Beijing, and Shanghai from 2011 to 2015 before the interest rate reform in China was completed, by conducting data analysis in the regression model. It is found that the benchmark interest rate for loans has an important role in influencing housing prices. Finally, this paper would help make a clear and better understanding of the mechanism of the Chinese benchmark interest rate for loans, and how Chinese governments used it to sort out residential accommodation issues by comparing it to the recent Benchmark interest rate (LPR).",0.0,https://aemps.ewapublishing.org/media/015b22be5e924391bc2c89a118bce8d5.marked.pdf
6ff2501a2fa0fc7fbfd48f9a5f3e86b9caf5ed57,10.19044/esj.2018.v14n13p280,The Structural Analysis of the Determinants of Shanghai Real Estate Price,2018.0,European Scientific Journal,Zhi Chen,"What are the factors that play the most significant role in affecting Shanghai real estate price? This essay has established an econometric model and uses the perspective of structural analysis to substantiate the real factors that affect the housing price in Shanghai during the 1994— 2015. The essay first collects data from multiple authoritative sources according to potential factors. Then, the essay selects several optimal factors and conducts verification on them. The result is being analyzed. Finally, a conclusion has been reached: factors on the supply side of housing individually have small impact on the price while factors on demand side and policy demonstrate strong impact statistically. This conclusion further suggests that policy implemented by the government with respect to housing price problem in Shanghai could restrain the unreasonable growth to some extent.",0.0,https://doi.org/10.19044/esj.2018.v14n13p280
31edffcb761f2438a7209dcebdd15d8bfca12426,10.63503/c.acset.2025.20,HOUSE PRICE PREDICTION USING LINEAR REGRESSION,2025.0,Engineering & Technology,A. Dataset; Adarsh Sahani; Kundan Paswan,"Prediction of prices of houses is very important for buyers, sellers, and planners in the real estate market. In this paper, it is explained how Linear Regression can be used for estimating and predicting the prices of houses using the Ames Housing Dataset. Ames Housing Dataset includes data of 1460 houses and their 81 different features or attributes about the houses. We first cleaned missing data of the dataset using simple methods like replacing them with median or most common values. Then we trained the Linear Regression Model and tested it. Our model resulted in 0.82 score for R², 22417 for MAE, and an RMSE of about 36,879. From this, we understand that even a simple model like Linear Regression can work well in predicting prices of houses. In the end, we also discussed various studies related to our work and also included how we can improve this system in the future.",0.0,https://conferenceseries.adroidjournals.com/index.php/ACSET/article/download/24/18
630f612404b55bee0ff66c60687f3f517d1f820a,10.2139/ssrn.3545603,The Roof is on Fire: Wildfires' Effect on Housing Prices,2019.0,Social Science Research Network,V. Sierra,"Regression analyses have been commonly applied to studying the relationships between wildfires and housing prices in local markets. My study conducts a regression analysis on a panel of local markets using county-level data. It contributes to climate and housing literature by estimating the impact of wildfires on housing prices across the Western United States using a robust least squares regression. Most models estimate wildfire effects on housing prices using direct data from wildfire activities or acres burned due to wildfire as their variables of interest. Wildfire activity data is not easily accessible on the county-level; thus, this model utilizes average annual maximum temperatures to measure changes in climate over time which exacerbate and contribute to more frequent wildfire activities. (Westerling et al., 2007). My study finds that as the average maximum temperature increases within a county, the housing prices will generally decrease in value. The results of these effects are found to be statistically significant. Specifically, one percentage point increase in the growth rate of average maximum temperature reduces the growth rate of housing sales price by an average of ",0.0,
d205e7e5abb66e319fc11159afbb6382fb6b8445,10.53829/ntr201611fa3,Learning from a Large Number of Feature Combinations,2016.0,NTT technical review,M. Blondel,"[1] M. Blondel, A. Fujino, N. Ueda, “Convex factorization machines,” in Proc. European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2015. Convex Factorization Machines (CFM) are a high-accuracy regression model that can handle a large number of feature combinations. CFM is general-purpose and can be applied to a wide range of tasks: e.g., house price prediction, recommender systems and genome analysis. The proposed method can handle a large number of feature combinations by using a low-rank constraint. Moreover, it is guaranteed to obtain a global optimum In future work, to further improve predictive accuracy, we plan to support higher-order feature combinations. Besides recommender systems, applications include predicting combinations of genes that are responsible for diseases, which would help find effective cures. 001",0.0,https://ntt-review.jp/archive/ntttechnical.php?contents=ntr201611fa3.pdf&mode=show_pdf
d696b18a3b19b9050930610083ec3ba0ceb564d6,10.25236/ajbm.2022.040802,Understanding Hong Kong Property Market: An Analysis of Customer Preference and Market Trend,2022.0,Academic Journal of Business & Management,Mengtong Xie; Jing Xu,"UK Abstract: Housing shortage has been a significant issue in Hong Kong since 1997. For years, the government has put great effort in addressing this problem. This report describes a project aiming at identifying the key factors influencing customer preferences within the Hong Kong property market, so as to better understand the market needs and provide insights for land planning. Social media and property agency websites are main data sources. Web Crawler and a taxonomy database were developed to extract and map the information from social media into property market discussion. Visualizations and text mining have been used to perform analysis. We concluded that the housing preference in Hong Kong is concentrated in the New Territories and identified a negative relationship between average housing price and online social discussion frequency for top mentioned locations.",0.0,https://francis-press.com/uploads/papers/LTWDuSsNEC7JB9lYW855VRYNExO8EzT0fLwpNFt0.pdf
e20efcb8fda330116cae84d69ebf0277f555dce8,10.5089/9798229042437.001,Household Behavior under Macroprudential Borrower-Based Measures,2026.0,IMF Working Papers,Jaunius Karmelavičius; J. Otten,"This paper develops a life cycle model to study household choice under macroprudential borrower-based measures (BBMs). The model is extended to multiple heterogeneous households, allowing to assess both aggregate and distributional effects of BBMs on mortgage and housing demand. The framework is applied to Lithuanian and Slovak distributional data to quantify the impact of various BBM configurations. We find that the presence of binding BBMs can usefully dampen mortgage and house price growth. However, tight regulation may also redirect demand towards lower-valued housing, while pushing households into the rental market. In particular, loan-to-value (LTV) limits are most constraining for households with little or no initial wealth. This highlights the distributional consequences of BBMs and the importance of designing regulation to account for borrower characteristics.",0.0,https://doi.org/10.5089/9798229042437.001
c6a67a962700401e849e82135857884581b9cb66,10.55927/ajma.v3i4.11866,"Spatial Regression Analysis of Environmental and Structural Factors Influencing Shophouse Values in Makassar City, Indonesia",2024.0,Asian Journal of Management Analytics,Abdullah Najang; P. Gultom; Handy Octavianus,"This study investigates the factors that influence shophouse values in Makassar City, Indonesia, using a spatial regression model. The research addresses the lack of prior studies that consider spatial dependencies in property value assessments. By analysing data from 101 shophouses across four distinct city strata, factors such as building area, certificate type, and road width were found to significantly impact property values. Additionally, spatial relationships between neighboring properties were observed, indicating a 0.3 positive correlation. The study employed Structural Equation Modeling (SEM) with the R Project for Statistical Computing. The results provide insights into the spatial dynamics of urban property values, which are valuable for urban planners, investors, and policymakers aiming to optimize real estate development in rapidly growing urban centres.",0.0,http://dx.doi.org/10.55927/ajma.v3i4.11866
56d3855be100922ffd29e919f1825f3d73093375,10.54691/bcpbm.v24i.1525,An empirical analysis of second-hand house transaction prices based on machine learning,2022.0,BCP Business & Management,Yingshi Cai,"The Beijing real estate market is one of the most developed and representative real estate markets in China. As of May 25, 2016, Beijing accounted for 88.2% of the market residential transactions, and the Beijing property market has fully entered the era of second-hand houses. Therefore, the price of second-hand houses in Beijing can be judged by studying the factors influencing the price of second-hand houses in Beijing, and the study has theoretical significance. Taking Beijing second-hand houses as the research object, the data source is mainly designed as a crawler to mine the data and obtain the transaction attribute information of chain house network, and the data sample size is 2000 items in total [1]. In this paper, we obtained the important variables affecting the house price through multiple model analysis and predicted the data of 100 unknown house prices.",0.0,http://bcpublication.org/index.php/BM/article/download/1525/1534
af0c96ce33a64ca93154fb4cac37203950c7c38a,10.53383/100393,Cointegration and Economic Dynamics: Unraveling the Interplay between Gold Prices and Residential Property Prices in Five Different Nations,2024.0,International Real Estate Review,Syeda Tayyaba Ijaz,"This abstract delves into the intricate relationship between gold prices and residential property prices in China, Singapore, India, Iran, and Russia. Using a comprehensive dataset, our analysis elucidates the nuanced causal dynamics among these two economic variables. The findings reveal diverse interactions shaped by the interplay of local and global economic forces. In China, a significant decline in property values and a slight drop in gold prices highlight distinct market characteristics. Conversely, Singapore exhibits positive divergence, with an increase in property prices and substantial growth in GPs. India presents a contrasting pattern with a modest uptick in property values but an alarming decline in gold prices, thus suggesting a unique economic dynamic. Robust causal relationships are identified in the cases of Iran and Russia which underscore the significant influence of specific factors on the interplay between property value and gold prices. This foundational investigation emphasizes the necessity of tailored, context specific analyses and underscores the fluid nature of the relationship between the real estate and precious metal markets. The study provides valuabl",0.0,
ef7b11c7fc894f8dd51cc083d4e3aec3d448ba83,10.55164/ajstr.v27i5.251974,Enhancing linear regression through neighbor-based similarity analysis,2024.0,ASEAN Journal of Scientific and Technological Reports,Chinnawat Chetcharungkit,"When working with real-world datasets characterized by complex and non-linear relationships, the limitations of non-complex machine learning models like linear regression become evident. In response to addressing this technical problem, we propose a novel algorithm to enhance linear regression without the necessity of complex mathematical or statistical expressions. Instead, the algorithm segments data into multiple subgroups or neighbors, each with its own best-fitting line. The primary objective of this approach is to enable more accurate predictions for unseen data points by utilizing the most similar neighbors and their corresponding linear regression lines, with the support of k-nearest neighbors. Empirical evidence from three publicly available housing price datasets demonstrates the algorithm’s effectiveness in improving traditional linear regression models.",0.0,https://ph02.tci-thaijo.org/index.php/tsujournal/article/download/251974/171141
776917949fc1ede29c179cafbc16a4cd1c397c83,10.53383/100367,"Current Account Imbalances, House Prices, and Institutions",2023.0,International Real Estate Review,S. Akcay,"Current account imbalances and housing price boom-bust cycles have become the defining characteristics of the pre-global financial crisis period. In the same period, it is observed that even though the developments of the economies show similar trends in many countries (e.g. an increase in credit supply, a decrease in interest rates), they have distinct characteristics (e.g. the volatility of house prices, and level of current account imbalances). Additionally, their final impacts on the economy vary to a significant degree from country to country. The institutional features of the markets (e.g. accessibility of credit information, protection of investors) have the potential to contribute to this differentiation. However, there are no studies on the effect of institutional features on the relationship between house prices and current account imbalances. The aim of this study is to examine the relationship between house prices and current account imbalances as well as the role of institutions in this relationship for 14 EU countries. To do so, a simultaneous equations model is used. The results of the empirical analysis show that in the 2007-2008 global financial crisis, there is a ",0.0,
ae40f8865a232e508594d1da2838294d9a13cdd0,10.62051/cman5j03,Feature Selection and Regression for House Value Prediction,2024.0,Transactions on Computer Science and Intelligent Systems Research,Zhaowen Gu,"This report investigates the application of feature selection and regression techniques, including LASSO, Ridge Regression, and Elastic Net, in predicting house values. By analyzing these methods, we aim to identify the most influential factors driving house prices and assess their relative importance. Our study involves a comprehensive evaluation of various linear regression models to determine their effectiveness and consistency in predicting house prices. The results reveal that while all examined techniques demonstrate robust performance, certain methods, particularly Elastic Net, offer superior predictive accuracy and better handle multicollinearity among features. This report provides valuable insights for real estate professionals and data scientists seeking to refine their predictive models and make informed decisions based on comprehensive data analysis.",0.0,https://wepub.org/index.php/TCSISR/article/download/4069/4444
f2bc891ab586492021d40355a0aa440e9bbc170b,10.1109/icadeis71120.2026.11644565,Comparing Random Forest and LightGBM for Residential Property Price Prediction Using Multi-Platform Online Listings in Indonesia,2026.0,"International Conference Advancement Data Science, E-learning and Information Systems",Tristanto Wijaya; Gian Fiorentino Kapoh; Bagas Adnan Putra; E. Banjarnahor,"Predicting residential property prices is challenging due to the heterogeneous and non-linear nature of housing markets. This study conducts a comparative analysis of machine learning models for house price prediction in Indonesia using multi-platform online real estate data. Property listings from Lamudi and OLX Indonesia were used to construct a dataset consisting of 3,347 records. Three regression models were evaluated: Random Forest (RF), Light Gradient Boosting Machine (LightGBM), and Linear Regression as a baseline model. The models were assessed using multiple train-test split scenarios and cross-validation. Model performance was evaluated using Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), and the coefficient of determination $\left(\mathrm{R}^{\mathrm{2}}\right)$. The results show that the ensemble models achieve high predictive accuracy across all configurations, with Random Forest consistently outperforming LightGBM. In contrast, Linear Regression demonstrates significantly lower performance, indicating its limitation in capturing complex and non-linear relationships. The best performance was obtained with a 90: 10 trai",0.0,
bfb01afbc738d01dd29efa4bf39f946c934a211b,10.5539/ijef.v10n12p96,Influential Factors of Residential Commodity Price Changes in Sanya,2018.0,International Journal of Economics and Finance,Ying-Yu Du; Yong-Qi Huang; Can-xu Yao; Yuan-Biao Zhang,"Residential commodity price is not only an important index of government macro-control, but also an important livelihood topic in society. The purpose of this paper is to take Sanya as an example to make an empirical analysis on the relationship between the factors affecting commodity housing prices, and their effects on housing prices. By using pearson correlation analysis, factor analysis and principal component regression method, it is found that the main factors influencing the housing price in Sanya are the housing sales area, the gross domestic product, the per capita disposable income, and the land price level of residential land. Among them, housing sales area and Sanya city house price changes in the opposite direction, the regional gross domestic product, per capita disposable income, residential land price level plays a positive role in housing prices.",0.0,https://doi.org/10.5539/ijef.v10n12p96
b730558f676dc4628e57b03ab0649ee3f7c7991d,10.46632/daai/4/2/11,Enhancing House Price Predictability: A Comprehensive Analysis of Machine Learning Techniques for Real Estate and Policy Decision-Making,2024.0,Data Analytics and Artificial Intelligence,M. K; Dharish Jaya priyan J; D. N; A. A,"Accurate house price prediction is crucial for stakeholders in real estate markets and economic policy formulation. This research investigates the application of sophisticated machine learning (ML) algorithms to improve the precision of house price forecasting. By analyzing existing literature, we explore the methodologies employed in house price prediction using ML approaches. We emphasize the significance of precise predictions for various stakeholders, including homebuyers, sellers, investors, and policymakers. Additionally, this abstract critically evaluates the strengths and limitations of different ML 
techniques in predicting housing prices Our goal is to enhance predictability of models through rigorous analysis, thus facilitating informed decision-making when it comes to housing transactions, investments, and policy implementations through our research.",0.0,http://dx.doi.org/10.46632/daai/4/2/11
e59a5eb955526110f421fe4dd21582858c71d6ac,10.22214/ijraset.2019.5698,Crossbreed Regression Technique for House Prices Prediction,2019.0,International Journal for Research in Applied Science and Engineering Technology,Vadaka Keerthi,"-Usually, House rate index represents the summarized charge adjustments of residential housing. While for a single family house charge prediction, it needs more accurate technique based on location, residence type, size, construct year, neighbourhood amenities, and some different elements which could affect house demand and supply. With constrained dataset and information features, a realistic and composite data pre-processing, innovative feature engineering technique is examined in this paper. The paper additionally proposes a hybrid Lasso and Gradient boosting regression model to predict person house price. The proposed strategy has lately been deployed as the key kernel for Kaggle Challenge “House Prices: Advanced Regression Techniques”. The performance is promising as our trendy score was once ranked top 1% out of all opposition groups and individuals.",0.0,https://doi.org/10.22214/ijraset.2019.5698
8b762ad768e114a7814d7d0889da82be16f8d23b,10.15396/eres2019_315,The role of property finance in the performance of residential property markets: Evidence from UK House prices: 1967 to 2017,2019.0,26th Annual European Real Estate Society Conference,B. Aha,"Housing issues have become increasingly important throughout the developed world and have attracted much interest amongst economists, policymakers and the general public, following the catastrophic impacts of the 2007/08 global financial crisis. Globally, housing finance has undergone substantial changes, in terms of structure, composition and regulation, and witnessed considerable expansion within the last three decades. While studies abound seeming to explain national and regional house price movements, the dynamics of the housing market are still not widely understood. Though the importance of finance in the housing industry is generally well appreciated, very little attention has been paid to the drivers of housing finance and their impact on house prices. The determinants of mortgage credit growth and how these interact with macroeconomic, fiscal and regulatory policy variables to shape house prices are still not well understood. This study seeks to make an invaluable contribution to this understanding. by analysing house price dynamics in the UK from 1967 to 2017 and examining the role of mortgage credit in the performance of the housing market. The key drivers underlying hou",0.0,
fb8ad1d9a57c491b22796b65a71035f949819c84,10.61173/wej5vk49,"Factors Influencing Real Estate Prices: An Empirical Analysis Based on STATA Using Panel Data from China, Japan, and the U.S.",2025.0,Finance & Economics,Lixin Feng,"The real estate acts as an essential and indispensable part of the national economy, strongly associated with the economic development. Since the real estate market and the economic development interact and influence each other, the study on the dynamics of real estate prices is very significant for monitor of the economy and formulation of policy making. The aim of this paper is to investigate the key determinants influencing real estate prices in three major economies: China, Japan, and the United States. By identifying and analyzing periods of significant price fluctuations, the study employs Stata software to examine the relationship between selected explanatory variables and housing price trends. The study shows that residential land price, population density and real gross domestic product per capita has the greatest influence on real estate price.",0.0,https://lseee.net/index.php/fe/article/download/140/FE005952.pdf
d972d9c097f9810e07978b12423366ec8abb66a5,10.24957/hsr.2025.33.4.5,Rising Household Debt and Housing Market Dynamics: Lease Deposit Indebtedness and Tenant-based Gap Investment,2025.0,Korean Association for Housing Policy Studies,Hoobin Lee,"This paper investigates the housing market channel resulting from the increase in household debt. Specifically, it examines who borrowed so heavily during the ultra-low interest rate period of 2020–2021 and what they did in the housing market. Among the lower class, there was an extensive expansion of credit, yet it did not translate into the democratization of homeownership. Rather, the expansion of Jeonse loans led to the indebtedness of housing lease deposits, thereby making owner-occupancy more difficult for the lower class. In contrast, among the upper class, the rise in household debt facilitated both housing investment based owner-occupation and tenant-based housing investment. Notably, the characteristics of Gap investment were particularly prominent in tenant-based housing investment, which excludes owner-occupancy. In this way, South Korea’s unique Jeonse system has produced a distinctive housing market channel through the mechanisms of Jeonse loans and Gap investment. The growth of household debt can impede the expansion of owner-occupancy both from below and above. In this context, rising housing prices can exacerbate wealth inequality: lower-class households bear heavi",0.0,
bbb37878bc38d8a3bd1f803436c174bac4f103e7,10.24957/hsr.2022.30.3.179,The Thirty Years of the Housing Studies Review : A Text-Mining Approach,2022.0,Korean Association for Housing Policy Studies,Soon-Mahn Park; Ho-Jin Lee; Eun Sang Jung; Seung-dong You; Yeong Woo Nam; K. Ji,"We analyze the research trend of the Housing Research Review over the period of 1993 to 2021. In particular, adopting text-mining methodologies: word frequency analysis, wordcloud technique, N-gram, and Topic Modeling, we analyze titles and keywords of all the papers on the journal. Based on those analyses, we find that words that the papers on the journal most frequently used over the past 30 years are ‘housing’ and ‘research’, which are followed by ‘price’, ‘househhold’ and ‘income’. Our word proximity analsyis shows the most-related keywords; housing prices, housing markets, fluctuations, and trading volume in terms of market and price structure; housing occupancy and household changes in terms of housing demand. 
Our analysis of Latent Dirichlet Allocation reveals six categories; ‘the ownership and apartments’, ‘price and space’, ‘real estate policy and regulation’, ‘household’s decision in housing market’, ‘regional characteristics evaluation’, and ‘residency and rental housing’. The most interested topics are related to ‘price’, and we confirm that the topics of interest has been changed over the decades; from ‘development and management’ and ‘rental housing and real estate’ ",0.0,
3bc3233face21db65983ba4fc10c2a94a24d092e,10.35136/krer.35.1.3,Long Memory and Regime Switching Characteristics of Housing Price Indices,2025.0,Korea Real Estate Institute,S. Kim,"This study empirically analyzes the long-memory and regime-switching characteristics of apartment price indices in eight cities of South Korea (Seoul, Busan, Daegu, Gwangju, Daejeon, Ulsan, Gyeonggi, and Incheon). An R/S test and MS-ARFIMA model were applied for the period from June 2003 to September 2024. 
Results of the R/S test revealed long-memory characteristics in apartment price indices across all the cities. Thus, we conducted additional analysis using the MS-ARFIMA model to capture long-memory and regime-switching characteristics simultaneously. The MS-ARFIMA model analysis confirmed both characteristics in all regions, with particularly strong long-memory characteristics observed in the contraction phase. Metropolitan areas demonstrate complex characteristics, with high volatility and strong long memory. Additionally, all cities show asymmetric characteristics where the contraction phase showed a higher persistence probability than the expansion phase. In contrast, nonmetropolitan areas demonstrated strong persistence during the contraction phases but relatively weak state persistence during the expansion phases. Therefore, preemptive policy responses when entering a hous",0.0,
5cc739b35495c1c469836e958ed0ce62a87a3700,10.1920/wp.ifs.2026.2526,Small area consumption estimates combining survey and financial footprints data,2026.0,Journal of applied econometrics,Peter Levell; Lars Nesheim; Gautam Vyas,"
 We estimate average equivalised consumption measures across 370 local authority districts in Great Britain, using small‐area estimation methods that combine information from a household budget survey, a much larger survey of local demographics and employment, and area‐level information on bank account outflows and energy consumption. We show that including bank account data substantially improves our estimates, showing that these and other financial footprints data can play an important role in measuring local consumption and hence living standards. We also compare consumption measures that correspond to welfare under different assumptions about mobility and the capitalisation of local amenities into house prices, as well as traditional local income measures, and show that the rankings of local authorities are sensitive to the choice of measure.",0.0,https://ifs.org.uk/sites/default/files/2026-04/WP202625-Small-area-comsumption-estimates-combining-survey-and-financial-footprints-data.pdf
e0b0108ab6436c6cff76724c973bc9e72551f3a7,10.1080/00036846.2025.2532887,Examining the role of artwork orientation on Picasso painting auction prices,2026.0,,Stephen Norman; Howard L. Smith,"ABSTRACT This study employs hedonic pricing models to investigate the effects of compositional factors on auction prices by utilizing a comprehensive dataset of over 1,300 Pablo Picasso paintings that integrates auction data and art historical references. The novel contribution of this study is the analysis of painting orientation (horizontal, vertical or square) on auction price while controlling for the subject matter of each artwork, a methodological approach previously unexplored in the literature. Results indicate that painting orientation significantly influences auction prices independently of subject matter, surface area, time period, auction location and painting surface. These findings highlight the importance of including orientation in hedonic pricing models and offer practical insights for collectors, art investors and auction houses.",0.0,https://doi.org/10.1080/00036846.2025.2532887
ce3d2fb9f2afc13cb54d20ea9df342dfde0fd768,10.1080/13504851.2012.745924,Multilateral index number theory and generalized repeat sales house price indexes,2013.0,,Daniel Melser,"One of the most common approaches to constructing home price indexes is the repeat sales method. In this article, it is shown that this approach is part of a family of widely used multilateral index number methods known as weighted GEKS. Here, the price index is constructed in two stages. First, elementary indexes are constructed between each period. Second, these bilateral indexes are aggregated into a transitive set of multilateral indexes using weighted least squares regression. We show that the repeat sales index has precisely this form and identify the specific elementary index formula and weights used. This observation provides a basis upon which to consider generalized repeat sales indexes which use different elementary indexes and weights. We apply some of these methods to repeat sales data and show that these choices matter empirically.",0.0,https://figshare.com/articles/journal_contribution/Multilateral_index_number_theory_and_generalized_repeat_sales_house_price_indexes/27486624
91eece1ea1e5f617c5d641f6bdb29ca32073d203,10.1145/3718491.3718612,Urban Street View Spatial Evaluation and Distribution of Residential Properties at Different Price Points,2024.0,Proceedings of the 4th Asia-Pacific Artificial Intelligence and Big Data Forum,Chen Geng,"In residents' pursuit of quality living environments, the quality of the residential surroundings is becoming an important consideration when purchasing a house. Previous studies have paid little attention to the impact of urban street views on residential prices. This study utilizes street view data and the SAM model based on deep learning technology to extract the visual features of street spaces around residential areas, qualitatively analyzing the association between urban street view visual features and the distribution of residential properties at different price points. The results of this study indicate that using the SAM model for extracting visual features of urban street views is feasible. Urban street view evaluation has an impact on urban real estate prices, and computer technology assists in quantifying and visualizing this impact.",0.0,https://dl.acm.org/doi/pdf/10.1145/3718491.3718612
80eca804dcfd2a6b965c6e79de34885df4a0f86a,10.62441/nano-ntp.v20i7.5028,Empowering Homebuyers with Advanced House Price Prediction Through Machine Learning,2024.0,Nanotechnology Perceptions,,"This project aims to develop a house price prediction application using Flutter, Firebase, and a machine learning (ML) algorithm, specifically linear regression. The application utilizes Flutter for the user interface, Firebase for data storage and retrieval, and linear regression for predicting house prices based on various features such as the number of bedrooms, square footage, and location. The linear regression model is trained using historical house price data stored in Firebase, which is pre-processed to handle missing values and scaled appropriately. Once trained with CSV files, the model is deployed within the Flutter app using Firebase ML Kit, enabling real-time predictions for users. This integrated solution provides a seamless user experience while harnessing the power of machine learning to deliver accurate house price predictions.",0.0,https://doi.org/10.62441/nano-ntp.v20i7.5028
dc4f87dd92e8f3e4becc9ac57d23bda903c5f9a4,10.1061/jupddm.upeng-6315,Analyzing the Effects of Infrastructure Expansion and Urbanization on Housing Prices: A Spatiotemporal Approach across Chinese Cities,2026.0,Journal of urban planning and development,Tao Zhang; Ridong Hu; Jing Tang,"
 This study examines the impacts of transportation infrastructure expansion and urbanization on housing prices in 285 cities across China. Utilizing a dynamic spatial lag model and a spatiotemporal geographically weighted regression model, it analyzes the spatiotemporal heterogeneity of housing prices. Findings indicate that the actual average housing prices of cities are influenced by competitive states with neighboring cities’ prices; a 10% increase in highway length in a city leads to short-term and long-term decreases in actual average housing prices by approximately 0.46%–0.615% and 1.118%–1.503%, respectively; every 1% increase in urbanization rate results in an approximately 0.001%–0.0014% increase in actual average housing prices. This paper provides new insights into understanding the dynamics of urban development and housing prices.",0.0,https://ascelibrary.org/doi/pdf/10.1061/JUPDDM.UPENG-6315
7315bfdaddb6289b37a7d73d1182faf2107c497c,10.47065/bits.v4i2.2130,The Effect of Initialization Weights for Multi Layer Perceptron Performance on Prediction of House Construction Costs,2022.0,"Building of Informatics, Technology and Science (BITS)",A. Rozaq,"The house is one of the primary human needs besides food and clothing. Therefore, the community will always try their hardest to meet primary needs. For the middle and lower class people, it is going to very difficult to build a residential house because the income does not match the increase in house prices. With an artificial neural network, the middle to lower class people can estimate the costs that must be prepared if you want to build a residential house, of course this will be cheaper than using housing developer services. Based on the data that has been obtained, the researcher is then trained and tested using an artificial neural network with 13 data input, 25 hidden layers, a learning rate of 0.75, the number of iterations of 1000, the best test results are MSE value, 0.1, mean accuracy of 97.22 and computation time of 0,028 seconds",0.0,https://ejurnal.seminar-id.com/index.php/bits/article/download/2130/1427
a731247c2b779e9f70acd9b4763a55ac27db0a8d,10.1145/3767052.3767059,Machine Learning and Deep Learning-Based Housing Rental Price Prediction in China: Analysis of Endogenous and Market Factors,2025.0,"Proceedings of the 2025 International Conference on Big Data, Artificial Intelligence and Digital Economy",Shangjie Mo,"House price prediction has always been an important topic that attracts researchers from different fields. In this paper, an innovative house price prediction model is proposed, which comprehensively considers the intrinsic connection between various attributes of the house and the market price. This paper aims to accurately predict the reasonable price of a house under specific conditions through a variety of machine learning models, such as XGboost and artificial neural networks (ANN) and Convolutional Neural Networks(CNN), and analyze the important characteristics that determine the house price. Through the development and application of this model, this study provides more scientific and reasonable theoretical support for real estate market pricing, and also provides new research perspectives and methods for researchers in related fields.",0.0,https://dl.acm.org/doi/pdf/10.1145/3767052.3767059
a670c0239ac36ea0c7d908345a8e36f613189290,10.15396/eres2022_101,Stabilizing Geo-Spatial Splines with Helperpoints – How to Estimate Smooth Price Surfaces when there are Data Gaps,2022.0,28th Annual European Real Estate Society Conference,Norbert Pfeifer; Miriam Steurer,"This paper examines how to overcome an essential disadvantage of polynomial spline behavior: over-shooting of estimated spline functions in areas with poor data support. We introduce a new method that avoids the spline overshooting problem by placing helper points in data-gap areas before estimating the spline surface. We estimate helper point values via the Random Forest algorithm. Helper points force the algorithm to put a cost on deviating from reasonable local values in these areas. We show that our method can prevent spline overshooting where data are missing, can improve predictions in areas where data are scarce, but does not distort the spline surface in areas where data are plentiful. Our method also has a positive knock-on e ff ect in that it reduces the need for high (global) penalisation values and thus improves the spline’s response to changes in actual prices in regions with more data. Our method is particularly suited to the estimation of property price gradients, as property data are inherently unevenly distributed in space. We illustrate that our method can significantly improve the estimation of regional house price gradients using data for new apartment transaction",0.0,
9fdd9ae8df4ec58ee7c84efe4c586ccab7944056,10.2139/ssrn.3875963,"Demographics, Property Prices, and Credit Conditions: Analysis Based on Panel Data from 17 Countries Over a Half-Century",2021.0,Social Science Research Network,C. Shimizu,"Using panel data from 17 countries with varying economic circumstances from 1974 to 2019, we estimate regression models that explain residential property price dynamics by incorporating demographic factors and considering the interaction of those demographics with credit conditions. Our results show the importance of the demographic factors in modeling the long-run equilibrium of residential property prices. We find that the effect of nominal interest rates determined by monetary policy on asset prices varies depending on the country and the degree of population aging at the time. We also find that the persistently optimistic population projections lead to the oversupply of the residential stock in rapidly aging countries, resulting in stagnant residential property markets. Journal of Economic Literature Classification Numbers: E31, R21, R31",0.0,https://doi.org/10.2139/ssrn.3875963
7acf8629acb2a8f6c499c47a0a8b31bacead1d2d,10.1007/978-3-030-79150-6_47,Analysis and Prediction for House Sales Prices by Using Hybrid Machine Learning Approaches,2021.0,Artificial Intelligence Applications and Innovations,S. M. Soliman Hossain; Jyoti Rawat; D. Logofătu,". Over the past few years, machine learning has played an increasingly vital role in every aspect of our society. There are count-less applications of machine learning, from tradition topic such as image recognition or spam detection, to advanced areas like automatic customer service or secure automobile systems. This paper analyzes a popular machine learning application, namely housing price prediction, by applying a full machine learning process: feature extraction, data preparation, model selection, model training and optimization, and last, but not least, prediction and evaluation. We experiment with different algorithms: linear regression, random forest, and gradient boosting. This paper demonstrates the comparison of effectiveness of these algorithms that may help sellers and buyers to have a fair deal of their respective businesses.",0.0,https://inria.hal.science/hal-03287678
cb040bfe2b96548f7f8ec90514250f95aad2e49f,10.22214/ijraset.2022.40135,Amenity Detection using Machine Learning Algorithm,2022.0,International Journal for Research in Applied Science and Engineering Technology,S. Sivaranjani,"Abstract: For many centuries, statistics have been used as a prediction tool, until recently data science evolved. When hunting for a house, you may want to check out all the amenities the house has, to know if the house is really worth the price mentioned in any real-estate dealer website. To find so, image classification models are widely in use which first categorizes the photos listed on the website into different rooms and then finds the amenities present in the room by object detection algorithm [2]. Through Computer vision, we get a better understanding of the image/video which eases our house hunt. A comparative study between machine learning algorithms used in the state of art model and my proposed model for detecting amenities with a higher precision rate is produced in the upcoming sessions. Keywords: Dataset, Machine Learning",0.0,https://doi.org/10.22214/ijraset.2022.40135
fc067df80a7a4989006e5d292f765e6517c0a574,10.2991/emcm-15.2016.138,Research on Characteristics of Real Estate Price Bubbles in China,2016.0,,Minyi Yu; Chunjie Ma,"To illustrate the Chinese real estate market bubbles' situation and trends, analyze relevant characteristics and structural features, this research used qualitative and quantitative research methods, and focused on statistical analysis of housing prices in major cities and the whole country, like the growth rate of economic and price, the price earnings ratio and other data. Basing on the relevant literature at home and abroad, this results showed that there is a small deviation of China's overall economic development and the real estate index, individual cities is relatively large but still acceptable. Chinese real estate market bubble is not serious, because of irrational economic growth, super city agglomeration effect, short-sighted real estate regulations and deformity housing concept, consumers would feel house price is too high.",0.0,https://download.atlantis-press.com/article/25849676.pdf
83b9bcede57052f3ff5edb2f8c9379f4c66659d8,10.22423/kreus.2024.17.1.77,A Study on the Impact of Changes in Regional Housing Finance Policies on House Prices in Metropolitan Areas,2024.0,Konkuk Research Institute of Real Estate and Urban Studies,,"This study examines how the interaction between housing finance policies and regulatory areas affected house prices from January 2016 to March 2023, focusing on the strengthening of many housing finance regulations such as LTV, DTI, and DSR, and regulated areas such as overheated speculation districts and adjustment target areas. In particular, we aimed to identify the policy effects of housing finance policy and regulated areas and whether the interaction of housing finance policy and regulated areas stabilised the market in terms of house prices by region in the Seoul metropolitan area. Regarding the characteristics of regulated areas, we found that overheated speculation districts have been concentrated in Seoul since 2016, and in the case of the Seoul metropolitan area, overheated speculation districts and adjustment target areas have a positive effect on apartment sales prices, leading to an increase in apartment sales prices. In the case of LTV and DTI, we found that lower LTV and DTI ratios decreased apartment sales prices in Gyeonggi-do and Incheon. In contrast, in the case of DSR, it was found that lower DSR decreased apartment sales prices only in Seoul. Lower DSR decreas",0.0,
47a7e4224207516230f83966436b49344f226f8d,10.54691/hb38s736,Centralization or Suburbanization? A Multivariable Regression Analysis of Average Residential Housing Prices in Beijing,2026.0,Scientific Journal of Economics and Management Research,Aaron Kaiqiang Zhou,"In 1978 China initiated and implemented the Opening Up policy, thus accelerating the rural-to-urban migration in the country level. The research uses Beijing as an example to examine the relationship between average residential housing prices and three key influencing factors. Multiple linear regression was selected as the main methodology for the analysis. Results indicate that housing prices is negatively 0.044 associated with newly constructed residential units, positively 0.018 associated with total unemployment, and positively 0.530 associated with disposable income per capita. To compare, New York city was picked to demonstrate the value difference between China and US. It is recommended to Beijing with the strategy of suburbanization, satellite cities, and redistribution of educational and headquarters of business to rebalance.",0.0,https://bcpublication.org/index.php/SJEMR/article/download/9721/9652
ac196020eae3d620e456d96a0cc33a3c8ff45797,10.6007/ijarems/v3-i1/598,"Evaluation of the Effect of Investment Opportunity Cost on the Process of Housing Supply in Iran (Case Study: Isfahan province, 1992-2012)",2014.0,,M. Sadeghi; Iman Keyfarokhi; Salman Gharakhani,"Factors such as workforce wage, construction materials price, and financial credits and so on influence the supply of residential units in the housing market. Unique characteristics of housing such as durability, heterogeneity and immovability are effective on supply. Besides, housing has capital quality as well as the consumption quality. In this study it was tried to insert investment like other production factors in the production function. Also, this function has been estimated for different regions of Isfahan province in order to consider unique characteristics of housing. The results obtained from estimation of supply function in different regions in the province revealed that housing supply in these regions is mostly influenced by land supply and supply has a low elasticity in comparison with wage, credits and housing price.",0.0,https://doi.org/10.6007/ijarems/v3-i1/598
8b329069f31befe2c7c6201e70c748930ae32a2a,10.13060/23362839.2026.13.1.609,Housing Prices under Geopolitical Threats: Transmission Channels of Geopolitical Risk along the EU’s Eastern Border – The Case of Poland,2026.0,Critical Housing Analysis,Maria Czech,"The aim of this paper is to assess the impact of different categories of geopolitical risk (GPR) on housing prices and identify its transmission channels in a border country of the European Union. The analysis focuses on Poland, which constitutes the EU’s eastern border, has the largest and most dynamic housing market in the region, and is directly adjacent to war-torn Ukraine. The study utilises a vector autoregression (VAR) model for diagnostic purposes and a multiple linear regression (MLR) model for identifying the types of geopolitical risk responsible for observed price responses. The VAR results confirmed the existence of an indirect channel (the immigration channel). In the MLR, the aggregate GPR is statistically insignificant, while selected risk categories have a varied impact on the short-term dynamics of housing prices.",0.0,https://www.housing-critical.com/data/USR_057_DEFAULT/07_Housing_Prices_under_Geopolitical_Threats.pdf
fd7021df8ce5c07cbe7ce683066f1eda6d335d25,10.36543/kauiibfd.2026.004,DETERMINANTS OF REGIONAL HOUSING SALES IN TÜRKİYE: A SPATIAL ECONOMETRIC ANALYSIS,2026.0,Kafkas Üniversitesi İktisadi ve İdari Bilimler Fakültesi Dergisi,Burak Samet Iraker; A. Önder,"This study aims to measure the presence of spatial effects on housing sales in Türkiye at a regional level. The analysis specifically investigates the impact of interest rates, housing credit volume, and construction permits on regional housing sales in Türkiye, as well as other factors commonly used in the literature, such as real housing price, inflation, migration rate, unemployment, and GDP per capita. Using data from 2010 to 2023, NUTS-2 regions are analyzed through a spatial panel data method. The results indicate spatial interdependence in housing sales among regions of Türkiye. Furthermore, increases in the real housing price index, housing loan, interest rates, and inflation have been found to reduce housing sales, whereas increases in the total amount of housing loans and net migration rates lead to higher housing sales.",0.0,https://dergipark.org.tr/en/download/article-file/5312553
4f050e37e5a8a6c3c9cd0516dce5ab579093967d,10.1016/s0166-0934(07)00403-x,Journal of Virological Methods: Subject Index,2007.0,Journal of Virological Methods,,"Capital gains, Japan: recommended tax, 216; tax related to land, 226-29 Capital gains, United States, 193-94 Capital market, United States, 75-77 Case-Shiller property sales indices, 32, 35-36 Central business district (CBD), Japan: agglomeration economies in, 97-102; land price function, 114-25; land prices and population density, 102-8; Mills-Muth urban spatial model interpretation, 87-89; policy proposals for Tokyo, 125-28; TokyoNew York comparison, 89.91-97; underutilization of Tokyo’s, 1 11-13 Central business district (CBD), United States: composition of, 133-34; factors influencing move from, 145-48; factors limiting growth of, 157-58; housing consumption in, 135-39; wasteful commuting, 154-57 Commuting, Japan: cost of, 87-89, 108-11; costs, 88-89; subsidies for, 87-89, 126-27 Commuting, United States: by automobile, 145-48; costs of, 134, 136-41; large metropolitan areas, 141-45; metropolitan areas, 141-42; regression model of urban, 152-54; shift from public transportation, 148-52; urban trip characteristics, 150-52 Commuting, United States and Japan, 7-8 Company housing, Japan, 217,230-31 Consumption, Japan, 178. See also Bequest motive, Japan Consumption, United States: ",0.0,
4c788dd503356d6e1cf7d8c861bf3ff4fd10cd44,10.9734/bpi/castr/v15/8599d,Estimation of Land Value using Spatial Statistics: An approach towards Focusing on Real Transaction Land Prices in Korea,2021.0,Current Approaches in Science and Technology Research Vol. 15,Bongjoon Kim; Taeyoung Kim,"to The present work is aimed to compare OLS (Ordinary Least Squares) and spatial regression models which are methods of calculating the traditional value of land—using data on the practical transaction price of land—and to enhance the applicability of estimation of official land assessment prices set by the Korean government while deducing policy implications for effective implementation. That is, as a way to overcome the limitations of the traditional regression model, we compare various Generalized Regression Models such as SLM (Spatial Lag Model), SEM (Spatial Error Model) with OLS. Consequently, an in-depth diagnosis is conducted to generate a proper estimation model for land pricing, and, also, the analysis focuses on vertical and horizontal equity using COD (Coefficient of Dispersion), COV (Coefficient of Variation) and PRD (Price-Related Differential). The results indicate that SEM is more appropriate than AIC (Akaike info criterion) and SC (Schwarz criterion) in terms of measuring log-likelihood, demonstrating that the spatial autocorrelation model is superior to the traditional regression model. It shows that the SEM is also the best among the tested models with regard to ",0.0,
30471000ec443d8e28e3f371f59312723b425527,10.1108/ijhma-07-2022-0104,Investigating the asymmetric relationship between housing prices and the stock market in Iran: quantile-on-quantile approach,2022.0,International Journal of Housing Markets and Analysis,Roozbeh Balounejad Nouri,"
Purpose
The purpose of this study, the nonlinear relationship between the real estate market and the stock market was investigated in Iran. For this intent, the monthly data from 2012:4 to 2022:5 is used.


Design/methodology/approach
In this study, the quantile-on-quantile estimation method is used, which is a combination of the nonparametric estimation methods and the quantile regression.


Findings
The research results show that, in the low quantiles, the effect of stock market return on the housing market return is negative or zero. In fact, in this situation, the increasing returns in the stock market will shift part of the financial resources of the economy to the market and create stagnation or even negative returns in the housing market. This situation is seen more strongly in some other quantiles, including the 0.25 and 0.75 quantiles; in contrast, the effect of high quantiles of stock market returns is positive on the housing market.


Originality/value
It seems that the demand in the housing market increase in a situation where the returns of the stock market are growing, and the market is in a bullish condition, and this causes an increase in the price and returns in t",0.0,
c0ca419adb85a83abdceb712780f32c10d68f5cb,10.62381/e264408,"A Study on the Housing Tenure Choice Intentions of Youth and Its Influencing Factors from the Perspective of Population Migration: Evidence from a Field Survey in Zhejiang Province, China",2026.0,Economic Society and Humanities,Zixuan Wang; Shu-Yun Zheng; L. Wu; Ye Zi,"China’s urbanization has entered the middle and late stages, and young people have become the main force of urban–rural population migration. However, they generally face a dilemma between renting and purchasing housing due to high housing prices and an imperfect rental housing market, with significant differences in housing decisions between migrant youth and local youth. From the perspective of population migration, this paper conducts an empirical study based on survey data of 509 young people in Zhejiang Province, using descriptive statistics, multiple regression, and grouped OLS regression. The results show that the proportion of young people renting housing in Zhejiang is relatively high, and housing purchase pressure has become normalized. Pension insurance, family burden, and housing distress significantly affect youth’s housing tenure choice, and higher education can effectively reduce the housing purchase pressure of renting youth. Population migration also shapes youth’s housing behavior differently in terms of city hierarchy, individual characteristics, and family structure. This study reveals the internal mechanism of housing tenure choice decisions among youth in deve",0.0,
98438191d74bdd40ba8f1ee8325b8fb8b7420348,10.54254/2754-1169/4/20221059,Influence of Objective Factors on House Prices,2023.0,"Advances in Economics, Management and Political Sciences",L. Lyu; Xin-Yu Song,"With the development of economy and the improvement of people's living standards, many people will try to buy houses. But when it comes to buying a house, people will also pay attention to some objective factors such as the size of the house and supporting facilities. This paper uses the statistical analysis software SPSS linear regression analysis, factor analysis, comparative analysis and other methods to analyze the impact of objective factors on house prices, through data analysis, the fitting degree also reached about 0.88. In the experimental results, it is found that taxi distance, market distance, hospital distance, carpet area, built up area, parking type, city type, rainfall have a significant impact on house prices. Because in real life, These objective factors will be considered when people choose to buy a house.",0.0,https://www.ewadirect.com/proceedings/aemps/article/view/632/pdf
5671ef6cd26812170b178077f550b5aa9fdc40e1,10.31158/jeev.2025.38.3.739,Residential Areas’ Spatial Effects on College Enrollment Types: A Multiscale Geographically Weighted Regression Approach,2025.0,Korean Society for Educational Evaluation,Seo-Bo Park; Jin-Eun Yoo,"This study investigated the impact of residential areas on college enrollment types by analyzing 162 administrative districts in Seoul where general high schools are located. Previous studies, which employed traditional statistical methods assumining spatial stationarity, failed to account for the spatial dependence inherent in the variables. To address this limitation, the spatial autocorrelations of school and regional variables related to 4-year and 2-year college enrollment were examined using Moran’s I and Local Indicators of Spatial Association (LISA). Model performance was subsequently evaluated through comparisons of Ordinary Least Squares (OLS), Spatial Error Model (SEM), Spatial Lag Model (SLM), and Multiscale Geographically Weighted Regression (MGWR). The analysis yielded three key findings. First, significant spatial autocorrelation was identified in regional variables such as the average apartment sale price. Second, the MGWR model demonstrated better fit than the other models, particularly for 2-year college data. Third, from a local perspective, the MGWR model revealed spatial non-stationarity and locally varying effects of variables. These results highlight the nece",0.0,
3db0010c979648962d30e2e5c0b1cbdac492f127,10.33543/j.1401.3440,CALCULATING THE PRICE OF COMMERCIAL REAL ESTATE IN THE CZECH REPUBLIC,2024.0,AD ALTA: 14/01,Karel Brůha; Vojtěch Sloup; Iva Lorencová,"Property prices have surged recently, mainly due to limited real estate supply amid high demand supported by a large monetary base. This has driven up rental prices, especially in major cities compared to their peripheries. This manuscript examines rental prices in Prague, Brno, Ostrava, Pilsen, and České Budějovice from March to October 2023. It uses distribution functions, correlation coefficients, contour heat maps, and parameterized regression to define a probability price interval for office properties, identify a positive correlation between area and rental prices, and develop an algorithm for setting appropriate rental prices. The findings are useful for practitioners, real estate agents, and government institutions, though they are closely linked to macroeconomic variables. Future potential options are discussed.",0.0,http://dx.doi.org/10.33543/j.1401.3440
82a5228270eeb78556e15dacb919d275b0f57963,10.1109/icccnt56998.2023.10307946,Advanced Regression Models for Accurate House Price Prediction: An Analysis of Performance and Interpretability,2023.0,International Conference on Computing Communication and Networking Technologies,Abhigya Verma; Pooja Gera; S. Singhal; A. Mohapatra,"The accurate prediction of house prices has important implications for the real estate industry, investors, and policymakers. In this study, we aimed to compare the performance of various regression models, including basic and advanced techniques, in predicting house prices using a public dataset containing 79 features. Our analysis included extensive feature engineering and data preprocessing to ensure the best possible performance of each model. Our findings suggest that advanced models, such as Bayesian regression and kernel regression having mean cross_val_score 0.9046 and 0.9058 respectively, outperformed basic models, such as multiple linear regression and polynomial regression. We also identified the importance of addressing issues such as multi-collinearity and outliers in the data to ensure the accuracy of the models. Our study contributes to the development of more precise and reliable methods for predicting house prices, providing insights into the strengths and limitations of different regression models. The implications of our work extend to the real estate industry, policymakers, and investors who rely on accurate real estate valuations for informed decision-making. O",0.0,
bbc5cfca4ebec1ddeec39f4d061990c47c01851a,10.36825/riti.13.32.003,Desarrollo de aplicación web prototipo para estimación de valores de viviendas en México aplicando modelos de aprendizaje automático,2025.0,Revista de Investigación en Tecnologías de la Información,Fabián Espinoza Garza; Yobani Martínez Ramírez; Alan David Ramírez Noriega; Iván Noel Álvarez Sánchez,"The development of a prototype web application for estimating home values in Mexico using machine learning models (ML) is presented. The evolution of valuation in Mexico is described, along with the opportunity that machine learning represents to improve accuracy and efficiency. The article is based on open data from the National Housing Information and Indicators System (SNIIV) and employs Random Forest (RF) and Linear Regression (LR) models, highlighting the superiority of the former in performance. The methodology, architecture, and technological tools used to build the application are detailed, and the accuracy results are presented by state, demonstrating the technical feasibility of the prototype despite limitations such as performance variability and the lack of regulations for its application in real-life cases.",0.0,https://riti.es/index.php/riti/article/download/406/728
addca736b4d34741aeb57ccd2da843f375187d82,10.1109/cds52072.2021.00001,Proceedings 2021 2nd International Conference on Computing and Data Science CDS 2021 - Title page,2021.0,2021 2nd International Conference on Computing and Data Science (CDS),,The proceedings contain 103 papers. The topics discussed include: distantly supervision for relation extraction via LayerNorm gated recurrent neural networks;model optimization techniques for embedded artificial intelligence;a survey on single image deblurring;prediction of house price index based on machine learning methods;review of deep learning-based approaches for COVID-19 detection;comparative unsupervised clustering approaches for customer segmentation;technical change and development trend of automatic driving;target localization method based on virtual anchor nodes of one single unmanned aerial vehicle;one improved OpponentSIFT and HOPDFG descriptor based image classification algorithm;and business intelligence based novel marketing strategy approach using automatic speech recognition and text summarization.,0.0,https://doi.org/10.1109/cds52072.2021.00001
38bdcfa5cbca15dd16078daa707d480e6cf8cf31,10.18690/um.epf.5.2024.8,Prediction of Residential Real Estate Selling Prices in Serbia Using Artifical Neural Networks,2024.0,Challenges in the Turbulent Economic Environment and Organizations’ Sustainable Development,Ljiljana Matic; Vesna Ranković; Tijana Geroski; Zoran Kalinić,"The increasing housing prices over the past decades have added complexity to the real estate appraisal process. Therefore, it is important to create a proper prediction model which can encapsulate complex dependence of the property price from variable inputs. But, the problem of predicting real estate prices is highly non-linear and depends on many parameters. This research explores the potential of utilizing artificial neural networks (ANNs) to forecast the selling prices of apartments in Belgrade, Serbia, based on various apartment parameters. The findings demonstrate high efficiency of the ANN models in property valuation and, if all the preconditions of property value modelling are met, the ANN technique stands as a reliable valuation approach that could be used by both real estate researchers and professionals.",0.0,https://press.um.si/index.php/ump/catalog/download/870/1282/4109
702cae1a310df2978c8f8431f2b10b8f083488bd,10.1109/iconat66879.2025.11362756,An Innovative Framework on Predicting House Price Using Machine Learning Approaches,2025.0,2025 IEEE 4th International Conference for Advancement in Technology (ICONAT),D. Das; Ritam Dutta; Shilpa Singh; Shipra Sharma; Navin Kumar Goyal; Sanjay Kumar Sinha,"As house prices are increasing day by day therefore, it becomes a real necessity to create a smart mechanism to predict house prices around your area of choice. House Price Index (HPI) is mainly used to detect variations in house prices. House price is connected with some factors viz. the geographical location of the house, the population density around that area etc. Based on the specific location and population density, HPI detects the accurate price of the selected house. This technique can assist the buyer or seller in determining the accurate price of a house according to geographical location, and number of rooms availability. Our proposed machine learning (ML) approach i.e. Multiple Logistic Regression (LR) is applied to diagnose market trends and give more accurate result. In our proposed framework, we have collected two data sets from Kaggle. One is individual state dataset named “Bangalore house price dataset” and another one is “Dataset of India”. After an extensive literature survey on developing smart house price prediction framework, we have trained the existing model with Multiple LR, Decision Tree (DT) and Lasso Regression. Our simulator recorded the accuracy of 90.",0.0,
35666a064276bbb147a6e6129c1ed60a56a61643,10.24957/hsr.2026.34.1.5,Asymmetric Effects of Housing Supply: Evidence from a Nonlinear ARDL Model,2026.0,Korean Association for Housing Policy Studies,Ho-Gyun Byeon; Sang-Gun Lee; Yang-Ho Shin,"This study empirically analyzes the determinants of housing supply by applying the Nonlinear Autoregressive Distributed Lag (NARDL) model to identify asymmetric responses in the housing market. The analysis covers the Seoul metropolitan apartment market from January 2013 to September 2024, with housing supply as the dependent variable. The main explanatory variables include housing prices, construction costs, mortgage rates, land prices, gross domestic product (GDP), gross national income (GNI), and policy dummy variables representing the Moon Jae-in administration’s August 2 Real Estate Measures and the Yoon Suk-yeol administration’s 2.7 Million Housing Supply Plan. The results reveal that changes in housing prices exert asymmetric effects on housing supply. Supply increases gradually during periods of rising prices but contracts sharply during price declines, suggesting that developers respond more sensitively to market uncertainty. Rising construction costs, interest rates, and land prices were found to suppress supply, whereas GDP and household income positively affected it. In conclusion, housing supply does not respond linearly or symmetrically to economic and policy changes.",0.0,
a9db4156b0ec074010430d677c59dfd5dd44eca3,10.58225/tim.2025-3-207-215,AZƏRBAYCANDA İNVESTİSİYA-TİKİNTİ KOMPLEKSİ MÜƏSSİSƏLƏRİNİN İNKİŞAF ŞƏRTLƏRİ VƏ XÜSUSİYYƏTLƏRİ,2025.0,Tikintinin iqtisadiyyatı və menecment,F.Ə. Vəliyev,"An examination of the development trends in Azerbaijan’s housing market reveals that,
despite the increasing number of enterprises operating in the sector, housing prices have been rising
rapidly in a manner disproportionate to the income levels of the population. For example, in 2024,
overall housing prices increased by approximately 10–15% compared to 2023. The price growth in
new buildings amounted to 14–15%, while in old buildings it was 9–11%. This rise significantly
reduces the affordability of housing for the population. Most of the newly constructed apartments
are built mainly in city centers. However, the scarcity of available land plots in central areas leads
to a rapid increase in land prices. Nevertheless, the sharp rise in housing prices cannot be explained
solely by this factor. Therefore, it is necessary to examine the key problems in the formation and
improvement of organizational and economic mechanisms in Azerbaijan’s housing market, as well
as the development conditions and characteristics of the country’s investment-construction complex
enterprises. In addition, the influence of both external and internal factors on the quality and pricing
of housing products, t",0.0,
539c6241d6f7d7a09aa2c3739422b58b23325dc4,10.1088/1742-6596/1994/1/012023,Support Vector Regression with Gaussian kernel for Housing Prices Prediction,2021.0,"Journal of Physics, Conference Series",Di Miao; Hongru Tang; Bo-Sheng Wang,"The housing sector is one of the main sources of economic growth in both developing and developed countries. It is reported that nearly half of people buy or sell houses at an inappropriate price. Based on the public data set of Boston housing prices, this essay analyzed the factors affecting house prices and selected the five most important factors based on the decision tree with the ID3 algorithm. Then, this essay developed the support vector regression (SVR) with Gaussian kernel to predict housing prices. Experimental results showed that our method achieves superior accuracy and effectiveness compared with the SVR with linear kernel, KNN, and decision tree. To verify the applicability of our model, this research applied this model in Beijing housing price data, and it also achieved satisfactory fitting results.",0.0,https://iopscience.iop.org/article/10.1088/1742-6596/1994/1/012023/pdf
b64794ca2cf6d11f6f0d4dfe9693b1d1a650a754,10.37727/jkdas.2023.25.2.639,An Empirical Analysis of the Determinants of Household Debt in Korea,2023.0,The Korean Data Analysis Society,Dong-Woo Ko; Seong-Min Yoon,"South Korea's household debt is an important subject of research because it is constantly increasing in size and relatively large compared to other countries. In this study, the determinants of household debt are analyzed from the perspective of economic environment and policy factors. To this end, regression analysis was performed household debt and explanatory variable time series data from Q4 2007 to Q3 2022. The main results obtained from the empirical analysis are as follows. First, economic growth supports households' ability to afford debt. Second, the housing asset price factor contributed to the increase in household debt. Third, mortgage lending decreases when loan interest rates rise, but the effect of interest rate on aggregate credit is somewhat unclear. Fourth, the suppression and relaxation of housing lending through regulation has a significant impact on the size of mortgage lending. The results of this analysis suggest the following policy implications. First of all, in order to manage household debt, it is necessary to stabilize housing prices through housing loan policies. In addition, stable real economic management is required to support households' ability to ",0.0,
6ef1bbe6327b57182969f98c2677b769e798d8e2,10.54691/fhss.v2i12.3217,Discussion on the Influencing Factors of Housing Prices in Shandong Province,2022.0,Frontiers in Humanities and Social Sciences,Xinke Feng; Jia-Feng Yao; Zhu Shu,"Aiming at the influencing factors of commercial housing prices in Anhui, based on the relevant data of the 2000~2020 Shandong Statistical Yearbook, three explanatory variables of actual GDP, actual per capita disposable income of urban residents and total population were selected, and a multiple linear regression model was established by Eviews software, and econometric test methods such as multicollinearity, heteroscedasticity and autocorrelation were tested and the model was modified. The results show that the per capita disposable income and total number of urban residents have a positive impact on the price of commercial housing in Shandong Province. Based on the research conclusions, it is proposed to provide a reference for the stable development of the commercial real estate industry in Shandong Province.",0.0,https://bcpublication.org/index.php/FHSS/article/download/3217/3170
bd4e1700daf5091640904a663d417539f0358083,10.37407/kres.2025.43.1.93,A Study on Real Estate Lease Trend Analysis : Using Text Mining Techniques,2025.0,Korea Real Estate Society,Y. Seo,"This study analyzed 1,834 academic papers related to real estate lease issues published between January 1, 2020, and December 31, 2024, using text mining and topic modeling techniques. 
The results of frequency and TF-IDF analysis revealed that the most significant keywords were “housing,” “tenant,” “landlord,” “lease,” and “contract.” N-gram analysis showed that key phrases such as “Housing Lease Protection Act,” “Commercial Building Lease Protection Act,” “housing lease,” “landlord and tenant,” “Supreme Court rulings,” and “contract renewal request right” ranked highly. The CONCOR analysis confirmed that diverse topics were explored in the literature, including legal interpretations of residential and commercial leases, financial policies, institutional reforms, commercial real estate, and farmland leasing. The LDA topic modeling analysis identified major research themes such as legal disputes, changes in goodwill and the real estate market, the role of financial and economic systems, and policy discussions related to farmland and the environment. 
Based on these findings, future research is suggested in the areas of lease renewal rights and rent cap regulations, deposit returns ",0.0,
f9539860062e699a656b500bd1ba709ab1a44dd8,10.53486/9789975155663.06,Sustainable rural development by using land market evaluation in the Republic of Moldova with the space econometrics method as the financial tool in land consolidation,2022.0,"30 Years of Economic Reforms in the Republic of Moldova: Economic Progress via Innovation and Competitiveness, Vol III",D. Cimpoieș; A. Racul; I. Danilov,"The aim of the paper is to define the spatial econometric method for the land evaluation in rural areas by using the opportunity price in land transactions. The factors that determine land market in the Republic of Moldova are significantly related to the productivity of agricultural land, their location within the local landscape, characterized by the slope and soil quality, adjacency to local or republican access roads for storage and other. Also, an important role in the formation of the plots market price has the pressure of the urban space to convert the agricultural lands afferent to the cities and villages in industrial or residential spaces. This financial pressure with an exponential decrease concentric with respect to urban centers is not negligible in the formation of the price of land transactions.",0.0,https://irek.ase.md:443/xmlui/bitstream/123456789/2019/1/CIMPOIES-D_RACUL-A_%20DANILOV-I_Conf_September%2024th-25th_%202021_Vol_3.pdf
9aeb5e05694105f3fe1531442cdddb190e826cae,10.1080/15568318.2026.2634707,Revamping feasibility study framework for sustainable regional development - should we invest more in transport for lagging regions?,2026.0,International Journal of Sustainable Transportation,S. Cho; Keechoo Choi; Yongju Yi,"Abstract This research addresses the issue of the relationship between transport investment and sustainable development. More specifically, it supports the idea that a sizable transport investment for a region lagging economically is more cost-effective than that for a more developed area. Methodologically, a set of multivariable regression models is used based on econometrics principles. All three components (transport accessibility, industry, and the interactions of the two) comprising economic growth are preferable to lagging regions by raising house prices or income levels. This research answers positively the title above by comparing the opportunity costs for developed regions like Seoul with firm theories. We compare ten-minute walking accessibility, fifteen-minute accessibility, and thirty-minute accessibility by public transportation. All accessibilities are preferable to the non-Seoul areas, and more sizable accessibility intensifies the trend. The results obtained in this research can be used for sustainable economic development as a justification to evolve the incumbent feasibility study of transport facilities in Korea and can shed light on the future direction of fundi",0.0,
31bcde3e073273692e87cf9d46abdae7ca0d9afa,10.48550/arxiv.2510.04114,Wasserstein projection distance for fairness testing of regression models,2025.0,arXiv.org,Wanxin Li; Yongjin P. Park; Khanh Dao Duc,"Fairness testing evaluates whether a model satisfies a specified fairness criterion across different groups, yet most research has focused on classification models, leaving regression models underexplored. This paper introduces a framework for fairness testing in regression models, leveraging Wasserstein distance to project data distribution and focusing on expectation-based criteria. Upon categorizing fairness criteria for regression, we derive a Wasserstein projection test statistic from dual reformulation, and derive asymptotic bounds and limiting distributions, allowing us to formulate both a hypothesis-testing procedure and an optimal data perturbation method to improve fairness while balancing accuracy. Experiments on synthetic data demonstrate that the proposed hypothesis-testing approach offers higher specificity compared to permutation-based tests. To illustrate its potential applications, we apply our framework to two case studies on real data, showing (1) statistically significant gender disparities that appear on student performance data across multiple models, and (2) significant unfairness between pollution areas under multiple fairness criteria affecting housing pric",0.0,
3265c9e0bcce594c113217915320b22ce5b86518,10.56557/jobari/2022/v28i27608,ANALYSIS OF INFLUENCING FACTORS OF HOUSE PRICE IN CHANGSHA BASED ON THE MULTIPLE LINEAR REGRESSION MODEL,2022.0,Journal of basic and applied research international,Shimeng Gong; Li-Juan Hu,"House price has always been a hot issue concerned by the people. In recent years, the rapid growth of house prices across the country has become an important factor restricting economic development. Changsha has attracted much attention and reference because it has achieved good results in the regulation of the real estate market. By adopting the multiple linear regression model, we in this paper quantitatively analyze the factors that affect house prices in Changsha from four aspects: per capita disposable income, per capita consumption expenditure, total population at the end of the year, and investment in real estate development. It is helpful to grasp the development law of Changsha's real estate market and provide a certain reference basis for the regulation of the real estate market in other cities.",0.0,http://dx.doi.org/10.56557/jobari/2022/v28i27608
9308ff2cf5a64c1b41ac0d9ab4919a135e3c93e8,10.35136/krer.32.3.4,Effect of Redevelopment Project District Characteristics on Neighboring Housing Prices,2022.0,Korea Real Estate Institute,Jae Won Lee; S. Bae; Sang Youb Lee,"This study analyzed the impact of nearby redevelopment project characteristics on the apartment and single/multi-family house prices in all areas of Seoul. The impact of the distance to the redevelopment project area, the number of supply households, and the number of project areas were analyzed using the housing sale transaction price from 2006 to 2020, and all housing types show the same direction. Findings reveal that the closer the supply of households, the higher the transaction price. Moreover the number of project areas has a positive effect after a certain distance. This indicates a positive effect on factors such as price synchronization when new houses are supplied from nearby project areas, expectations as project candidates, and shares in the benefits of improving the residential environment. Redevelopment projects are likely to be used as large-scale housing supply assurance measures in the future. When designing an area, one must consider planning and progress by region so that the size, number of union members, and maintenance infrastructure ratio do not significantly impact the housing market. This study obtained general results for all regions in Seoul, yielding im",0.0,
836ff23bb78342f6d67dd0fbce42f477df2d7acf,10.24191/smrj.v20i2.24314,Housing preference among young people: A study from the perspective of university students in Malaysia,2023.0,Social and Management Research Journal,,"This article aims to investigate housing preferences among young people in Malaysia. This article argues the difference between the supply and demand of homes in this market that needs to be improved, especially on the actual needs of young people. This study utilises a quantitative survey to collect data, and statistical analysis to evaluate the research findings. The study's findings revealed that their housing preference was significantly influenced by factors such as housing price, housing location, housing environment and housing attributes. This research aims to assist housing providers in developing affordable housing that matches potential homebuyers’ preferences to avoid property overhangs and offer fundamental guidance to the government for creating housing policies that benefit young people.",0.0,http://dx.doi.org/10.24191/smrj.v20i2.24314
d36b509d603132645ed71fd666edd147059b9761,10.1109/uemcon62879.2024.10754766,A Data-Centric Approach to Post-Pandemic Housing Market Analysis,2024.0,"Ubiquitous Computing, Electronics & Mobile Communication Conference",Matin Pirouz; Preston Mccullough,"The housing market in California has gone through some unexpected fluctuations during the COVID-19 pandemic. The housing inventory reached at all-time lows and prices reached highs not seen since before the economic crisis of mid2000s. This paper explores these trends using Central California as a case study. Home valuation on home sales since 2018 in Fresno County of Central California are modeled with geographically weighted regression, geographically and temporally weighted regression, as well as artificial neural networks. Moreover, autoregressive integrated moving average models are utilized to explore the trends of price and days on the market in Fresno County. Finally, statewide COVID-19 data and Blueprint for a Safer Economy are used to predict changes in year over year housing prices across various California counties. The geographically weighted regression model outperformed the other two valuation models, both of which incorporate the date a home was sold as a predictor. The time-series analysis on Fresno County trends demonstrates unpredictability during the pandemic. The neural network underperformed in predicting sales price in counties, indicating that different poli",0.0,
da3a3796b804cb629a45b98bff36aefc948d5452,10.1371/journal.pone.0324005,WLreg: A new re-parametrization of the Weighted Lindley distribution and its regression model,2025.0,PLoS ONE,E. Altun; Christophe Chesneau; H. Alqifari,"A novel re-parametrization of the weighted Lindley distribution is introduced to develop a regression model suitable for skewed dependent variables defined on ℝ+. This new model is called the WL2 regression model. It is shown to outperform existing models such as the gamma, extended gamma, and Maxwell-Boltzmann-exponential regression models. Parameter estimation is performed using the maximum likelihood estimation technique, and the efficiency of these estimates is assessed through a simulation study. An application to a house price data set is presented to highlight the importance of the WL2 regression model. In addition, we propose the WLreg software, accessible via https://bartinuni.shinyapps.io/WLreg, to facilitate the application of the new regression model for practitioners in the field.",0.0,https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0324005&type=printable
99cc1ccea7e1a37f6653c266c68db9a63149a198,10.62381/acs.sdit2024.55,Analysis of Price Fluctuation in China's Real Estate Market Based on Least Squares Method,2024.0,Academic Conferences Series,Shutong Song,"Based on the least squares model, this study conducted an empirical analysis of price fluctuations in China's real estate market and explored the impact of macroeconomic variables and policy factors on real estate prices. Through the analysis of factors such as GDP, residents' disposable income, inflation rate, unemployment rate, interest rate and land supply, the results show that economic growth and the increase in residents' income level have significantly promoted the rise in housing prices, while the increase in inflation rate, unemployment rate and land supply has suppressed the rising trend of housing prices to a certain extent. The model test results show that the constructed model has good robustness, conforms to the structural characteristics of real estate market data, and the analysis results are reliable. Studies have shown that economic growth and the increase in residents' income are important driving forces for house price increases, while reasonable policy regulation and land supply management have a positive effect on controlling house price fluctuations. This study provides a quantitative basis for understanding the causes of price fluctuations in China's real es",0.0,
fd9178fb8cb70aa274f87d8f133f714287665f70,10.1080/00949655.2026.2686833,Higher-order spatial autoregressive partially linear varying coefficient models,2026.0,Journal of Statistical Computation and Simulation,Yan-Hui Li; Ti-Zheng Li,"{A new class of semiparametric higher-order spatial autoregressive models is proposed to make a significant contribution to spatial econometrics.} In this paper, we propose a new class of semiparametric higher-order spatial autoregressive models by allowing regression function to possess partially linear spatially varying coefficient structure. The proposed model is sufficiently flexible to simultaneously capture different types of spatial correlation and more accurately characterize spatial heterogeneity of regression relationship. We develop a computationally efficient and heteroskedasticity-robust estimation method for the proposed model by utilizing generalized method of moments (GMM) and local linear smoothing method, and derive asymptotic distribution of resulting estimators. Moreover, we develop a generalized likelihood ratio testing method to check whether coefficient functions in the proposed model have interesting parametric forms, in which a bootstrap procedure is suggested to appropriate null distribution of resulting test statistic. Simulation studies show that the proposed estimation and testing methods work quite well in finite samples. The Boston housing price data ",0.0,
d1e57dd75317f89c0f2bdafbbd0123f611146cdb,10.1108/jfmpc-04-2024-0031,"Spatial justice and apartment prices in Prishtina, Kosovo: unveiling the predictors and implications",2025.0,Journal of Financial Management of Property and Construction,Visar Hoxha; B. Beqaj,"
 
 The purpose of this study is to investigate the impact of spatial justice factors—such as access to amenities, green spaces, socio-economic status, transportation and environmental quality—on apartment prices in Prishtina, Kosovo, thereby contributing to the understanding of urban development dynamics in rapidly urbanizing cities.
 
 
 
 The present study used multiple regression analysis to investigate the relationship between apartment prices and various quantitative variables. Additionally, this study used logarithmic transformations and normalization to delve deeper into spatial predictors that affect housing prices.
 
 
 
 This study reveals that socio-economic status and access to emergency services are the most significant predictors of apartment prices. Furthermore, transportation and green spaces gained prominence after normalization, highlighting their context-sensitive roles in shaping housing prices.
 
 
 
 The originality of this study lies in its exploration of spatial justice variables in the underrepresented context of Prishtina, Kosovo, a rapidly urbanizing post-conflict city. By offering novel insights into urban housing markets and spatial justice, this resea",0.0,
c53999462c81b158b1b9bb0f8e5b78401c11e400,10.1515/rle-2025-0019,Property Rights and Price Discovery in the Housing Market: Evidence from School Quality Capitalization,2025.0,Review of Law & Economics,G. Turnbull; Minrong Zheng,"Abstract This paper applies meta-analysis of school quality capitalization estimates reported in the literature to examine the relationship between differences across US state approaches to protecting property rights and price discovery in housing markets. After controlling for possibly confounding influences from the housing supply elasticity and regional effects, the analysis shows that restricting local government powers of eminent domain for redevelopment is associated with house prices doing a better job conveying information about school quality differences across neighborhoods. While the property rights variables used here are narrowly defined, following previous literature, we argue they likely indicate the state’s broader approach to protecting private property rights in general.",0.0,https://doi.org/10.1515/rle-2025-0019
0ea15722d381f646e63256f35dd3106df61867a0,10.1109/icbase63199.2024.10762744,Birth Rate Prediction in China Based on Combination Algorithm of Factor Analysis and Neural Network,2024.0,2024 5th International Conference on Big Data & Artificial Intelligence & Software Engineering (ICBASE),Jingui Wu,"China has always been a large population, but in recent years, China’s birth rate has not increased, but has a downward trend. Therefore, on January 1, 2016, China opened the two-child policy for the first time since family planning was normal, but it has not worked, and even showed a downward trend year by year. At the same time, China’s age structure has shown an aging trend. In order to improve this situation, the three-child policy and a series of related auxiliary welfare policies were released on May 31, 2021. To this end, this article collects 11 factors that affect the birth rate in China from 2005 to 2022, such as housing price, education, child support and old-age support. The analysis method is used to reduce the dimension, and two comprehensive factors are obtained, and then the neural network model is used to predict the birth rate based on two comprehensive factors. Use the data of the first 16 years as training data, all 18 years are predicted as test data, and the average error between the predicted birth rate data and the actual birth rate data is $2.75 \%$. The prediction effect of the model is very good. Through this model, the birth rate in China is $6.7 \%-6.8 ",0.0,
3d7e50787f7248c2b9680305c93312d480e895ee,10.30845/ijhss.v9n2p16,Analysis on the Mobility of Urban Housing Price on Consumption in China,2019.0,International journal of humanities and social sciences,Hua-Fu Shen; Shunbin Zhong,"This paper study the mobility of urban housing price on consumption in china’s city. Firstly, this paper introduces the path of urban housing price on consumption. Secondly, the panel regression study shows that the increase of housing price has a significant positive effect on consumption. Further analysis by polynomial Logit shows that the rise of housing price has no significant impact on the location mobility of urban consumption from 2004 to 2008. In the period of 2008-2012, it can significantly promote the upward flow of urban consumption. In the cross-period from 2012 to 2016, it can significantly prevent the downward flow of urban consumption, while the upward flow has no significant impact. And these three different results are mainly due to the house price role in our economy.",0.0,https://doi.org/10.30845/ijhss.v9n2p16
578c7f8a67ed6a4885ad715128fbb75a8331a7a5,10.1103/f4vr-xdny,Diffusive Nature of Housing Prices.,2025.0,Physical Review Letters,Antoine-Cyrus Becharat; Michael Benzaquen; J. Bouchaud,"We analyze the French housing market prices in the period 1970-2022, with high-resolution data from 2018 to 2022. The spatial correlation of the observed price field exhibits logarithmic decay characteristic of the two-dimensional random diffusion equation-local interactions may create long-range correlations. We introduce a stylized model, used in the past to model spatial regularities in voting patterns, that accounts for both spatial and temporal correlations with reasonable values of parameters, some fitted on impulse response data. Our analysis reveals that price shocks are persistent in time and their amplitude is strongly heterogeneous in space. Our study quantifies the diffusive nature of housing prices that was anticipated in the 1990s, albeit on much restricted local datasets.",0.0,https://hal.science/hal-05273330/document
c88d4b568109010aa6900a74b688291b55b7122b,10.1109/swc65939.2025.00055,Advanced Machine Learning for House Price Prediction,2025.0,2025 IEEE Smart World Congress (SWC),Juan Pang; Rossitza S. Marinova,"This research uses machine learning to improve house price prediction, a key concern for buyers, sellers, and investors. Traditional valuation methods often overlook complex relationships between property features – machine learning models can better capture these dynamics. Using the Kaggle dataset ""House Prices: Advanced Regression Techniques,"" which includes 79 variables on homes in Ames, Iowa, we apply data cleaning, normalization, and feature engineering to prepare the data. The work evaluates a wide range of property features, including physical attributes, location specifics, and neighborhood characteristics, to increase the accuracy of house price predictions. Regression models including Linear Regression, Random Forest, and Gradient Boosting are evaluated, along with hyperparameter tuning and cross-validation to optimize performance. The goal is to develop a robust predictive model that accurately estimates house prices and identifies key predictors such as physical attributes, location, and neighborhood features. By enhancing prediction accuracy, this study supports smarter, data-driven decisions in real estate and contributes to the broader application of AI in smart urba",0.0,
eb1de91667e7277bcc04bde651e784ec4186d76f,10.5539/jmr.v12n2p1,Statistical Inference on Semiparametric Spatial Additive Model,2020.0,,Chuan-Hua Wei; Ran Yan; T. Tao,"There has been a growing interest on using nonparametric and semiparametric modelling techniques for the analysis of spatial data because of their powerfulness in extracting the underlying local patterns in the data. In this study, stimulated by the Boston house price data, we apply a semiparametric spatial additive model to incorporation of spatial e ects in regression models. For this semiparametric model, we develop a linear hypothesis test of parametric coecients as well as a test for the existence of the spatial e ects. For the problem of variable selection, the adaptive Lasso method was applied. Monte Carlo simulation studies are conducted to illustrate the finite sample performance of the proposed inference procedures. Finally, an application in Boston housing data is studied.",0.0,https://doi.org/10.5539/jmr.v12n2p1
4971bc2c72074ee341c24d7588056fb7f0ec7428,10.31920/2978-3380/2025/v1n1a4,Macroeconomic Determinants of Housing Supply in Kenya,2025.0,"African Journal of Urbanism, Architecture, and Building",Naftaly Mose; Erickson Matundura; Paul Odwori; Emmanuel Tanui; Martha Moreka; E. Mutai,"Kenya is one of the developing countries trying to provide affordable and decent housing to its residents. Macroeconomic instability persists despite efforts, impeding housing supply from both government and real estate sectors. This study examines the macroeconomic factors influencing Kenya's housing supply from 1980 to 2024, using time-series data. The augmented Dickey-Fuller and Johansen cointegration tests are conducted, along with the Vector Error Correction Model, to assess long run relationships between the variables, which allows for the use of the error correction model. Moreover, the Granger causality test examines the causal links between the variables. In the long-run, house prices and economic growth positively impact house supply while inflation rate, interest rate and the government expenditure negatively impact the supply of housing. Short-run analysis reveals a negative coefficient for interest rates. Granger causality testing supports the one-way feedback hypothesis between interest rate and supply of houses. Study findings suggest that government should explore methods to develop financial products and instruments that make it easier for individuals and governmen",0.0,
c51c3d25a708fb2d468d7debecb147e452f30635,10.54691/bcpbm.v32i.2985,Prediction of Housing Price in Beijing Based on Linear Regression Model,2022.0,BCP Business & Management,Dong Shao,"With the booming of the economy, more people are willing to have their own house and want to live in Beijing. But the increasing price make people feel confused and hard to do the choice. So this content describe the situation of housing price rise up in Beijing in 20 century by collecting the data and analyze the history and predict through linear regression. This action can help citizen to decide whether they should buy a house and where they are supposed to buy. From the content, the research demonstrates the city center is the most popular place and people want to live the place with the transport. What’s more, the housing price in Beijing will increase in the future. It can help people realize the how the house price system operates and let them to make the correct decision.",0.0,https://doi.org/10.54691/bcpbm.v32i.2985
a408e1de9351d02b0461b080fc8a88cb83cd15c4,10.37708//em.swu.v17i1.3,MACHINE LEARNING ALGORITHMS FOR FORECASTING ASSET PRICES: AN APPLICATION TO THE HOUSING MARKET,2020.0,Economics and Management,Anton A. Gerunov,"This article investigates the application of advanced machine learning algorithms for forecasting housing prices. To this end we leverage a dataset of 414 observations of housing deals in Taipei and model it with both traditional econometric and novel machine learning algorithms. An exhaustive search among 107 alternative methods is conducted and their forecast accuracy is reported in detail. Using the root mean squared error (RMSE) as a benchmark metric, we find that implementations of the random forest family have superior performance, far surpassing that of more traditional approaches such as the multiple linear regression. The results have utility for both academics and practitioners and can be easily t ransferred to other forecasting problems in economics and business.",0.0,https://doi.org/10.37708//em.swu.v17i1.3
74099967a079fff42f0df3135c0f69cc4e059615,10.23917/determinasi.v3i4.502,A Quantitative Examination of Housing Price Determinants in Yogyakarta,2025.0,Determinasi: Jurnal Penelitian Ekonomi Manajemen dan Akuntansi,Bagas Yudhanto Aji; Elit Rizki Wijaya; Juliana Diva Putri Raharjo; Nur Fazillah; Nuke Allya Nurmadina,"This study examines the determinants of housing prices in Yogyakarta, focusing on structural property features such as land area, bedrooms, bathrooms, vehicle slots, and house area. Utilizing a quantitative approach with multiple linear regression on secondary data, the research identifies land area as the most significant predictor of property value, followed by bedrooms and bathrooms. Vehicle slots provide moderate influence, while house area shows a lesser impact. These findings highlight the critical role of land scarcity and urban growth in shaping housing prices, offering actionable insights for policymakers, urban planners, and developers. Future studies should explore qualitative factors like neighborhood quality and cultural influences to complement these results.",0.0,https://jsr.ums.ac.id/determinasi/article/download/502/518
18fe9238aa258567492d025d82cef7701360966f,10.1109/icca66035.2025.11430799,Beyond Econometrics with a Spatial-Temporal Learning Framework for Predicting and Forecasting Housing Market Responses to Crime,2025.0,International Conferences on Computing Advancements,Jerome Mawuena Klu; I. Osunmakinde; M. Abdulgader; Cheryl Hinds,"Understanding the impact of crime on housing markets is essential for urban planning, real estate investment, and public policy. However, predicting housing price resilience is complex due to spatial and temporal crime dynamics. This study introduces the Model-Aided Resilient Forecasting Architecture (MARFA), a spatial-temporal framework combining machine learning models (Random Forest, XGBoost, Neural Networks) with an LSTM-based deep learning model to assess Virginia’s housing markets (2014–2023). The framework integrates categorized crime rates (property, person, and society) with housing price data to predict and forecast housing prices under three crime scenarios: baseline, +10% annual increase, and −10% annual decrease. XGBoost delivered the highest predictive accuracy (R2 = 0.9021; MA = 95.89%), while LSTM enabled multi-year forecasting. Compared to prior studies relying on econometric methods with limited forecasting, MARFA offers improved accuracy and broader spatial-temporal insights. Results show urban centers like Fairfax and Virginia Beach exhibit strong resilience, whereas smaller high-crime areas such as Galax are more vulnerable. This data-driven approach provides a",0.0,
75531b16f8b08606e95deb3ee258b079ecb57d92,10.4000/11y7n,Exploring Differences in Trends Between Private and Subsidised Housing Prices in Hong Kong,2024.0,Bulletin de Sinologie,Eddie C. Cheung; Yiu C. Ma; Kwok-Ho Chan,"As different classes of residential dwellings, government-subsidised Home Ownership Scheme (HOS) housing and unsubsidised private housing are aimed at adjacent groups of households on the housing ladder in Hong Kong. Subsidised housing is in high demand, and one important way of meeting it is to have better-endowed HOS families move up by buying into the private market. The paper explores the differences in price trends between these two classes of properties and attempts to find some of their determinants. Empirical analysis of historical prices of HOS and private housing reveals higher volatility in HOS prices and a differing trend with private market prices, as well as many more HOS transactions after the implementation of the White Form Secondary Market (WSM) Scheme.",0.0,http://journals.openedition.org/chinaperspectives/pdf/16952
e7af4f6a8560dbd619e402b3ff5067373a4dcb50,10.1177/14687968261437365,Perceived inequality of opportunity and xenophobic prejudice: Multilevel evidence from an Asian metropolis,2026.0,Ethnicities,H. Kim; Ahhyun Cho,"
 A large body of research addresses why some natives are tolerant of outgroup members while others oppose them. For the most part, prior studies focus on macrolevel indicators (e.g., unemployment, economic globalization, immigration influx) and microlevel characteristics (e.g., age, gender, education, income). Despite the difference in the unit of analysis, they commonly emphasize ‘objective’ factors rooted in the concept of xenophobic threat. Against this backdrop, the present study shifts the analysis to a ‘subjective’ dimension, namely, perception of (in)equality of opportunity. We contend that, all else equal, individuals who perceive their society to be more unequal, i.e., lack procedural fairness, show greater resistance toward outgroup members. Based on a large-scale probability sample (
 N
 = 42,923) of residents of Seoul, the capital of South Korea, we empirically demonstrate this argument. Specifically, Korean natives who feel a stronger sense of perceived inequality are less willing to accept, or more hostile toward, the foreign-born population. Our analysis further shows that the magnitude of this focal link is greater in the context of wealthier communities (measured ",0.0,
8e7cc531c0e95ca007c2793a76b35efaf0512132,10.1109/bigdata52589.2021.9671298,Tracking Property Ownership Variance and Forecasting Housing Price with Machine Learning and Deep Learning,2021.0,2021 IEEE International Conference on Big Data (Big Data),J. Jiao; Seung-Jun Choi; Weijia Xu,"Big data and its production, management, and utilization are essential components in smart city planning. This paper presents a research framework for applying machine learning and deep learning using multiple big data sets on real estate. We built ensemble machine learning models to track property ownership variance in Austin, TX, USA. Then, the study employed the long short term memory (LSTM) model as a deep learning approach to forecasting property value in the same area. For model validation, root mean squared errors were calculated in both models. To avoid underfitting or overfitting of LSTM, we experimented with specific parameters settings. Bagging-based random forest machine learning model outperformed other ensemble machine learning models. Regarding property ownership variance, the Random Forest model’s highest feature importance generally comprised the race, age of residents, land use and built environment factors, number of schools, and neighborhood location. Our LSTM model predicted Austin to retain a rising curve in housing prices and identified which part of Austin experiences an increase or decrease in property value. The predictive models may help city planners to ",0.0,
d25749a03659a8b7eff68324f4e72c597704e691,10.1177/00420980261452502,Superstar wealth inequalities and the role of housing: A regional perspective from Britain,2026.0,Urban studies,Isil Erol; Chris Foye,"This article examines the evolution of wealth inequalities across regions in Britain, and in particular the role of house price inflation, homeownership and mortgage debt in driving these wealth inequalities. Drawing on descriptive and regression analysis of eight waves of the UK Wealth and Assets Survey from 2006 to 2022, our findings indicate that (net) wealth inequalities rose more rapidly (and from higher levels) in London than in the rest of Britain. We argue that that this discrepancy can be significantly attributed to housing: not only did London experience higher rates of house price inflation but these gains were shared amongst a smaller subset of property owners and were levered with relatively high levels of mortgage debt. Moreover, London also has a disproportionately large number of asset-poor, low-income renters, which further exacerbates wealth inequalities. We also find that increases in homeownership rates at the regional scale are consistently associated with a compression of (net) wealth inequalities. Our findings highlight the need for more research that considers the distinctive features of different regions, and particularly ‘superstar cities’, in conditioning",0.0,
07c037af001c700907a158cf30fce23fc4070ab4,10.1109/ice-smartech59237.2023.10461965,A Deep Learning Approach to Predict Housing Market Price Trends in Bandung,2023.0,2023 1st IEEE International Conference on Smart Technology (ICE-SMARTec),Intan Rahmatillah; I. D. Sudirman,"The purpose of this study is to investigate whether deep learning can be used to accurately forecast Bandung area property values. The dataset was obtained from a well-known website for selling houses and then processed with three fully connected layers with eight neurons each to predict the label. The study shows that the deep learning model used to predict house prices has a high accuracy, with a small root-mean-squared error and a high correlation between predicted and actual prices. This model uses features such as square footage (area), bedrooms, bathrooms, and district to make predictions. House size is the most important factor, followed by the number of bathrooms and the Cibeunying Kaler district. The relative importance of each factor is also provided. These results add to the growing body of knowledge on the topic of predicting future housing prices and suggest that deep learning is a useful tool for homeowners, investors, and other players in the Bandung real estate market. This study demonstrates how deep learning has the potential to provide reliable forecasts of future housing price trends, which can aid in making sound choices. Additional features and datasets may be",0.0,
824516f44231cd0e6de2d438a950fd1e8f32feb0,10.1109/iccds64403.2025.11209198,Empowering Urban Planning Through a Data-Driven Framework for Smart Cities,2025.0,International Conference on Computing and Data Science,Priya Mina; U. Kumari; Amrita Behera; Megha Dua; Pankaj Gupta,"Cities worldwide are facing three interconnected difficulties as a result of the fast growth of urban populations: affordable housing, sustainable energy use, and effective transportation networks. The majority of current solutions are still fragmented and domain-specific, despite efforts to address these concerns through smart city projects. In order to give useful insights for urban planning, this study presents a unified, data-driven framework that makes use of machine learning and big data analytics. The framework's three main objectives are to es- timate urban energy consumption, identify gaps in public transit connectivity, and predict trends in housing prices. It analyzes historical data and produces predicts insights using supervised learning models, such as Linear Regression, Random Forest, and Gradient Boosted Trees (GBT). The GBT model performed better in terms of accuracy than the others. Furthermore, differences in transit accessibility and emission hotspots were highlighted by the integration of geographic visualization using Folium. An easy-to-use, scalable decision-support system that assists urban planners in building more efficient and equitable cities is made pos",0.0,
9fa6aad599ea0ab3ac382161a61fc9c3781af73c,10.15396/eres2019_42,Macroeconomic determinants of residential property prices and bubble testing in the property market in Ghana,2019.0,26th Annual European Real Estate Society Conference,Anthony Owusu-Ansah; Wilfred Anim-Odame,"In this paper, we examine the main macroeconomic factors that determine residential property price changes in Accra, the capital of Ghana and also test whether the residential property market is in bubbles. We employ quarterly time series data over 25 years and the vector error correction model (VECM) to examine the dynamics of the market. The principal results stemming from this paper show that GNI per capital, employment rate, inflation rate, stock prices, interest rate, cocoa price and urban population growth positively drive residential price in Accra. The results also establish that there is a long-term relationship between the seven macroeconomic indicators and residential prices in the country. Any short-term disequilibrium correct itself over the long-term because of these economic forces. This phenomenon suggests that the residential property market is not in bubbles. Understanding the fundamentals of residential market affordability in the country remains a challenge for policy makers. The study, which is a novelty in Ghana has accordingly produced results with policy implications for the government and policy makers in promoting residential property in the country, parti",0.0,
34292012819cef3d699a52adf030e77ba998c611,10.1142/s2010495225500034,"A Comparison Study of Single and Hybrid ARIMA, RF, SVR and ANN Models: The Turkish Residential Property Price Index",2025.0,Annals of Financial Economics,Ebru Çağlayan-Akay; K. Topal; Şaban Kızılarslan; H. Bülbül,"The autoregressive integrated moving average (ARIMA) model is widely used in time series analysis. However, this model is not able to capture nonlinear structures. The hybrid model brings different perspectives to forecasting analysis. This model uses a combination of ARIMA models and machine learning methods to overcome the deficiencies of single linear or nonlinear models. This paper aims to investigate whether hybrid models increase the forecasting accuracy compared to single models such as the ARIMA, random forest (RF), support vector regression (SVR) and artificial neural networks (ANNs). To this aim in this study, the Turkish Residential Property Price Index series were analyzed with the ARIMA, RF, SVR and ANN single models and the ARIMA-RF, ARIMA-SVR and ARIMA-ANN hybrid models. The methods were compared using forecasting evaluation criteria such as the RMSE and MAE. The findings proved that the ARIMA-RF has the highest out-of-sample forecasting accuracy compared with other models. Also, the Diebold–Mariano (DM) test was used for the comparison. DM test findings show that ARIMA-SVR also has significant prediction accuracy compared to other models. The results of the study su",0.0,
8655c6727505155b7e570963d773ca9150da3baa,10.3790/kuk.44.1.27,Migration und Immobilienmärkte: Fallstudie China,2011.0,,H. Nitsch,"We have examined the role of migration processes for the development of Chinese residential property markets at province level and have found empirical support of the following hypotheses: Migration between regions bears a close relationship with income differentials. The population shift induced thereby in combination with the disposable level of per-capita income and with urbanization is a dominant factor in the development of regional residential property price differentials in China. The main source of migration processes is the rural area compensating the weak natural growth in population in the metropolis. Conversely, high residential property prices in the conurbations are the determinants of the level of investment activity together with Tobin’s q.",0.0,https://hdl.handle.net/10419/293651
d6ce91755158f5e7f936d64c3b1263a530cacf9a,10.47611/jsrhs.v11i4.3151,Using Supervised Machine Learning to Predict House Prices,2022.0,Journal of student-scientists' research,Alexander Tsai; Hieu Nguyen,"Given the recent influx of prices in the housing market, determining a fair housing price has been of high interest for many homebuyers and sellers alike. In this project, various machine learning models are used to predict the price of a house based on physical features and characteristics such as lot size and neighborhood. Extensive data preprocessing and feature engineering were employed to aid the models’ performance compared to other models in the market. The best models have been able to predict U.S houses’ prices within a RMSE value of $23,000 when the mean price of a house in the dataset is $180,000. In future research, this model can be implemented in various other places within the U.S and additional features can improve performance further.",0.0,https://www.jsr.org/hs/index.php/path/article/download/3151/1640
3cf3d25cf5805bd4ad746c1985560227468d2faa,10.20527/jiep.v8i1.553,Faktor-Faktor yang Mempengaruhi Permintaan Rumah Bersubsidi diKota Banjarbaru,2025.0,JIEP: Jurnal Ilmu Ekonomi dan Pembangunan,Emylda Naura; D. Maulina,"This study aims to determine the effect of house prices, per capita income, and interest rates simultaneously and partially that affect the demand for subsidized housing in Banjarbaru City. This research uses multiple linear regression research methods with quantitative secondary data with a time series of 2010-2022. The results stated that simultaneously, all independent variables had a significant effect on the demand for subsidized houses in Banjarbaru City. Partially, price has a positive and significant effect, while interest rates have a negative and significant effect on the demand for subsidized houses in Banjarbaru city. While per capita income is negative and has no significant effect on the demand for subsidized housing in Banjarbaru city.",0.0,https://jiep.ulm.ac.id/index.php/jiep/article/download/553/489
8278d4bc6386f7850d62584a98831dc2b7c6f23d,10.67825/lrjstm.2026.8021631,Explainable Machine Learning-Based Decision Support Framework for House Price Prediction in Kathmandu Valley: A Comparative Study of Five Modern Regression Models,2026.0,"LBEF research journal of science, technology and management",Shambhu Gautam; Om Prakash Panjiyar; Sujal Shrestha,"Property valuation in the Kathmandu Valley is still largely informal, based on the heuristics of the brokers rather than on any systematic analyses. The present study builds and tests an explainable machine learning model for predicting the house price in Kathmandu, Lalitpur and Bhaktapur. After attempting to clean a raw data set of 2211 listing records (crawled 27 April 2020), a number of data-quality issues were identified and rectified, resulting in 1547 records for analysis. Five regression models—Random Forest, XGBoost, GBM, SVR, and KNN—were optimized using 5-fold cross validated grid search and trained and evaluated on ten engineered features, such as the target-encoded location score and a composite road accessibility score. Random Forest achieved the best test-set performance (RMSE = NPR 22,586,299; R² = 0.494; MAE = NPR 10,614,911), ahead of KNN, GBM, XGBoost, and SVR. In the explainability analysis, location score and amenities count were the top two predictors of the price across all methods, in contrast to the typical structural characteristics of the properties. The framework provides a transparent and reproducible decision support tool for the Kathmandu Valley market",0.0,
dbd33f8beb3a03a0e37000aa26d189fcaabf2b0c,10.1108/ijhma-10-2020-0127,Golf courses and home values in California’s Central valley,2021.0,International Journal of Housing Markets and Analysis,Nyakundi M. Michieka; D. Lacombe; Y. Ampatzidis,"
Purpose
The purpose of this study is to examine the net effect of golf courses’ proximity on home sale prices in Kern County, California.


Design/methodology/approach
A spatial Durbin error model is used with sales price data for 1,693 homes sold in Kern County in the third quarter of 2018. This paper compares 90 different spatial econometric models using Bayesian techniques to produce posterior model probabilities which guided model selection and the number of neighbors to use.


Findings
The results show that significant spatial dependence exists in home values in Kern County. Point estimates indicate that homes abutting golf courses are valued at less than those which are not. This study also finds that the farther away from golf courses the average home is, the higher its value.


Originality/value
This study contributes to the existing literature in three dimensions. First, this paper analyzes whether proximity to golf courses impacts home values in Kern County where a study of this nature has not been conducted. Second, the analysis uses transaction data for 2018 which was a period when the sport’s popularity was fading and golf courses closing. Third, Bayesian model compar",0.0,
7da8bdc306fd9690ce3d1e4097932659902b958f,10.1109/scisisis55246.2022.10002111,Sequential Estimation of Prices of Newly Built Houses in Tokyo Using the Linear State Space Model,2022.0,2022 Joint 12th International Conference on Soft Computing and Intelligent Systems and 23rd International Symposium on Advanced Intelligent Systems (SCIS&ISIS),Satoshi Yamada; Kazushi Okamoto; Atsushi Shibata,"In housing pricing, it is necessary to resolve information asymmetry and consider spatiotemporal heterogeneity. Conventional methods are based on regression models, which express heterogeneity by weighting using spatiotemporal distance or sampling by period while ensuring explanatory power through regression coefficients. These methods cannot capture changes from the previous regression coefficient. Therefore, the state-space model is used to update the regression coefficients sequentially, thereby making use of the information from the previous period. To verify the performance of this model, newly built house prices in central Tokyo from June 2016 to July 2017 were estimated and compared with the linear regression model and geographically weighted regression (GWR) in terms of mean absolute percentage error (MAPE) and calculation cost. The results suggest that interpolation can be used to estimate small sample sizes that cannot be estimated by the linear regression model and that the more efficient calculation since average prediction time is 338 times shorter than the linear regression model and 2234 times shorter than GWR. However, the MAPE median was 34.8% and 44.3% worse than ",0.0,
9d81b56654e92164cbceda63bcf6353186d89f84,10.1109/icaccs57279.2023.10112805,Computer Vision Based Empty Floor Space Recognition System For Infrastructure Management,2023.0,2023 9th International Conference on Advanced Computing and Communication Systems (ICACCS),Tejas Mahajan; S. Bhatlawande; S. Shilaskar; Suraj Chaudhari; Rohan Mahajan,"Efficiently monitoring occupancy to optimize space utilization is a fundamental aspect of infrastructure management that can lead to better resource allocation and reduced costs. This research aims to create a system that can identify vacant floor space, which is essential for managing various aspects such as facilities, real estate, retail, logistics, warehouses, and smart city infrastructure. For this, the detection of on-floor object should be done properly. To ensure that the system is correct, the images from the dataset must be properly pre-processed. The paper gives comprehensive overview about system which performs empty floor detection using different machine learning classifiers. The research done is basically focused on machine learning model which can give more accurate results. To evaluate the precision of the system, different machine learning classifiers such as Decision Tree, K Nearest Neighbour (KNN) and Random Forest are applied. Systems uses Binary Robust Invariant Scalable Key points (BRISK) feature descriptor to obtain the key points which helps all the classifiers to provide high accuracy. Different classifiers offered varying degrees of accuracy among those R",0.0,
8e8c97c370a59d5aea7be466ba47628e2b72e807,10.36997/ijusv-ess/2020.9.2.176,Income Inequality and House Prices - the Case of Bulgaria,2020.0,,Hristo Mavrov,"During the years of the global crisis in Bulgaria a housing bubble were developed and at the same time our country shows the highest income inequality among the EU countries. The purpouse of the research is to take part on the current debate about the link between income inequality and housing prices and to examine this relationship for Bulgaria. The Gini coefficient and Palma ratio were used as a measure of income inequality, and housing prices are presented in nominal and real terms for the period 2006-2019. The results of the regression analysis show a positive relationship between income inequality and housing prices in all cases, and for the period after the crisis the correlation coefficient is positive and extremely high and equal to 0.9.",0.0,https://doi.org/10.36997/ijusv-ess/2020.9.2.176
44e770ae5c501a6b23d91a578ed8bc84be5db836,10.54254/2754-1169/105/20241930,The Research about the Connection Between Housing Prices and Unemployment,2024.0,"Advances in Economics, Management and Political Sciences",Songhai Zhang,"The aim of this research is to investigate the potential correlation between housing prices and unemployment rates in London. Specifically, the study focuses on analyzing the relationship between the average housing price and the unemployment rate in the city. To achieve this objective, this paper employs statistical methods such as the t-test and regression analysis to determine whether there is a significant connection between the two variables. Additionally, a line chart is utilized to visually represent the changes in housing prices over time, providing a clearer understanding of the trends and patterns. By conducting this comprehensive analysis, we hope to gain insights into the potential impact of unemployment on housing prices in London.",0.0,https://www.ewadirect.com/proceedings/aemps/article/view/14109/pdf
b9d2976f3e9c9dafe3029a3e4512197ce17be8ef,10.17494/ogusbd.1682917,Robust Macroeconomic Determinants of Domestic Spot Gold Return in Türkiye,2025.0,Eskişehir Osmangazi Üniversitesi Sosyal Bilimler Dergisi,M. Hatipoğlu; Taner Sekmen,"The aim of this study is to investigate the robust drivers of gold return in Türkiye by using the extreme bounds analysis (EBA). According to findings, economic policy uncertainty, exchange rate, money supply and inflation are found four variables that are highly robust based on both Leamer and Sala-i-Martin models. In addition, house price is robust determinants of gold price as reported by Sala-i-Martin approach. From these results, it emerges that factors mentioned above are robust determinants of gold prices in Türkiye. The results of the study are also clear that spot gold return is driven by local variable more than global factors. This local factors are mostly related to the stance of monetary policy and the outcomes of monetary policy.",0.0,https://dergipark.org.tr/tr/download/article-file/4802805
7cf866f4ddcd337aa3f16c16941535eb12c2c174,10.1109/icsit65336.2025.11294987,Hybrid Real Estate Intelligence: Personalized Recommendations Using Machine Learning,2025.0,"2025 International Conference on Sustainability, Innovation & Technology (ICSIT)",M. Sridevi; V. Biksham; Salar Mohammad; Vangapally Raju; Y. Suguna; V. Reddy,"Nowadays growing the multiple property listings on the web, consumers rapidly struggle to search the important apartments properly. This article begins with a hybrid recommendation mechanism proposes to increase the apartment searching expertise by combining feature-based model similarity steps with machine learning methods for cost prediction. The proposed framework contains algorithms such as cosine similarity and K-Nearest Neighbors to recommend apartments which are similar with location, cost range, and model with type. Latest regression methods and techniques are applied apart from Random Forest, Gradient Boosting and XGBoost are exists to forecast property prices depends on the primary features. With the hybrid approach, proposes scoring approach with these two features are integrated to consider both the anticipated very less with affordability and the resemblance property for physical concern. The most suitable importance of regression models is predicting the metrics like MRR, Precision@5, NDCG@5, Recall@5 that are includes to calculate the quality of recommendation outputs. A more sophisticated effective system can be delivered accurate and property with tailored suggesti",0.0,
e59638d993bcf04239a2c849b87f04b5ad346434,10.48550/arxiv.2310.07563,Using Tableau and Google Map API for Understanding the Impact of Walkability on Dublin City,2023.0,arXiv.org,Minkun Kim,"In this article, we explore two effective means to communicate the concept of walkability - 1) visualization, and 2) descriptive statistics. We introduce the concept of walkability as measuring the quality of an urban space based on the distance needed to walk from that space to a range of different social, environmental, and economic amenities. We use Dublin city as a worked example and explore quantification and visualization of walkability of various areas of the city. We utilize the Google Map API and Tableau to visualize the less walkable areas across Dublin city and using WLS regression, we assess the effects of unwalkability on house prices in Dublin, thus quantifying the importance of walkable areas from an economic perspective.",0.0,https://arxiv.org/pdf/2310.07563
e43e7a2cc7f06fa96c88e6bdbf10be0769c23242,10.21203/rs.3.rs-805003/v1,House Price Prediction Model Based on Neural Network,2021.0,,Chusheng Wang,"
 Through an in-depth understanding of house price prediction issues, the paper aims to establish a BP neural network model for house price prediction based on ideas and methods of the BP neural network. By the BP neural network method, the paper realizes sorting, statistics, and analysis of house prices in Chongqing for 10 years as well as the main factor analysis of house prices. Then, correlative analysis is conducted with the software on house prices and their influential factors. Significant correlations are manifested. MATLAB was used to compile relevant programs and a BP neural network model was established for prediction and verification of house prices. Through the market survey, house prices are finally predicted by software.",0.0,https://www.researchsquare.com/article/rs-805003/latest.pdf
c24bf9b1f48cd30f265de26f0e97f698422708a5,10.1109/dsaa65442.2025.11247992,ModelForge: A Metric Approach to Machine Learning Model Consolidation,2025.0,International Conference on Data Science and Advanced Analytics,Florian Siepe; T. Prinz; Thorsten Papenbrock,"Many companies provide their customers with digital services for analytical purposes that are backed by modern expert machine learning models specifically trained for individual appliances. These models are often easy to train, but the deployment and operation of numerous individual machine learning models is a resource-intensive challenge. Due to hidden features in the individual appliances, consolidating all expert models into one model is often not possible. However, certain groups of models with similar appliances usually can be combined without (significant) loss in performance. To find these groups without knowledge of the actual hidden features, this paper proposes the consolidation algorithm ModelForge, which is based on a novel embedding strategy for model clustering. The Prediction Loss strategy embeds arbitrary models into Euclidean space in a way that close models share similar properties and can, therefore, effectively be consolidated. We validate ModelForge across four diverse domains, which are energy forecasting, timeseries anomaly detection, weather postprocessing, and house price prediction, to show that it yields more accurately consolidated models than previous ",0.0,
73f9f103667e733383ef3c8804c6780d34a53c14,10.2478/remav-2025-0024,Understanding Price-To-Rent Ratios Through Simulation-Based Distributions And Explainable Machine Learning,2025.0,Real Estate Management and Valuation,Jonas Vogt,"Abstract Index-level price-to-rent (PTR) ratios are a widely used metric for analyzing housing markets, employed by both real estate practitioners and policymakers. This article seeks to improve the contextualization of observed PTR values by examining the interplay between these ratios and macroeconomic and housing-market developments in a non-linear framework. We analyze historical data on housing prices, rents and macroeconomic developments from 18 advanced economies, spanning from 1870, using Boosted Regression Trees and explainable machine learning techniques. As a precursor to this analysis, we also present the empirical distribution of the price-to-rent ratio and the implied housing risk premia across all years and countries.",0.0,https://doi.org/10.2478/remav-2025-0024
78d383533cabae25ca0424953894b86a138916cb,10.1145/3569966.3571182,The application of spatial big data in urban real estate industry-A case study of Xi'an city∗,2022.0,International Conference on Computer Science and Software Engineering,Haoyu Yu; Xian-Xian Dang,"Real estate data analysis and visualization are important contents of urban research and urban management, while big data and computer technology provide scientific methods and tools for them. This research is based on big data technology. Firstly, the paper obtains the relevant massive data on the network through computer technology, and makes a visual analysis of the current situation. Secondly, the paper uses Kriging interpolation method to predict and analyze the trend of house prices and display them visually. Finally, the paper establishes an ordinary least squares (OLS) regression model to visualize and quantify the location factors affecting house prices, and makes a spatial differentiation analysis.The research results of this paper explore the spatial pattern and action mechanism of house prices in Xi'an, which has a certain reference significance for optimizing urban spatial layout and rational allocation of urban resources. At the same time, this paper establishes a set of methods of big data mining, data analysis, data visualization and extracting factors affecting house prices based on computer technology, which provides an idea for the application of big data in real",0.0,
e345676db9f8aa43245c7b9bdf49828a7a68e83e,10.15396/eres2019_82,A study on the impact of regional differences in housing of migrant workers and the integration of urban and rural development - An analytical framework based on behavioral economics,2019.0,26th Annual European Real Estate Society Conference,P. Lyu; Yue Gu,"Research objectives:Based on the analysis framework of behavioral economics, this paper explores the regional differences of migrant workers' housing.Research methods:theoretical analysis, spatial error model (SEM).Research contents:(1) At the micro intergenerational level, analyse housing between the new generation and the old generation of migrant workers by the influence of the regional differentiation.(2) At the macroeconomic level, the influences of different channels such as economic development, industrial structure and urban absorption on the housing of migrant workers are studied and discussed.(3) Taking urban and rural development as the condition, analyze the impact of regional differences on the housing of migrant workers;(4) Discuss the degree of regional differences of migrant workers housing in different periods, such as the short term and the long term.Research conclusion:In view of the intergenerational differences of migrant workers, we should improve the urban housing conditions of the new generation of migrant workers respectively, and give full play to the wealth effect of rural housing of the old generation of migrant workers. And according to the different re",0.0,
5a510ef6da8156877e7715936e3fa8cf89899540,10.48175/ijarsct-22034,A Study on Housing Price Prediction: Determinants and Effects,2024.0,"International Journal of Advanced Research in Science, Communication and Technology",Rajeshwari; M. N,"This study explores key factors that influence housing prices and assesses their impact on property valuation. By analysing a range of attributes such as area, number of bedrooms and bathrooms, stories, presence of air conditioning, basement, parking, and proximity to preferred areas the project aims to build predictive models for accurate pricing. The study uses sample of 500 house prices from Kaggle datasets and makes use of statistical and machine learning techniques, including multiple regression analysis, this research identifies significant predictors and quantifies their effect on house prices. The study provides insights into how property features offers useful information for buyers, sellers, and real estate professionals.",0.0,http://doi.org/10.48175/ijarsct-22034
32c2050a0ecf00c11014993bd07444b10c8a6951,10.1109/iccbd-ai62252.2023.00106,Price Prediction and Analysis Based on the LightGBM Regression Model,2023.0,"2023 4th International Conference on Computer, Big Data and Artificial Intelligence (ICCBD+AI)",Sheng Huang,"Price forecasting is widely used in many fields.lt is of great significance for economic development to find out the model and method of predicting price accurately.Traditional methods of predicting prices include market comparison, income restoration, and cost estimation, but these methods require a significant amount of human and material resources and usually fail to predict housing prices accurately due to the influence of numerous factors. Therefore, this paper aims to use the LightGBM regression model and LGBMRegressor algorithm for the prediction and analysis of housing prices. We collected a large amount of data on second-hand housing prices and preprocessed the data to eliminate entries with missing values. Subsequently, we performed a general descriptive statistical analysis of the data and established feature data and label data based on different characteristics such as region, age of the house, nearby geographical conditions, cultural and traffic factors. Finally, we divided the dataset and made model predictions. The experimental results show that the predicted values of the regression model are basically consistent with the actual fluctuations in housing prices, allo",0.0,
48a9e27aba4bd2ca8f96ba73d4ddda71359aa3fe,10.53383/100381,Productivity Shocks of Dominant Companies and Local Housing Markets,2024.0,International Real Estate Review,T. Nguyen; Arsenio Staer; Jing Yang,"We extend the literature on the influence of firm-level characteristics on housing markets by exploring the association between the labor productivity shocks of dominant firms and local housing prices. Using a sample of all U.S. firms from COMPUSTAT during 1980-2017, we find that the aggregate shocks of labor productivity of dominant firms at the metropolitan statistical area (MSA)-level explain for a significant portion of the local housing price changes in MSAs while controlling for other housing price determinants. About a year or more is required for the shocks to propagate through the local housing markets, which make them a viable predictor of future housing price. The productivity shock – housing price relation is stronger in areas that have more concentrated high-tech dominant firms or where dominant firms have closer links to their local non-dominant industry peers. Shocks are also more influential during economic expansion than economic contraction. Furthermore, the relation also exists at the zipcode level but the shocks propagate faster than at the MSA-level. The findings provide helpful insights for real estate practitioners and policymakers, especially in areas with a",0.0,
a28c9273c19f7ce7487da7d16266044745b78db5,10.7202/1111341ar,Fiscalité locale et prix immobiliers des propriétés résidentielles,2024.0,Canadian Journal of Regional Science,Asmae Aqzzouz; A. Schaffar,": The objective of this paper is to study the effect of property tax rates on housing prices. The paper focuses on the way property taxes and local public expenditures affect housing prices, in the 978 communities of the South region, by using spatial econometrics. One of the most original aspects of this paper is that is applies to a very thin spatial level of analysis, the county level. The paper develops original data for housing prices, property tax rates and local public expenditures. First, an increase in the property tax rates increases the housing prices which negatively affects the housing market’s exchanges. Second, this negative effect seems to be compensated when the county increases the provision of local public goods.",0.0,https://www.erudit.org/fr/revues/cjrs/2024-v47-n1-cjrs09327/1111341ar.pdf
b11c02b14e465e192bff0d31c43600c7871af71b,10.1109/iccubea65967.2025.11283836,Integrating Weather Data to Improve House Price Prediction Accuracy of Machine Learning Models: Evidence and Implications,2025.0,International Conference on Computing Communication Control and automation,Indranath Chatterjee; Swapnajit Chakraborti; J. K,"House price prediction has traditionally relied on textual features like the number of bedrooms, bathrooms, and square footage, but this approach often overlooks crucial qualitative aspects. Integrating house images allows models to evaluate visual appeal, architectural style, and property condition, including curb appeal, neighborhood aesthetics, and surrounding area demographics. Incorporating weather data enables analysis of both direct and indirect effects of weather on property values. The primary goal of including imagery data is to enhance prediction accuracy, while weather data serves to assess the impact of weather events on house prices. This research demonstrates that combining these diverse data sources, especially long-term weather data, enhances prediction accuracy. With different machine learning algorithms, this research has established that incorporation of weather data has led to increase the prediction power of house price models whether it is only textual or textual and imagery dataset. However, the improvement in prediction accuracy due to weather data varies depending on the region. These findings may be used for smart city initiatives, namely, urban planning,",0.0,
4e2e7696ecbdf4313c1f06feefa9e61c15d0d895,10.54691/bcpbm.v29i.2295,Did monetary policy cause a housing bubble in the US?,2022.0,BCP Business & Management,Bohan Feng,"This article uses quantitative analysis, setting three variables: the federal funds rate, mortgage servicing as a percentage of disposable personal income, and house prices. I made a simple model using the logical relationship of the independent variable, mediator variable, and dependent variable. Then regression analysis is conducted to explore the relationship between monetary policy and real estate bubbles. The conclusion is that loose monetary policy contributed to the housing bubble, but raising the federal funds rate did not contain the rise in housing prices, which means the existing monetary policy tools are insufficient to solve the problem. A better regulatory system is needed to avoid the emergence of bubble economies.",0.0,https://bcpublication.org/index.php/BM/article/download/2295/2277
7455838043be366abb4270b2ceec37f610b2b118,10.1108/jfrc-06-2018-0088,Comparison of advanced economies’ performance in bubbles mitigation,2019.0,Journal of Financial Regulation and Compliance,Emilio Gallego Neira; Carlos Martínez-de-Ibarreta,"
Purpose
This paper aims to analyze the effectiveness of macroprudential and fiscal policies taken from a sample of ten advanced economies in relation to the mitigation of real-estate and credit bubbles by comparing their performance.


Design/methodology/approach
This comparison is elaborated with a seemingly unrelated regression methodology, which allows the assessment of individual countries’ performance and improves the estimation of the dependent variables versus an individual regression.


Findings
The analysis concludes that countercyclical measures have been more effective to control the growth of household debt. Furthermore, this study validates that macroprudential measures focused on the residential sector meet their objective of controlling the growth of house prices, whereas those macroprudential measures with more generic targets are effective to control the growth of household debt.


Originality/value
As opposed to previous panel-regression studies, which have analyzed the performance of macroprudential and fiscal measures in generic terms, this paper compares the performance of these tools in ten advanced economies. Based on the analysis performed, several recommen",0.0,
71338b846833a334c9e4bdb0e8c028ab9d715dfe,10.1109/iscs69371.2025.11386147,AI-Driven House Pricing System using Machine Learning,2025.0,IEEE International Symposium on Compound Semiconductors,Meghna Luthra; Sangeeta Kumari; Rajshri; Jagriti Singh; Ayashi,"Accurately forecasting property prices in today’s dynamic market remains a crucial task, as it directly influences the decisions of buyers, sellers, investors, and policymakers. The older evaluation methods often failed to consider many important and diverse features like environmental and demographic variables, often resulting in less reliable predictions in the housing markets. In this research, Ensemble-based learning models like LightGBM and XGBoost outperformed other traditional models like Random Forest, Linear Regression, and Neural Networks. The gradient boosting algorithm was successfully applied to process large datasets and proved effective in capturing complex feature interactions. When used for processing large datasets, Gradient boosting models, showed high efficiency in capturing even the intricate feature connections. Features including socioeconomic indicators, such as flood-prone areas, population density, and crime rates, and proximity metrics, like the distance from schools, hospitals, and public transportation, were incorporated using spatial feature engineering. When purchasing or selling a home, this approach will help the people in the real estate market in ",0.0,
33395030a1242a611d340b7d0353e570f818e758,10.1109/uemcon67449.2025.11267586,Prediction of Housing Prices During Economic Variability Using Machine Learning and Deep Learning Techniques,2025.0,"Ubiquitous Computing, Electronics & Mobile Communication Conference",Maliha Momtaz; Faisal Quader; Rodney Leslie; G. Dimitoglou; Bill Hilbers,"Housing prices in the US market may be highly dependent on varying economic conditions such as inflation or other factors such as a pandemic, political instability, or engagement in armed conflicts. Monetary inflation, in particular, may cause sharp increases in the prices of various goods and services, including housing costs. In this work, we connect housing data and economic indicators using a housing and a consumer price index (CPI) dataset to predict home prices. The goal is to predict home values using machine learning (ML) and deep learning (DL) models (linear regression, recurrent neural networks, etc.). Various evaluation metrics and methods ($R^{2}$, adjusted $R^{2}$, and RMSE) are used to evaluate the performance of these algorithms. Our approach aims to help buyers, sellers, and policymakers better understand how economic changes affect housing prices. By accurately predicting price trends, stakeholders can make more informed decisions when buying or selling homes. This study also shows how combining different types of data can improve prediction accuracy. The results demonstrate that some machine learning models can effectively capture complex patterns in the housing m",0.0,
685fde4903f990542f952f7a10707fa3e1f661fe,10.1117/12.2628106,Applying multiple linear regression and quadratic curve fitting to predict Beijing's housing prices,2022.0,Other Conferences,Peixi Cheng; Shen-Yu Li; Jun Qi; H. Song,"This paper constructs a statistical model that could predict housing prices in Beijing. With the fast development of China's society, the real estate market has shown an incredible growth rate. For Beijing, as the capital of China, the housing market would be the most specific example for research. Thus, we gathered about 20 years of housing data from the official site to construct a statistical model to predict housing prices. Furthermore, we use predicted data compared with real data. Since China has strong central control, the market is most affected by policies, and we cannot quantify it. However, we chose several factors that could be put into the model, including income, GDP, population, consumption level, and GDP from construction. These factors are considered the most important elements that will affect housing prices and are the factors we use in our prediction model. In the end, we make the predictions for values in 2019 and 2020, and the predicted price has little difference from the actual data, which could demonstrate our model's accuracy. However, our model is built ideally, and for real-word prediction it needs to consider more unpredictable factors, such as central ",0.0,
b00d19428e1f19472b143f880d8549d7fbe7d420,10.26686/pq.v16i2.6478,Reforming capital income taxation to improve housing affordability,2020.0,,L. Allan,"New Zealand’s distortionary tax environment for housing imposes large costs on young people. Since 1989, New Zealand has taxed owner-occupied housing more lightly than other forms of capital income. In contrast, retirement savings have been taxed heavily. This combination has created a bias towards owner-occupied housing, encouraging homeowners to live in higher quality properties than they would under a neutral tax system, and bid up the price of land located near desirable amenities. 
While existing, often older homeowners have enjoyed high land and house values, our generation has faced artificially inflated house prices. Distortionary capital income taxation has contributed to New Zealand’s housing affordability crisis.",0.0,https://doi.org/10.26686/pq.v16i2.6478
df63fc964971d3a5e46b409ac941cbaa7498effe,10.1117/12.3107708,Research and implementation of housing price analysis based on multiple regression algorithms,2026.0,"International Conference on Telecommunications, Optics and Computer Science",Yang Gong,"With the continuous development and progress of the times, people's living standards are rapidly improving. At this time, people put forward higher requirements for ""housing"" in the basic necessities of life. For example, if you want to live in a better house, the relative house price will also be higher. In order to help those who need to buy a house, this paper proposes a housing price research and analysis method based on regression analysis, which first obtains the public historical data of housing prices; then cleans and analyzes the data; then visualizes the general laws of housing price data; The obtained data is modeled by different regression algorithms (K-nearest neighbor regression, polynomial regression, random forest regression (RFR), and support vector regression (SVR)) models; finally, four regression models are used to separately predict the newly arrived data, and then comprehensively compare different data. The regression algorithm model predicts the value. After a large number of experimental tests, the method proposed in this paper is simple to use and has high analysis efficiency. It can provide analysis and reference for people who need to buy a house, and it ",0.0,
4bdc7248b6068c181a5a84b1b4472cffeea1e613,10.5817/cz.muni.p210-9610-2020-33,Spatial differentiation of housing construction in Czechia: Towards Florida's new urban crisis?,2020.0,,E. Drápela,"Since the 1990s, there has been an increase in interregional differences in housing prices in Czechia. These differences largely depend on the size and economic strength of the municipality or regional centre, but there exist also differences between regions. The article uses the indicator of housing construction intensity (HCI) for the twenty-two-year period 1997-2018 per 1 km2, which is processed at the level of municipalities using spatial autocorrelation (Anselin Local Moran's I) and hotspot analysis (Getis-Ord Gi*), and presented in GIS. By comparing the results of both methods it was found that the interregional differences in the popularity of the Czech regions are significantly influenced by their distance to the main economic centres. On the contrary, the hypothesis that some regions with a worse environment, a higher share of the socially weak population and a low supply of above-average jobs will be the cause of the negative push effect has not been confirmed. In discussion, the current situation is compared with Richard Florida's concept of “New Urban Crisis”, to which arrival in Czechia it indirectly points to, although the initial conditions in Czechia are significant",0.0,
5aa0c59ec559223e2cc27a4234f041368d70bc74,10.1109/intech64186.2025.11198471,"Economic Impact of Location, Size, and Amenities on House Price Prediction in Tashkent",2025.0,InTech,Saidkhuja Farrux Ogli Yashinkhujaev; Akobir Mirzaakhmadov; Abdulaziz Miralim; T. Z.; Siddhartha Dutta Chanakya; Zahira Tabassum,"The aim of this study is to examine how machine learning tools can be applied to predict real estate prices. The majority of the current methods used to evaluate the prices of real estate properties tend to become rigid as the real estate market becomes more dynamic. In this aspect, this research beforehand is to construct a better and an adaptive model for estimating house prices using recent machine learning models especially with respect to certain issues such as market trends, property attributes and geographical position of the property. This study has tried various predictive modeling techniques, such as Decision trees, linear regression, ensemble approaches, among others, to identify the best suited approach for predicting price. It also brings forward the notion that to achieve the expected results, the data has to be well prepared with the appropriate features picked out and the model assessed. Results exhibit how machine learning improves efficacy in the price predictive analytics, which benefits buyers and sellers in the real estate industry. Lastly, we take a step forward in this innovative domain of artificial intelligence within properties by addressing future price p",0.0,
7e087fa13574b7bc9d66569acf30995c9fcc4728,10.32866/001c.147490,Downzoning Chicago: How Local Land Use Policy Has Reduced Housing Construction and Reinforced Segregation,2025.0,Findings,Y. Freemark; George Kisiel,"In the postwar United States, cities used downzoning policies to limit construction, often for the sake of preserving neighborhood aesthetics and protecting property values. We show that downzonings in Chicago between 1970 and 2016 were more frequently implemented in high home value areas. We evaluate downzoning’s consequences by comparing outcomes between Chicago tracts that were subjected to this regulatory change and those that were not, using fixed-effects regressions. In downzoned areas, housing supply declined, but housing values and white population shares increased. Overall, downzoning has contributed to reduced housing availability in high-demand neighborhoods, while reinforcing class and racial segregation.",0.0,https://findingspress.org/article/147490.pdf
304797b9f46ba924c409836f2406de84f26be27b,10.31460/mbdd.1668933,PREDICTING HOUSING PRICES IN ISTANBUL USING ARTIFICIAL INTELLIGENCE: A COMPARATIVE ANALYSIS OF ARIMA AND LSTM MODELS,2025.0,Muhasebe Bilim Dünyası Dergisi,Levent Sümer,"Due to high inflation, Türkiye has been struggling with high housing prices. This study compares two forecasting models: an econometric time-series model, ARIMA, and a machine learning algorithm, LSTM, in predicting housing prices in Istanbul. First, only the Central Bank’s quarterly average housing unit prices are used in both models. Second, two crucial macroeconomic variables, the mortgage loan interest rate and the inflation rate (as measured by the CPI), are added to the model. The results reveal that the forecast obtained from LSTM outperforms the ARIMA approach. This research fills a significant gap in the literature where the implementation of artificial intelligence in the housing industry is limited.",0.0,https://dergipark.org.tr/en/download/article-file/4740630
5ac2b60c997e73c29661f1ed7e694d765fe4f57a,10.53486/ser2026.08,Econometric assessment of the influence of financial and economic factors on the prices of new homes in Bulgaria (2015-2025),2026.0,Sustainability and Economic Resilience in the Context of Global Systemic Transformations,Andrey Zahariev,"This report presents an econometric model of type ARIMAX (0,2,1), developed to forecast and explain the dynamics of the House Price Index for New Dwellings in Bulgaria for the period 2015Q4-2025Q3 on a quarterly basis (40 observations in total). The model is based on a preliminary screening of 16 potential factors across four thematic groups: macroeconomic indicators, income and labour market, credit indicators, and investment and wealth. The objective is to identify statistically significant determinants of housing prices, assess the quality of the model, and formulate conclusions regarding its practical applicability for analysis and short-term forecasting of the new residential property market in Bulgaria.",0.0,https://irek.ase.md:443/xmlui/bitstream/123456789/5030/1/8.%20Andrey%20ZAHARIEV.pdf
ddb4167adfbea995b86dd4ed4f83bf6ff9971552,10.1080/01446193.2026.2724430,Re-evaluating the drivers of urban housing affordability from a construction cost perspective: evidence from the emerging real estate market,2026.0,Construction Management and Economics,Peres Ofori; Albert Chan Ping Chuen; Rotimi Boluwatife Abidoye,"Abstract Rapid urbanisation in Sub-Saharan Africa has intensified housing affordability crises, yet drivers remain poorly understood. This study tests whether construction material costs determine property prices in Kumasi, Ghana, using a mixed-methods design (139 occupants, 12 experts). Regression and robustness checks reveal that for residential properties, the relationship is negligible (R2 = 0.001, p = 0.634); material cost fluctuations explain <0.1% of price variation. For commercial properties, a significant positive relationship exists (R2 = 0.374, p = 0.003). Land costs (GHȼ 60,000–200,000/plot), locational premiums, and demand-supply dynamics dominate residential pricing. These findings are transferable to emerging economies with weak land governance and speculative markets. Material cost mitigation policies are ineffective. Policy must shift to land market regulation, spatial planning, tenant protection, and building standards, advancing Sustainable Development Goals(SDGs) SDGs::3, 8, and 11. The paper provides the first regression-based falsification of the cost-push hypothesis in Ghana, demonstrates residential-commercial divergence, and quantifies the affordability-dur",0.0,
47e55f1102316ae971d8dc2cdbc99c5f207ca5f9,10.1080/00343404.2025.2582638,Can more housing supply improve affordability? A subnational perspective from Portugal,2025.0,Regional studies,Diogo Ribeiro; Hugo de Almeida Vilares; L. Carvalho,"ABSTRACT We investigate the impact of housing supply on affordability in rapidly appreciating subnational markets in Portugal. Our spatial econometric model confirms a negative relation between housing stock and prices, yet predicts that, on average, maintaining the construction pace of the 2000s would lower prices by only 3%, while doubling it would bring a 6% reduction. We also find significant price impacts from short-term rentals and international demand. Simulations indicate that a policy mix combining moderate supply growth with sensible limitations in those domains could more effectively alleviate affordability pressures in high-demand regions, bringing spatial nuance to the ‘supply scepticism’ debate.",0.0,https://researchonline.lse.ac.uk/id/eprint/130587/1/Manuscript_pdf_with_figures.pdf
9a8ee9d9a3d0d084239bc3681d37dc4172b68f84,10.54254/2754-1169/2024.25061,Research on Different Factors Affecting Airbnb Housing Prices,2025.0,"Advances in Economics, Management and Political Sciences",Gengyuan Zeng; Ning-Ning Huo; Xinhe Zhang,"To study the different factors affecting Airbnb housing prices, this research uses the data from the Airbnb platform and evaluates key determinants influencing listing prices on the Airbnb website. The study employs exploratory data analysis (EDA) and linear regression analysis to analyze the impact of these variables on Airbnb housing prices. The research finding reveals that accommodations, bedrooms, and beds have a significant correlation with housing prices. Insights coming out of this research are able to provide valuable perspectives to Airbnb hosts and its housing rental business. It is suggested that focusing on these factors will enhance Airbnbs pricing strategies and its overall market performance.",0.0,https://www.ewadirect.com/proceedings/aemps/article/view/25061/pdf
a8e2e0c0bf8eb32585c21fc6a2c788b810e86ea7,10.53383/100397,Using an Asymmetric Loss Function to Alleviate the Risk of Loan Collateral Overvaluation,2025.0,International Real Estate Review,Changro Lee,"Financial institutions are increasingly adopting machine learning-based valuation models to evaluate loan collaterals. However, most machine learning algorithms do not differentiate between the risks associated with the undervaluation and overvaluation of such assets. From the perspective of a lender, the risks of overvaluing loan collateral are more critical than those that arise from undervaluing them. In this study, we alleviate this risk of overvaluation by explicitly considering an asymmetric loss function. We customize a gradient boosting machine (GBM) by specifying an asymmetric loss function, and assigning a higher penalty for overvaluation. This customized GBM is then used to predict house prices in Gimhae, South Korea. The results show that the GBM effectively reduces overvaluation while maintaining prediction accuracy. Researchers and practitioners need to intentionally bias their machine learning algorithms to incorporate the asymmetric risks associated with their businesses. The approach proposed in this study can help stakeholders make informed decisions in the lending process, thereby mitigating the risk of default by borrowers, and ultimately promoting sustainable l",0.0,
aa30118f72705961365846f2e02df6b0291fdcf7,10.2991/itms-15.2015.308,Study of Factors Affecting Consumer House Purchase Decisions in The Third-tier Cities ----- With Real Estate Market in Sichuan Jianyang as the case,2015.0,,Yong-Shun Lin,"Questionnaires of factors affecting consumer house purchase decisions were released in Jianyang. SPSS software was used for related determent analysis and regression analysis on influencing factors through data collection and sorting. Key factors affecting customer house purchase decisions were concluded from two aspects of total house price and purchase time afforded by customers. Study results showed that six variables of family income, residential area, real estate macroeconomic situation, living district overall layout, housing types and neighbor quality had significant impact on affordable house price and purchase time. KEYWORD: House purchase decisions; Influencing factors; Real estate market; Jianyang",0.0,https://download.atlantis-press.com/article/25843118.pdf
faa206cb5b84dd2d3aa940acb1af4299819e9239,10.1080/07474938.2025.2454410,The application of multiple-output quantile regression to the US financial cycle,2025.0,Econometric Reviews,Michal Franta,"Abstract The paper demonstrates the benefits of multiple-output quantile regression for macroeconomic analysis. The domestic financial cycle, which is characterized by the co-movement of credit and property prices, is a natural subject of such methodology. More precisely, I examine the tails of the joint distribution of US house price growth and household credit growth since the late 1970s to shed some light on the evolution of systemic risk and its links to various economic and financial factors. The analysis finds that the crucial indicators include the banking sector’s exposure to household credit, household leverage, house price misalignment, and financial market volatility. This contrasts with the negligible role of real-economy factors. In addition, the estimated effect of monetary policy shocks on systemic risk suggests rejecting the “leaning against the wind” strategy. Finally, it is shown that the multiple-output quantile regression framework is a useful tool for forecasting and tracking systemic risk over time. The sustainable growth of house prices and credit can be distinguished from their growth accompanied by the rise in systemic risk to guide policymakers on an appro",0.0,
dfa228916cb5e6c7a6ef82b5fa5df4487e390696,10.1080/03610918.2026.2649417,Linear partially time-varying coefficient spatial panel data model with fixed effects,2026.0,Communications in statistics. Simulation and computation,Xiaojuan Kang; Zhao-Yong Sun; Ti-Zheng Li,"Abstract In this paper, we propose a semiparametric spatial panel data model with fixed effects and partially time-varying coefficients. The proposed model serves as an intermediate class of models with good robustness by nonparametric treatment on certain explanatory variables and relatively more precise estimation on the parametric effects of other explanatory variables. To estimate the model parameters, we develop an estimation procedure based on local linear regression and profile likelihood. Moreover, a generalized likelihood ratio testing procedure is developed to identify explanatory variables with constant coefficients, in which a bootstrap procedure is suggested to approximate the null distribution of the resulting statistic. Simulation studies show that our estimation and testing procedures perform quite well in finite samples. In particular, our simulation studies demonstrate that efficiency gain can be achieved when information about the partially time-varying coefficient structure is appropriately utilized. We finally apply the proposed model and its estimation and testing procedures to study spatial spillover effects and time-varying feature of province-level house pr",0.0,
a40740d04b9c2ee1c8f235ad50bbdfc78d515b81,10.1007/s11079-017-9452-1,The Size of the Rental Market and Housing Market Fluctuations,2018.0,Open Economies Review,A. Czerniak; Micha L. Rubaszek,"The paper investigates whether the size of the rental market affects house prices fluctuations or the volatility of construction sector activity over the business cycle. For that purpose we construct a database of variables describing the housing sector in a group of twelve initial euro area members and ten other OECD countries over the years 1995–2014 and conduct a series of panel regressions. We find that a developed rental market attenuates fluctuations in the housing sector, especially for the common currency area sample. We claim that differences among monetary union countries in terms of rental market developments can be destabilizing as they might lead to heterogeneous response to common shocks.",0.0,https://link.springer.com/content/pdf/10.1007/s11079-017-9452-1.pdf
ee209d77c2ef5cd7007d0aa380d8946ca3401458,10.1109/csitss67709.2025.11294013,Assessment and Prediction of House Price Using Machine Learning,2025.0,2025 9th International Conference on Computational System and Information Technology for Sustainable Solutions (CSITSS),D. S; V. S; K. N.; Jose de Jusus Agustin Flores Cuautle,"The Assessment and Prediction of house price is a difficult area in the investigation. Traditional statistical methods are used to predict the prices, but they failed due to the complexity of real estate data and non-linear relationships among features. Various machine learning methods have become more popular for predicting home prices. because their ability to learn and solve the complex problems also relationships between the variables. The present investigation analyzes the house pricing data sets of Haryana state with two categories such as, Data collection based on parameters like, no of bedrooms, bathrooms, living area, number of floors, condition of the house, Postal Code, Number of schools nearby, Distance from the airport, based on these parameters 14000 datasets are collected, and the machine learning algorithms that are being compared are decision trees, random forests, and linear regression. Finally results reveals that, for Linear Regression the accuracy R-square obtained is 0.581, Decision Tree the accuracy R-square obtained is 0.631 and Random Forest the accuracy R-square obtained is 0.783. Random Forest is getting more accuracy than decision tree and linear regress",0.0,
4e208e373ccd6827ab7ac6860404e4f2c77fbda1,10.36871/ek.up.p.r.2026.07.01.015,The impact of digital nomads on interregional migration and financial flows in the regions of the Russian Federation,2026.0,"EKONOMIKA I UPRAVLENIE: PROBLEMY, RESHENIYA",E. A. Surina; N.Yu. Tanyushcheva; E. Timofeeva,"The article analyzes the impact of digital nomads – remote workers, primarily IT specialists leading a mobile lifestyle – on interregional migration and financial flows across the constituent entities of the Russian Federation. Based on official statistical data from Rosstat and the Bank of Russia, as well as data from the HSE statistical digest ""Digital Economy Indicators: 2026"" and the results of sociological surveys, the socio-demographic characteristics of digital nomads are identified, and donor and recipient regions are determined. It is found that the influx of high-income specialists into Krasnodar Krai and Kaliningrad Oblast stimulates growth in average per capita income, consumer spending, housing prices, and mortgage debt (growth up to 201%). At the same time, key risks are identified: the digital divide (the difference in broadband penetration between regions reaches 1.8 times in subscriber density), labor precartization, and deepening interregional inequality (the gap in gross regional product (GRP) per capita – up to 7 times). Recommendations are formulated for the development of state policy in the sphere of digital infrastructure and social protection of digital nom",0.0,
b6e9f3e04640bb727b2f12e671290d724f63ce3c,10.2991/icsser-18.2018.60,An Empirical Analysis of the Impact of Macroeconomics on Real Estate Market-Based on the data in China (2006Q1~2017Q4),2018.0,,Ji-Wen Jiao; Wei-Yu Jiao,"This paper sets up a VAR(1) model by collecting the quarterly data on China’s macroeconomic and real estate industry. By means of Granger Casualty Test, impulse response function and variance decomposition, the paper studies the impact of macroeconomic variables on real estate variables. The conclusions are as follows: changes in the macroeconomic system have a significant impact on the investment in the real estate development investment and the domestic lending; and the fluctuations of housing price, to some extent, are short of the support of macroeconomic fundamentals and effective demands. Keywords—Macro-economic; Real Estate; Vector Auto-regression; Granger Casualty Test; Dynamic Effects",0.0,https://download.atlantis-press.com/article/25904802.pdf
52fee415cd8218c59d3341f4483bd2df4a4ded50,10.1109/icsc67755.2025.11334736,Teaching Artificial Intelligence through Problem-Based Learning using Orange Data Mining: A Visual and Practical Approach,2025.0,International Computer Science Conference,A. Aitouche; A. Guerroui,"This paper presents a problem-based learning (PBL) strategy for teaching Artificial Intelligence (AI) through two practical case studies using Orange Data Mining-a visual and interactive platform that requires no coding. The approach engages undergraduate students with limited programming experience in real-world problems involving both regression and classification tasks. The first case involves predicting housing prices based on socio-economic and environmental variables. The second case focuses on fault diagnosis in Proton Exchange Membrane (PEM) Fuel Cell systems using real-time sensor data. In both scenarios, students design machine learning workflows, train models, and evaluate their performance using metrics such as precision, F1 scores and recall. Implemented in a third-year Bachelor AI course in ICAM Lille-Catholic Institute of Engineering and Technology, this approach enhanced students’ understanding of AI concepts, critical thinking, and modeling competence. Results from assessments and feedback suggest that combining visual tools with PBL creates an inclusive, engaging, and effective AI learning environment across domains including smart cities and sustainable energy.",0.0,
c89071ce7fe7a6f97ec7ffa5339b9616c41a47a0,10.71465/fias374,A Comparative Study of Machine Learning Algorithms for Predicting Housing Prices in Chinese Cities,2025.0,Frontiers in Interdisciplinary Applied Science,Jian-Wei Wang; Xiao-Ping Chen; Lin Li,"This study conducts a comparative analysis of machine learning algorithms for predicting housing prices in major Chinese cities, addressing the growing complexity and economic significance of the real estate market. With housing affordability becoming a critical socioeconomic issue, accurate price prediction models are essential for policymakers, investors, and urban planners. The research evaluates the performance of four algorithms—Linear Regression, Decision Trees, Random Forests, and Gradient Boosting Machines—using a dataset comprising historical transaction records, macroeconomic indicators, and location-based features from 10 major Chinese cities. Results indicate that ensemble methods, particularly Gradient Boosting Machines, achieve the highest predictive accuracy, with a mean absolute error reduction of up to 18% compared to traditional linear models. The findings underscore the importance of incorporating non-linear relationships and feature interactions in housing price modeling. This study not only provides a practical framework for real estate valuation but also highlights the potential of advanced machine learning techniques in addressing urban economic challenges.",0.0,
ec28d528a649781bb3c84ab02eb4d078126560c9,10.35940/ijitee.b6445.129219,Recommendation of Price on Airbnb using Machine Learning,2019.0,International Journal of Innovative Technology and Exploring Engineering,J. Choi,"Airbnb’s rental property prices are challenging because they determine how many customers there are. Customers, on the other hand, need to evaluate the offer price with minimal knowledge of the optimal value of the accommodation. This white paper aims to develop a reliable pricing model that uses machine learning and natural language processing techniques to assess prices by providing minimum available information about prices for both real estate owners and customers. Attributes, rooms, and bed features made up the predictors and created the prediction model using a variety of methods, from linear regression to root mean square error evaluation was used for creating the prediction model.",0.0,https://doi.org/10.35940/ijitee.b6445.129219
74e5d01b6b08f5ea07bcd112fa9d7c41bae73554,10.1109/icesit53460.2021.9696701,A Multi-modal Attention-based Seq2eq Model for Predicting Real-estate Prices,2021.0,2021 IEEE International Conference on Emergency Science and Information Technology (ICESIT),P. Yao,"Some studies show that the closure and reopening orders brought by covid-19 have had a negative impact on the residential real estate market. Generally speaking, real estate sales decreased significantly during this period, such as office buildings, shopping centers and family houses. Although the overall situation is declining, there are also some new situations. For example, people's desire for spacious family space caused by home office leads to an increase in the demand for large houses in the suburbs. This paper mainly compares the sales differences between suburban family houses and urban family houses in San Francisco and New York in the real estate market during covid-19. The data come from multiple dimensions such as house listing price on the real estate sales website, Machine learning methods could be used for analysis. This paper proposed a multi-modal joint attention seq2seq method to analyze these differences and the reasons for the differences. The experimental results show that one of the possible reasons the house price change in San Francisco is that there are more high-tech job position and their family income is higher than the average level of other regions.",0.0,
cad3f7a66ed4b2f7d1868c568362b1863a593b87,10.35136/krer.33.1.3,Relationship between False Price Reporting and Market Distortions in Real Estate,2023.0,Korea Real Estate Institute,Sungwon Lee; Chunil Kim; K. Ji,"In Korea, the housing market is undergoing a period of rapid price increases, and a policy to prevent false price reporting is implemented as a stabilization strategy. However, research on the relationship between false price reporting and market distortions in the real estate industry remains lacking. This study aims to empirically estimate whether false reporting of real estate price cause market distortions. Specifically, the prices of canceled trade suspected of false reporting and of normal trade are compared by using the data of Real Estate Trade Management System (RTMS) apartment sales in Seoul, Korea from Feb. 2020 to Dec. 2021. Double-adjustment in Propensity Score Matching is combined with Coarsened Exact Matching to obtain an accurate comparison. For the two groups of prices, pairs with similar attributes such as transaction time, location, apartment area, floor, and building age are matched. Results show no significant price difference between the two groups. False reporting of housing prices may have occurred in the specific period and region with high transaction cancelations, but its effects are negligible and cannot be concluded as a cause of market distortions.",0.0,
b229566723043222000ec52ff7abdf039b0ab7ae,10.11118/ejobsat.v2i2.55,Housing Price Fundamentals through the Business Cycle,2016.0,,M. Wenz; William Yu,"We examine the fundamental determinants of nominal home price growth from 1995 to 2012 across 300 metropolitan areas in the U.S. This sample period provides a trough-to-trough time period that allows for analysis through a complete business cycle. By using a supply-to-demand ratio for home price appreciation, we identify a straightforward and powerful method for predicting home price appreciation across markets. We suggest an alternative and simple method for addressing endogeneity in house prices and include a comprehensive measure of human capital. We find five significant factors: home supply growth, personal income growth, human capital, an ocean dummy, and geographic constraint.",0.0,https://journal.ejobsat.cz/index.php/ejobsat/article/view/55/pdf_26
a6f4e70c4bebbf36bb81febe96e673de0485c1b0,10.65864/aywc61kby1,Disparities in Pollution Capitalization Rates,2026.0,CESifo working papers,J. G. Zivin; Gregor Singer,"We examine how exogenous changes in air pollution exposure over the past two decades have altered disparities in home values between Black and White homeowners. We find that air quality capitalization rates are significantly lower for Black homeowners, so much lower that, despite secular reductions in the Black-White pollution exposure gap, housing value disparities increased. An exploration of mechanisms suggests 60% of this difference is attributable to seller race and 40% to racial neighborhood composition, robust to a range of seller, property and neighborhood characteristics. We discuss our findings through the lens of direct and systemic discrimination in housing markets.",0.0,https://www.ifo.de/sites/default/files/docbase/docs/cesifo1_wp11555.pdf
a77d4f15dc315a9a20152df49818fe723ad86be6,10.5220/0011754800003607,A Research on the Relevance of the Crime and the Housing Price Based on the Linear Regression Model,2022.0,"Proceedings of the 1st International Conference on Public Management, Digital Economy and Internet Technology",Jia-Li Guo; Zitao Ying; Zhengqi Sun; Y. Zhu,": As the most expensive area to live in the United States, Manhattan's housing prices are influenced by many factors, with crime rates being one of the most important factors affecting Manhattan's housing prices. Under this situation, this paper will explore the relationship between house prices and crime rates in Manhattan through the house prices and crime rate data in 2016-2017, by using python and R to build a simple linear regression model to find the relationship between the average house price and crime rate. As for the conclusion section, this paper will give the results of the analysis of the data with the conclusion and the practical implications of this conclusion.",0.0,https://doi.org/10.5220/0011754800003607
4130cce5b8b0e6f5bea96e21912b6db9c57eedc0,10.22495/cocv9i3c4art7,DETERMINANTS OF THE UPSWING PHASE IN THE SOUTH AFRICAN REAL ESTATE GROWTH CYCLE,2012.0,,M. Franken; J. Bloom; Rousseau Lötter,"Understanding and predicting cycles in real estate prices would allow investors to maximise their investment in real estate. This paper builds on the work of a previous study and includes a regression analysis of the upswing phase of the residential real estate growth cycle, which is intended to identify potential leading indicators of an upswing phase in the residential real estate cycle. The results for the upswing phase indicate that house prices, interest rates, growth in household consumption, growth in the South African All Share Index and growth in the Rand-Dollar exchange rate, all lagged by one quarter could be considered to predict the upswing phase of house prices.",0.0,https://virtusinterpress.org/spip.php?action=telecharger&arg=5401&hash=ed7c7a54ebccbf5d79118de965c7918c530c19c1
92b606bb098a0347861424cd53e378579ff05bad,10.1177/23998083251378324,"The development differences of districts and the boundary effect of housing prices in Hangzhou, China",2025.0,Environment and Planning B Urban Analytics and City Science,Ling Zhang; Si-Jie Chen; Lifei Zhu,"This study investigates whether significant price differentials exist for otherwise comparable houses positioned on either side of district boundaries. A spatial regression discontinuity model is developed to explain the administrative boundary effect of housing prices through differences in development quality among various districts. The findings show that differences in the level of comprehensive economic and social development between districts are an important reason for differences in housing prices and the emergence of boundary effects. The spatial differentiation of housing prices on either side of a boundary is consistent with the comprehensive development quality of districts. Moreover, the difference in high-quality educational resources among different development factors holds the greatest explanatory effect on the administrative boundary effect of housing prices. The key remaining explanatory factors, in descending order of importance, are population density, employment density, the presence of first-class hospitals, and average fiscal revenue. These findings offer insights into potential strategies for balancing development in rapidly growing cities.",0.0,
5a8c923a0b10dee052f28900574d5d29b1998057,10.54091/krepa.2022.23.1.1,An Empirical Study on the Effect of Real Estate Policy on Housing Price Using a Regime Switching Regression Model,2022.0,Korea Real Estate Policy Association,Chasoon Choi,"the Markov regime switching model. As a result of the analysis, it could be captured that variables significantly affect on real estate prices in each regime. 
First, it was found that during the boom, the policy to strengthen real estate regulations did not have an effective influence on stabilizing the housing sales market. Second, it was found that deregulation and strengthening policies had an effective effect on each market during the recession and boom of the jeonse market. Third, ρ11 and ρ22, which are the probabilities of the transition, show a phase of recession and boom, respectively, and the real estate market is all more likely to maintain the recession. Third, ρ11 and ρ22, which are the probabilities of the transition, represent the phase of recession and boom, respectively. ρ11 is larger than ρ22, so the housing sales, jeonse, and land markets are more likely to maintain the recession. This shows the characteristics of asymmetry and phase persistence of real estate price volatility. Therefore, there is a need to closely monitor the effectiveness of each policy means for each phase, develop and apply a prediction and evaluation simulation model.",0.0,
daf03a7c559a39abe6c5fd64122e366daf10994c,10.1109/icdsca53499.2021.9650136,Computer mathematical statistics applied in the housing price investigation through machine learning and linear regression model,2021.0,2021 IEEE International Conference on Data Science and Computer Application (ICDSCA),Bo-Han Jia,"To Figure out the inner law of the housing price in Beijing and the key factors that influence the housing price, quantitative analysis is used through three statistical tools: autoregressive moving average model, linear regression model and random forest model. The first model shows that the coefficient of autoregressive part is greater than one, revealing an increasing trend of housing price. The second model shows that there are four factors, number of residents in Beijing, production of tertiary industry, per capita urban disposal income, number of elementary school students, have strong linear relationship with the housing price. From the third model, there are three factors, number of subways, number of buses and number of medical institutions, may have strong non-linear relationship with housing price. Then the conclusions that the increasing trend of housing price in Beijing may be kept in the future, there are 7 main factors having robust relationship with the housing price in Beijing, though some of them may not be linear and the statistical tools can be really helpful in analyzing the field of housing price or some other fields have been reached.",0.0,
3db8e798cf760db972f5428a89e267c0d5a82425,10.1097/01.ju.0001009372.61513.54.07,MP35-07 RACIAL DIFFERENCES IN BLADDER CANCER MORTALITY ADJUSTING FOR SOCIODEMOGRAPHIC DISPARITIES IN A STATEWIDE CANCER REGISTRY,2024.0,Journal of Urology,Mollie Goldman; Camilo Arenas-Gallo; Adithya Balasubramanian; Jack C. Millot; Xian Wu; Alec Zhu; Stephen Rhodes; Jason R. Brown; J. Shoag,"INTRODUCTION AND OBJECTIVE: Sociodemographic disparities in fl uence bladder cancer (BCa) outcomes. We explored differences in bladder cancer speci fi c mortality (BCSM) and other-cause mortality (OCM) between Black and White patients from Ohio, after accounting for baseline characteristics, cancer features, and social determinants of health including area deprivation index (ADI) and wealth. METHODS: We used the Ohio Cancer Incidence Surveillance System to capture clinical and demographic data from patients diagnosed with BCa between 1996 to 2016. Patient home addresses were linked to home value estimates from Zillow.com to serve as a proxy for individual wealth (Zestimate). ADI was sourced at the census block group level. Primary outcomes were group differences in BCSM and OCM. Groups were balanced for cancer and sociodemographic variables at diagnosis via inverse probability weighting. Group comparisons were made via weighted cumulative incidence functions and weighted Fine-Grey subdistribution hazard models. RESULTS: The fi nal cohort included 37,148 patients, of which 35,182 (95%) were White and 1,966 (5%) were Black. Most patients had urothelial BCa",0.0,
3ad1cba09577309f1ae002023958a18fa55e971a,10.4018/978-1-5225-9276-1.ch017,Housing Submarkets and Future Demographic Developments,2020.0,Megacities and Rapid Urbanization,D. Kyriakidis,"Europe is undergoing a profound demographic change. This change will affect significantly all aspects of modern economies including the demand and the prices of the housing stock. The relationship between prices of the housing market and associated demographic variables has been long established. However, in the current literature, the housing market is considered to be unitary and coherent, that is one price reflects the housing stock without taking into account the housing characteristics which in real economy are considered essential for price calculation. To this respect it must be noted that housing submarkets existence has been long established based on the current literature. However and in relation to housing submarkets, the actual goal of the studies currently exist was the definition process, the models and the techniques that should be employed in order to acquire best results. Housing submarkets are considered important in the understanding of different social phenomena. In this chapter an attempt is made to review the relationship of housing prices to demographic variables and then a review on the definition process of housing submarkets.",0.0,
821769831965c61647bdfca84a127d5aa2390d07,10.1109/smarttechcon57526.2023.10391563,Research on Optimization Algorithm of Real Estate Enterprise Value Evaluation Based on BP Neural Network,2023.0,2023 Second International Conference On Smart Technologies For Smart Nation (SmartTechCon),N. M; S. Surendran; S. Saravanan; Tulsidas V. Nakrani; M. R.; M. Arun,"Because of its professional skills and expertise, it is able to persuade both the buyer and the selling and make the transaction easier. An optimal design scheme for real estate businesses' worth appraisals is proposed here, and it is based on BPNN (BP neural network). A worth appraisal system is developed by doing an analysis of several worth indicators pertaining to real estate companies, and then the system is optimized with the use of BPNN. In the final step, an analysis of the simulation test is performed. According to the findings of the simulation, the arithmetic has a certain accuracy, which is 8.34% higher than the accuracy of traditional arithmetic. On the premise of ensuring the efficient processing of data in batches and finding the rules therein, reduce the impact of human subjectivity, improve the accuracy and scientificity of real estate appraisal, and provide certain reference for the national and local governments to reasonably regulate house prices, so as to promote the stable operation and healthy development of the real estate market. In doing so, you will be able to promote the growth of the real estate market in a healthy manner.",0.0,
9fb3927d427945afbdca7c2dec8cd7915f0105d3,10.1097/01.ju.0001009372.61513.54.08,MP35-08 MAPPING SOCIOECONOMIC DISPARITIES: ANALYZING RADICAL CYSTECTOMY OUTCOMES IN SAN DIEGO COUNTY,2024.0,Journal of Urology,Dhruv Puri; K. Yuen; M. Meagher; Kshitij Pundit; Austin Fan; M. Wong; Joanna Langner; Nuphat Yodkhunnatham; Y. Santiago-Lastra; Tyler Stewart; Aditya Bagrodia; A. Salmasi,"INTRODUCTION AND OBJECTIVE: Sociodemographic disparities in fl uence bladder cancer (BCa) outcomes. We explored differences in bladder cancer speci fi c mortality (BCSM) and other-cause mortality (OCM) between Black and White patients from Ohio, after accounting for baseline characteristics, cancer features, and social determinants of health including area deprivation index (ADI) and wealth. METHODS: We used the Ohio Cancer Incidence Surveillance System to capture clinical and demographic data from patients diagnosed with BCa between 1996 to 2016. Patient home addresses were linked to home value estimates from Zillow.com to serve as a proxy for individual wealth (Zestimate). ADI was sourced at the census block group level. Primary outcomes were group differences in BCSM and OCM. Groups were balanced for cancer and sociodemographic variables at diagnosis via inverse probability weighting. Group comparisons were made via weighted cumulative incidence functions and weighted Fine-Grey subdistribution hazard models. RESULTS: The fi nal cohort included 37,148 patients, of which 35,182 (95%) were White and 1,966 (5%) were Black. Most patients had urothelial BCa",0.0,
99d4770c7afe60cc5020bc42784b9f2b8cd2b903,10.26689/pbes.v7i6.9103,Analysis and Evaluation of Housing Price Factors Using Mathematical Modeling,2024.0,Proceedings of Business and Economic Studies,Xing Lyu,"In recent years, the real estate industry has achieved significant progress, driving the development of related sectors and playing a crucial role in economic growth. However, rapid real estate market expansion has led to challenges, particularly concerning housing prices, which have drawn widespread societal attention. This article explores the theories of housing prices, analyzes factors influencing them, and conducts an empirical investigation of the impact of representative factors on ordinary residential prices. Using regression analysis and the entropy weight method, a mathematical model was developed to examine how various factors affect housing prices.",0.0,https://ojs.bbwpublisher.com/index.php/PBES/article/download/9103/7925
b530585da005aa141536452bf13929251edaf4ac,10.2478/sbe-2022-0006,"Are The Effect of Housing Prices on Bank Performance Different Among Korean Commercial, Regional and Specialized Banks?",2022.0,Studies in Business and Economics,Jung Heonyong,"Abstract This study analyzes the effect of housing prices on banking performance in Korea. The findings of the study reveal that the impact of housing price changes on banking performance was different in the commercial banks, regional banks and specialized banks. This seems to be due to the different characteristics of each bank. The three types of banks in Korea have different functions, and thus the impact of changes in housing prices on their respective banking performance is different. Therefore, it would be desirable for Korea’s financial regulatory authorities to draw up policies and perform its supervisory functions in consideration of these points.",0.0,https://sciendo.com/pdf/10.2478/sbe-2022-0006
470bbc1749f2b0f1a7c981aec65f94ab1e1a7301,10.12783/dtem/icem2019/31233,Analysis of Residential Space Structure Based on Commercial Housing Price in Central Urban Area of Linyi,2019.0,DEStech Transactions on Economics Business and Management,Jin-yi Wu,"Taking the central urban area of Linyi as study area, the average selling price of 134 commercial residential projects for sale in March and April 2019 are collected. Kriging spatial interpolation method is used to analyze the spatial distribution characteristics of housing prices in the study area. On this basis, the paper analyzes the structural characteristics and formation mechanisms of the residential space. This paper state that the formation and development of residential space has historical continuity and is significantly influenced by policy factors. The market mechanism plays an important role in the adjustment of urban residential space, too.",0.0,https://doi.org/10.12783/dtem/icem2019/31233
85bf62773c26cf137b11eefe22a6e070131263b3,10.22313/reik.2022.20.4.01,A study on the real estate market after a pandemic such as COVID-19: Focused on the impact on housing prices,2022.0,Residential Environment Institute Of Korea,J. Park; Han Sung Joo,"The purpose of this study is to examine whether infectious diseases such as H1N1 flu, MERS, and COVID-19 affect housing prices, and to analyze how the money supply and interest rates at the time of each epidemic affect housing prices, using a fixed-effects model. was used. The implications of this study are First, this study has great implications at this point in that there are few previous studies on the relationship between infectious diseases such as COVID-19 and housing prices, and there is no empirical analysis. Second, this study was possible because panel data combining cross-sectional data and time series data were constructed, and macroeconomic and regional characteristics through the era of infectious diseases could be reflected. In conclusion, the impact of post-COVID-19 epidemics on house prices, such as COVID-19, was found to be different in the metropolitan area and Seoul. It was judged that the new flu had a positive impact on the metropolitan area, but had a negative impact on house prices in Busan, Ulsan, and Gyeongnam. It is judged that COVID-19 has had a positive impact on the metropolitan area, Busan, Ulsan, and Gyeongnam.",0.0,
ebc8506bb3a1757d19f55cc692861f52c150be11,10.1109/icccnt61001.2024.10724138,"Property Price Estimation Using Machine learning and implementing a website using HTML, CSS, and JavaScript",2024.0,International Conference on Computing Communication and Networking Technologies,Naga Swathi Nidamanuru; K. Rajesh; U. Srinivasarao; Kalpana Koppolu; Kola Balavani; Mogadala Vinod Kumar,"Property price estimation uses various kinds of algorithms in Machine Learning like linear regression, lasso, and decision tree that best predict the house prices with the highest accuracy. In this paper, we use various machine learning algorithms to build a model that predicts the house prices based on the requirements like location, area, number of bedrooms, and no of bathrooms. A Huge set of data on housing prices is trained for various attributes to create an algorithmic model. To better understand the links between the several housing qualities and the selling prices, we will do exploratory data analysis (EDA), which entails visualizing the data and discovering patterns and trends that help to develop the prediction model. Data pre-processing and data cleaning is done before creating the model. We build a linear regression model, and we compare it with the other machine learning algorithms like lasso regression and classification and regression tree algorithms and use the one that yields high accuracy. The tested model is imported through a pickle file and a Flask server is used for developing the website using HTML, CSS, and JavaScript.",0.0,
b39b4c23d0acb47a2232a9a866be9f970bc75804,10.48550/arxiv.2602.00668,NCP: Neighborhood-Preserving Non-Uniform Circle Packing for Visualization,2026.0,Computational Visual Media,Duan Li; Jun Yuan; Xinyuan Guo; Xiting Wang; Yang Liu; Wei-Kai Yang; Shixia Liu,"Circle packing is widely used in visualization due to its aesthetic appeal and simplicity, particularly in tasks where the spatial arrangement and relationships between data are of interest, such as understanding proximity relationships (e.g., images with categories) or analyzing quantitative data (e.g., housing prices). Many applications require preserving neighborhood relationships while encoding a quantitative attribute using radii for data analysis. To meet these two requirements simultaneously, we present a neighborhood-preserving non-uniform circle packing method, NCP. This method preserves neighborhood relationships between the data represented by non-uniform circles to comprehensively analyze similar data and an attribute of interest. We formulate neighborhood-preserving non-uniform circle packing as a planar graph embedding problem based on the circle packing theorem. This formulation leads to a non-convex optimization problem, which can be solved by the continuation method. We conduct a quantitative evaluation and present two use cases to demonstrate that our NCP method can effectively generate non-uniform circle packing results.",0.0,
822f2e4de6299cd0faedf698797babe36d74961b,10.1109/icsm64417.2025.11541401,Performance Analysis of Deep Learning Architectures for Furnishing Status Classification,2025.0,International Conference on Smart Multimedia,Oguzhan Guclu; Muhammet Guven; Irem Islek; Çagla Çig Karaman,"The online real estate market has experienced substantial growth, with many platforms featuring listings for both rental and sale properties. A critical detail for customers is whether a property is furnished or unfurnished. Currently, this information relies heavily on user-provided descriptions and manual review, which can be time-consuming and prone to inconsistency. Automating the assessment of a property’s furnishing status using visual data from listing images offers considerable advantages for both users and platforms, including enhanced search efficiency and reliability. This study explores the use of transfer learning with deep learning algorithms to address the challenge of automatically classifying property listings by furnishing status from images. We investigate and compare the fine-tuning performance of several deep learning architectures, including ResNet, EfficientNet V2, ConViT, Swin Transformer V2, and ConvNeXt V2, for furnishing status classification. Experimental results demonstrate that Swin Transformer V2 achieves the highest classification performance, effectively capturing both local and global image dependencies.",0.0,
286d87e9dd7fb8d8425f935de9bb4d24cabb83e6,10.1109/cisct62494.2024.11134193,House Price Prediction System Using Bagging Based Ensemble Learning,2024.0,2024 4th International Conference on Innovative Sustainable Computational Technologies (CISCT),V. Gupta; Vidisha; H. Tiwari; Jyoti; Shubhani Aggarwal; A. Dwivedi,"One of the busiest and most vital sectors of any economy is the real estate sector. It is crucial for investors, buyers, sellers, and policymakers to have a precise estimate of home values. This article explains how the creation of numerous advanced machine learning models can be utilized to predict home values. Prediction is made using the most popular models, the most favored datasets, the most instructive features, and the proper evaluation procedures. Size, location, market conditions, and economic conditions are just a few of the physical and nonphysical aspects that make it difficult to accurately predict home prices. Real estate professionals, banks, and government agencies can now analyze trends and create complex models to forecast housing prices more accurately than they could with traditional analytical models thanks to digital advancements, particularly the use of machine learning in the housing sector. Using bagging-based ensemble learning, five machine learning models are hybridized to predict accuracy. In terms of correlation, R-squared, RMSE, and accuracy, our suggested ensemble model is outperforming the current model.",0.0,
b140c7964c3ca35e954555871fa688c7bef2442b,10.55041/ijsrem41722,A Self-Attention-Driven Deep Learning Framework for House Price Prediction Using Multimodal Data,2025.0,INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT,A. Pujitha,"- House price prediction remains a critical challenge in the real estate domain, requiring the consideration of diverse factors that influence housing prices. Traditional models often fail to capture the intricate relationships between these factors, resulting in limited predictive accuracy. To address this, we propose an end-to-end Joint Self-Attention Mechanism for house price prediction, integrating public facility data (e.g., parks, schools, transit) and satellite imagery to assess environmental contexts. Our approach emphasizes the identification of critical features and their interactions, enabling the discovery of complex spatial and contextual relationships.By combining the Joint Self-Attention Mechanism with Spatial Transformer Networks (STN), we aim to establish a robust and precise framework for understanding housing market dynamics. This innovative methodology introduces a new perspective on integrating spatial and contextual data for more informed and reliable house price predictions.

Key Words:  House Price Prediction, Joint Self-attention Mechanism, Heterogeneous Data, Google Satellite Map ,Spatial Transformer Network",0.0,
62317cf6ab2230712e445f726fcf7f11254c7f83,10.9734/bpi/mpebm/v5/11770d,Determination of Residents’ Perception on Health and Residential Value from Telecommunication Tower,2021.0,"Modern Perspectives in Economics, Business and Management Vol. 5",Norazmawati Md. Sani; A. F. L. bin Abdullah; Kai-Xin Tay,"In last decades, due to the cellular phone systems and the rapid increase in the number of users of cellular phones, a growing concern about the possible health hazards has increased among public and scientists, particularly exposure to Electromagnetic Field (EMFs). The objectives of this research are to determine the residents’ perceptions on the health impacts of telecommunication base stations in Malaysia and to examine its impacts on property value. Data from a face-to-face survey conducted in all states of Malaysia (N=509). The respondents were required to complete a standardized questionnaire that focused on the relevant psychological and psychobiological reactions measurement. Stata Software was used for statistical analysis using the Chi-square test with Fisher’s exact and binomial logistic regression. The result shows that only one health symptom headache was statistically significant for both residents who live near to base station ( 300m). The findings reveal that appearance of telecommunication tower is not influence the property price except one health symptom fatigue. The recommendations are also outlined in this paper.",0.0,
77de5ccae8ed1afded10068ecc9afe3ef8d498c6,10.1177/01640275241279922,Preferences for Features of Current and Future Residential Environments Among Korean Middle-Aged Adults,2024.0,Research on Aging,Eunju Lee; M. Huo; Kyungmin Kim,"This study examined differences in middle-aged adults’ preferred features of their current versus future residential environments and how these differences varied by health and social characteristics. A sample of 1,651 Korean middle-aged adults (aged 49–64) rated their preferences for each of 12 features (e.g., proximity to family/relatives, house price) regarding current and future residential environments, separately. Respondents considered “accessibility to health services” and “opportunity for leisure activities” more important for future residential environments than for current ones. Respondents with poorer health considered features that help them compensate for health decline more important, while those who contacted friends/neighbors more frequently and participated in more cultural activities considered features that help them maintain their social interactions more important for future residential environments than the past. Our findings identified middle-aged adults’ various demands for residential features after retirement, which reflect their strategic reactions to future needs for successful adaptation in later years.",0.0,
c144b800a70b8ccb565241b893fce7c9588079c8,10.3828/jtep.2024.58.4.357,"Driving Restrictions and Housing Prices: Evidence from the First Bridge and Tunnel Restriction in Chongqing, China",2024.0,Journal of Transport Economics and Policy,Xiao Jin,"This paper examines the impact of bridge and tunnel driving restrictions in Chongqing, China on urban housing prices. Using a spatial difference-in-difference method, it finds a 2.7 per cent decrease in housing prices within a 7 km radius of restricted areas due to higher commuting costs caused by driving restrictions. This decline is attributed to an increase in supply and a decrease in demand for nearby second-hand houses. Improving public transport, such as light rail and buses, can mitigate the rising commuting expenses resulting from driving restrictions, thereby alleviating the negative effects on housing prices near restricted areas.",0.0,https://doi.org/10.2139/ssrn.4602177
47a5ab840d2059b1fcd9def4db5b3172baaa9aaa,10.1109/iccrtee64519.2025.11053010,Feature Driven Property Valuation Using Machine Learning,2025.0,"2025 International Conference on Computational Robotics, Testing and Engineering Evaluation (ICCRTEE)",K. S; Keshore T; S. M; Sathya Selvaraj Sinnasamy,"Buying and selling a house is a big deal and the price should always be correct. Traditional methods of valuation have a huge time-factor, human discretion-driven. In this project to fulfil the need of the time more precisely and data-driven ""Property Valuation using ML"" We use state-of-the-art AI methods for better and more accurate prediction of house prices. In terms of the price prediction, we use XGBoost as it is very strong in the gradient boosting algorithm and Generative Adversarial Networks (GAN) to produce extra data in order to validate our models. The dataset goes through a large preprocessing, including feature engineering, normalization and imputation to make sure that we get good inputs for training. Together with our model, generalization error gets smaller and reduces the prediction error by achieving better generalization from real data to synthetic. This approach removes human bias, speeds up the valuation process, and makes real estate pricing more transparent. Whether for homebuyers, sellers, or financial institutions, our system provides a smart and efficient way to determine property values with confidence.",0.0,
88810f593245617237f571c090132be4395244a5,10.51505/ijebmr.2026.10501,Using the Granger Causality Test to Examine Whether Economic Policy Uncertainty Has a Significant Impact on Social Housing Rents,2026.0,"International journal of economics, business and management research",Jeng Ying Shieh; Yu-Te Su,"Granger causality can decompose the relationships among variables into multiple independent regression equations to examine the “correlation” between the current value of one variable and the past values of other variables. This study uses Granger causality tests to explore whether economic policy uncertainty has a significant impact on rents in the social housing market. Issues such as excessively high housing prices, a high vacancy rate, and insufficient transparency in the rental market are currently occurring in Taiwan’s housing market. Since 2011, the R.O.C. (Taiwan) government has promoted a policy of renting and not selling social housing, and through related plans, it has assisted socio-economically disadvantaged households to rent housing. This study is based on the real options valuation model, assuming that the value of privately owned social housing follows a geometric Brownian motion. It proposes a related valuation model, conducts sensitivity analysis, and further employs the Granger causality test to examine whether economic policy uncertainty has a significant impact on rents in the social housing market.",0.0,
e9a42515b3a50e17076b2408a1b813309c326c4b,10.15611/pn.2022.4.09,Monetary determinants of house prices in Central and Eastern European countries,2022.0,Prace Naukowe Uniwersytetu Ekonomicznego we Wrocławiu,V. Shevchuk,"
 This research aimed at the empirical estimation of the monetary determinants of house prices in the Czech Republic, Hungary, Poland, and Romania. The application of quarterly panel data for the period 2010-2019 indicates that a central bank policy rate increase was responsible for the fall in house prices, with a similar effect on house prices by a higher consumer inflation and nominal (real) exchange rate undervaluation. There was no reaction of house prices to the business cycle. However, the housing boom had a positive contribution to cyclical changes in output, while not affecting consumer prices and exchange rate.
",0.0,http://dbc.wroc.pl/Content/118515/Shevchuk_Monetary_determinants_of_house_prices.pdf
3006871c0722c665abc1eaa6cef565b495ba32a0,10.15864/ajec.2104,ANALYSIS ON THE STATUS OF RENT OF HOUSING INDUSTRY,2021.0,American Journal of Electronics & Communication,Madhulekha Hazra; Bikram Bhattacharya; Suryasish Sengupta; R. Mandal; Poojarini Mitra; Kaustuv Bhattacharjee; Anirban Das,"
 Abstract - Machine learning has been playing an active role in the past few years in several applications like image detection, spam reorganization, recommending products and in medical fields. Present machine learning algorithm helps us in enhancing security alerts, ensuring
 public safety and improve medical enhancements. Determining the sale price of the house is very important nowadays as the price of the land and price of the house increases every year. So our future generation needs a simple technique to predict the house price in future. The price of house
 helps the buyer to know the cost price of the house and also the right time to buy it. The right price of the house helps the customer to elect the house and go for the bidding of that house. There are several factors that affect the price of the house such as the physical condition, location,
 landmark etc. Our result exhibit that our approach to the issue needs to be successful, and can process predictions that would be comparative with other house rent prediction models. This paper uses linear regression technique to predict the house price.
",0.0,
517328cc00204398a833af777b4e47fdd205438d,10.37407/kres.2023.41.2.131,Can Housing Hedge Against Inflation?,2023.0,Korea Real Estate Society,Chasoon Choi,"This paper examines the inflation hedging capacity of Korea’s housing return from January 1987 to December 2022. The exponential generalized autoregressive conditiuonal heteroskedasticity(EGARCH) model and a dynamic ordinary least squares (DOLS) regression were employed to study the hedging capacity of Korea’s housing return against expected and unexpected inflation over the short run and long run. The results that could be obtained through this paper is as follows. First, The empirical results show a hedge effect on expected inflation only in housing return excluding gold over the short term, but not in unexpected inflation. Second, Over the long run, housing and gold returns provide a positive inflation hedge against expected inflation only. Third, it is found that the price volatility of housing and gold have both a positive asymmetric effect on news shocks. Over the long run, an increase in wages is found to increase housing prices by promoting housing demand, While no similar evidence is found in money supply.Therefore, there is a need to implement a stable wage policy to stabilize the housing market.",0.0,
5f905f2ca6a694a3bb7f93c6905fd62b4d3e2df9,10.1109/amlds63918.2025.11159400,Machine Learning Engine for Real Estate Price Estimation,2025.0,2025 International Conference on Advanced Machine Learning and Data Science (AMLDS),Abdul-Rahman Mawlood-Yunis; Youssef Roman,"Accurate price estimation is crucial for informed decision-making in the real estate industry. This study explores machine learning (ML) methods for predicting housing prices in Ontario’s Halton Region from 2022 to 2023, using a dataset of over 7,000 detached home transactions. Data preprocessing involved feature engineering, including economic indicators like prime rates. Exploratory data analysis revealed transaction patterns and market shifts linked to interest rate changes.ML techniques, including linear regression, Random Forest, and XGBoost, were employed, with models achieving R-squared values between 0.93 and 0.997. Decision Tree and Random Forest models were the most effective in capturing price variability. Additionally, a Flask-Based price estimation tool was developed, and trained on several regions of the Greater Toronto Area (GTA) allowing users to predict home prices based on specific property features.The study demonstrates the value of ML in enhancing real estate market efficiency by providing reliable price predictions, benefiting stakeholders such as homebuyers, sellers, and investors.",0.0,
7c4dacb72d739297f840d937375d5317500d4937,10.47772/ijriss.2025.90300195,Urban Regeneration and Housing Market Dynamics: Examining the Impact of Brownfield Sites in Malaysia,2025.0,International journal of research and innovation in social science,Aida Julia Aminuddin; Nurul Hana Adi Maimun; N. Zihannudin; S. Eni; Umussaa’dah Adam,"Urban regeneration efforts often face significant challenges due to the presence of brownfield sites, which pose financial, administrative, and policy issues. These sites can lead to negative environmental and social impacts, reducing the appeal and value of nearby properties. Due to the limited market evidence in Malaysia, this study investigates the impact of brownfield sites on house prices in Johor Bahru using a Multiple Regression Analysis (MRA) model. The research identifies key factors influencing house prices, including proximity to brownfield sites, and examines 691 housing observations over ten years. Results show no significant impact of an abandoned apartment building on house prices, suggesting that distance from certain brownfield sites may not deter buyers. These findings are valuable for property market stakeholders and urban planners, offering insights for future urban regeneration projects. Future research could explore other types of brownfield sites and employ more precise distance measures to understand their impact on the housing market further, supporting urban regeneration goals.",0.0,
85e04b4c15bf8e51f1bf42ddad8c2a5de0ff1b20,10.1108/dta-12-2022-0461,Measuring land lot shapes for property valuation,2023.0,Data Technologies and Applications,Changro Lee,"PurposeUnstructured data such as images have defied usage in property valuation for a long time. Instead, structured data in tabular format are commonly employed to estimate property prices. This study attempts to quantify the shape of land lots and uses the resultant output as an input variable for subsequent land valuation models.Design/methodology/approachImagery data containing land lot shapes are fed into a convolutional neural network, and the shape of land lots is classified into two categories, regular and irregular-shaped. Then, the intermediate output (regularity score) is utilized in four downstream models to estimate land prices: random forest, gradient boosting, support vector machine and regression models.FindingsQuantification of the land lot shapes and their exploitation in valuation led to an improvement in the predictive accuracy for all subsequent models.Originality/valueThe study findings are expected to promote the adoption of elusive price determinants such as the shape of a land lot, appearance of a house and the landscape of a neighborhood in property appraisal practices.",0.0,
9f6da5b708a04de55ca9657526447d0fe1e9ceab,10.1109/aece67531.2025.11386719,Real Estate Price Prediction Using Machine Learning: A Comparative Analysis with Stacking Regressor,2025.0,2025 5th International Conference on Advancement in Electronics & Communication Engineering (AECE),Richa Sharma; Sarath Chandra K Venkata Nageshwara; G. Srujana; C. Ramasubramanian; Saurabh Kumar; Ravi Kumar,"This paper is dedicated to the real estate price prediction and its importance and the methods used. It provides a systematic framework to the researchers and practitioners and direct them on factors that influence the housing prices and suggest the appropriate machine learning models. The study commences by first importing the necessary Python libraries, loading a real estate data set and conducting intensive data cleaning to accommodate missing values and outliers. Exploratory data analysis exposes important understanding of determinants of housing prices. Following the division of the dataset, the different machine learning models are trained and assessed by using the metrics like Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE). The Stacking Regressor becomes the best performing model with the lowest RMSE, and this is selected as the final model, which secures the correct pricing predictions of the property in the dynamic real estate environment. In this study, the dataset of Indian residential property of Kaggle is used, which consists of 14,621 rows and $\mathbf{2 3}$ columns.",0.0,
e48761f612a6bfa4416c40bde08347bf1b4ba45f,10.1145/3345035.3345093,Prediction of the Impact of Comprehensive Property Tax on Local Fiscal Revenue: Take Chongqing as an Example,2019.0,ICEME,Yuan Fu; Gui Ye,"Tax is an important support of local financial revenue. In recent years, with the rapid development of the real estate industry, the potential tax revenue of high housing prices has aroused wide attention of policymakers. Previous studies have shown that levying real estate tax has a good moderating effect on housing prices for a period of time, and can increase local fiscal revenue to a certain extent. This paper will take Chongqing as an example to predict and analyze the impact of the levy of property tax in 2020 on local fiscal revenue. In this paper, unary linear regression model is selected to calculate the price of urban residential commercial housing in Chongqing city in 2020. Based on the urban per capita residential area of 2008-2015 years in Chongqing, the grey system model is utilized to predict the per capita residential area of Chongqing cities and towns in 2020. Eventually, considering the time value of funds, the proportion of real estate tax revenue to the fiscal revenue of the year is measured, and the impact of comprehensive property tax on local fiscal revenue is evaluated.",0.0,
968c937f599499f6658e09a79495afc0aabdce83,10.1108/978-1-83909-936-620211002,Housing-price Convergence among Cities in China: Absolute or Conditional?,2021.0,,M. Fung; A. Cheng,"If the only difference between cities lies in their initial housing prices, the initially lower-price cities should eventually catch up with the initially higher-price ones, i.e., “absolute convergence.” Alternatively, if the major determinants of housing prices are city-specific, cities will converge to parallel growth paths of housing prices, i.e., “conditional convergence.” This study tests for the existence of absolute and conditional convergence in house prices among cities in China. The strong evidence for conditional convergence suggests that each city possesses its own steady-state housing price to which it is converging, which depends on the city's own socio-economic characteristics. In other words, differences in these socio-economic characteristics among cities can create permanent differences in housing price among them. The differences in steady-states house price across cities reflect differences in the level of socio-economic development among them. The findings inform the kinds of interventions and resources that are most likely to be effective in reducing income disparity.",0.0,
37c5cbfcb0500c5b1eab3b3a22beb8e88d00a500,10.1109/icares64249.2024.10768046,House Price Modeling in DKI Jakarta: A Web-Based Comparative Study of Spatial Models,2024.0,2024 IEEE International Conference on Aerospace Electronics and Remote Sensing Technology (ICARES),Sevien; A. A. S. Gunawan; Margaretha Ohyver,"A house is a fundamental need for individuals. House sellers can easily determine the market price of their property using the NJOP formula, which is used in the calculation of Land and Building Tax (PBB). However, for buyers, determining a fair market price for a house can be challenging. As a result, it is common for buyers to purchase a house at a price higher than its fair market value. Therefore, this study aims to determine the attributes of a house that affect the price of a house but also considering the spatial value of the location of the district of the house by comparing Spatial Autoregressive Model with Spatial Error Model. We concluded that the SEM model, characterized by the highest $\mathbf{R}^{2}$ and the lowest AIC and BIC values, is identified as the best fit for the dataset. Furthermore, we embedded the house predicting models in a web application, making it easier for the public to determine the price of the house they want to purchase while also assisting property companies in planning future housing development strategies to generate maximum and sustainable profits.",0.0,
560cc2aad97f92ece603764092f3d9d1c5e7701a,10.22423/kreus.2024.17.1.61,An Empirical Study on the Impact of Upzoning on House Prices: Focusing on the Naebang Station Intersection in Seoul,2024.0,Konkuk Research Institute of Real Estate and Urban Studies,Won-Joon Choi; Seong-won Lee,"This study uses the Differences-in-Differences (DID) method to examine the impact of upzoning announcements on house prices near Naebang Station. Data were analyzed using two models: apartments and townhouse & multi-family based on Chow Test result. We find that the upzoning announcement significantly increased house prices within 200 meters of Naebang Station upzoning area with statistically significant rises for townhouses and multi-family units, suggesting a positive externality. Apartments did not show significant effects, however we found significant price rise for townhouse and multi-family units due to substantial future development potential. Housing redevelopment projects also statistically significantly impacted house prices and there is much greater price increase in the redevelopment project. These findings highlight the need for policy-makers to anticipate varied market responses to rezoning initiatives and tailor policies to different housing types and neighborhood characteristics, contributing to a better understanding of upzoning policy impacts on housing markets.",0.0,
30c13b2803c76a66019467a953d0a48e26a88320,10.54691/bcpbm.v32i.2966,The Impact of Household Structure and Urban Agglomeration on Real Estate Prices in California,2022.0,BCP Business &amp; Management,Hua Zhou,"The purpose of this paper is to study the impact of regional economic and demographic factors on real estate prices and provide a theoretical basis for policy makers. The first section examines the economic traits of California in the 1990s and reveals a significant urbanization agglomeration impact. Through the use of linear regression, the data analysis model is further developed to examine the reasons for regional variances in home prices. The frequency of numerous families, small family sizes, and the concentration of big cities are proven to have a significant impact on housing costs.",0.0,https://bcpublication.org/index.php/BM/article/download/2966/2927
30f2d71cfd0ad7302b6c3b52a245960f88f8f459,10.1177/10780874251412356,Local Economic Development Policies and Market Effects: Policy Impacts in the land of OZ,2026.0,Urban Affairs Review,Brent C Smith,"The central objective of many place-based economic development policies is to incentivize private sector investment in areas that would otherwise be overlooked or underserved by market forces due to perceived risks, lack of infrastructure, or insufficient expected returns. One such policy in the United States, opportunity zones (OZs), provides tax incentives, in the form of deferred/eliminated capital gains taxes, to deliberately redirect real estate investments into targeted geographic areas. This analysis explores the effects of OZs on property values by using a nuanced approach that recognizes the operative word “place,” or proximity, along with time. This is essential to represent the diversity across OZ designated census tracts, and to compare property performance within designated OZs when compared to the entire market. Relying on a series of hierarchical linear equations, corrected for selection bias, the results indicate there are significant positive price effects in OZ tracts, for office, industrial and multifamily real estate, when compared against the larger market.",0.0,
25b76703ef4353ffa81fc66324eb936bff081adb,10.24957/hsr.2026.34.2.63,Residence in Social-Mix Housing Complexes and Fertility Intentions among Public Housing Residents: A Multilevel Analysis and the Moderating Effect of Local Housing Prices in Seoul,2026.0,Korean Association for Housing Policy Studies,Jisu Jeong; Hee-Jung Jun,"This study examines the impact of residence in social-mix housing complexes on fertility intentions among public housing residents. Fertility decisions are shaped not only by individual characteristics but also by the socio-economic conditions of the communities in which individuals reside. Accordingly, this study applies multilevel logistic regression models that consider both individual-level and local factors. The results show that residents of social-mix housing complexes exhibit higher fertility intentions than those living in stand-alone public housing complexes. However, this positive effect is not spatially uniform and is statistically significant only in Seoul districts with mid-range housing prices. These findings suggest that mixed-income housing development can function as a supportive residential environment for fertility intentions when a certain level of living conditions and social stability is present, and highlight the importance of considering both housing supply structures and local contexts in designing housing welfare policies to address low fertility.",0.0,
cfb3b5e0249529fa43ef955d763098f7399fd928,10.22617/wps250202-2,Evidence on the Determinants and Variation of Idiosyncratic Risk in Housing Markets,2025.0,,Lydia Cheung; Jaqueson K. Galimberti; P. Vermeulen,"This paper shows that housing idiosyncratic risk is time-varying, depends negatively on the house price, varies across locations, and decreases with the holding period. These systematic movements can be associated with information quality and offsetting factors in credit supply. While higher interest rates are associated with reduced idiosyncratic pricing, tighter deposit requirements are associated with higher risk. Idiosyncratic risk is positively associated with excess returns only through risk differences across house prices and holding periods, and not across time and regions.",0.0,https://doi.org/10.22617/wps250202-2
5b3ac2d2587dc0de26e9972ecbcd2dca48392ce6,10.33642/jhsspp.v6n1p1,Exploring Determinants of Housing Price Index in the Saudi economy,2024.0,International Journal of Social Science and Public Policy,Dirar Elmahi Elobaid Ahmed; R. Abdalla; Fayga Hussein Ballal Aawad,"Different macroeconomic factors affect the housing price index. In this study, the Saudi Arabian gross domestic product per capita and the consumer price index are two determinants that are examined using the Vector Error Correction Model (VECM). The analysis discovered two co-integration correlations between the three variables. Over time, consumer prices have a favorable effect. The three variables seem to mutually promote one another over the long run. Future studies in the area should investigate additional monetary and fiscal variables that might affect Saudi house prices.",0.0,http://ijssppnet.com/file/Rehab Abdelrahman Osman .pdf
4103c10395defa6d56d6fc9af4ec3d16114978aa,10.1109/icaice51518.2020.00079,Application of Combined Neural Network Based on Entropy Method in Smart City Forecast Problem,2020.0,2020 International Conference on Artificial Intelligence and Computer Engineering (ICAICE),Chun-Hong Zhang; Jiankai Zuo; Yunai Wu; Jia Zhang; Jing Liu; Xinyuan Chang,"With the continuous development of the national big data strategy and the construction of ""Digital China"", cities have been given new connotations and requirements. This paper takes the real estate price changes in Hainan Province as the background, collects relevant information and data, and makes relevant analysis and reasonable predictions for the housing price changes in Hainan Province. This paper comprehensively considers the prediction defects of MEA_BP neural network, Elman neural network and Wavelet neural network, and uses a combination algorithm based on entropy method to comprehensively consider the results of all prediction models. On the one hand, it can improve the prediction accuracy of the model, and on the other hand, it can reduce the sensitivity of the prediction results to changes in a certain factor, making the prediction results more reliable. This paper establishes a multiple and effective new era smart city prediction model, which provides a reference for building a new city database supported by a new generation of information technology.",0.0,
e6c8114a481642251b2d760b2e255df9f0fc4d1f,10.1080/13547860.2022.2116884,What affects the fraction of collateral-constrained households in the housing market? The case of Taiwan,2022.0,Journal of the Asia Pacific Economy,Shiou-Yen Chu,"Abstract This research develops a Two-Agent New Keynesian (TANK) framework with household type switching to investigate the determinants of a time-varying fraction of collateral-constrained households. As a practical application, the model is estimated with Taiwanese data via Bayesian methods. We first validate our model to fit the business cycle properties of Taiwan during 2008Q1–2019Q4 and analyze the dynamics of the fraction of collateral-constrained households in responses to preference shocks, sectoral productivity shocks and interest rate shocks. The results indicate that the fraction of collateral-constrained households increases with higher output growth, more housing consumption, higher interest rates and higher expected housing prices. Our findings affirm that collateral-constrained households are generally more sensitive to income changes than interest rate changes. They also imply that maintaining a fairly reasonable property price can ensure an adequate fraction of collateral-constrained households as well as stabilize the housing market in Taiwan.",0.0,
d62d375ffe318c6b8bc2f3bf185a6c922f3b2ca5,10.1016/j.qref.2019.01.015,"Subprime credit, idiosyncratic risk, and foreclosures",2019.0,Quarterly Review of Economics and Finance,Prodosh E. Simlai,"Abstract In this paper, we look at the determinants of foreclosure rates with particular attention to measures such as household leverage, which is related to subprime credit population, and idiosyncratic risk, which utilizes a spatial delineation of housing submarkets. We use county-level data from the state of California and provide a number of important findings regarding the determinants of foreclosures across housing submarkets. We find a significant negative relationship between foreclosures and both housing price growth and idiosyncratic risk, and a positive relationship between foreclosures and household leverage. These relationships persist even after we control for state variables such as tech pulse, mortgage rate spread, median household income, and unemployment rate. We show a breakdown of the cross-sectional variability of foreclosure rates by allowing a two-way sorting of the counties using housing price growth and idiosyncratic risk. The idiosyncratic risk measure reemphasizes the translation of leverage-induced shocks into foreclosure rates.",0.0,
c2b6a75d94d2ce27d185f96ffbc7fa5ee377ffff,10.65164/zrcja795,AN INTERPRETABLE ANALYSIS OF RESIDENTIAL APARTMENT PRICES IN TASHKENT USING LINEAR REGRESSION,2025.0,III-an’anaviy xalqaro ilmiy-amaliy konferensiya materiallari,Abdurasul Bobonazarov,"Accurate understanding of residential housing price formation is essential for urban planning, real estate market transparency, and informed decision-making by buyers and sellers. In recent years, online real estate platforms have emerged as valuable sources of large-scale market data; however, empirical studies based on local housing data in Uzbekistan remain limited. This paper presents an interpretable analysis of residential apartment prices in Tashkent using multiple linear regression applied to real listing data collected from an online real estate platform.",0.0,https://science-utas.org/index.php/confofutas/article/download/123/127
3dffa9c45da02f5e8e61799f5d4d86ea1cf1bf27,10.22423/kreus.2022.15.1.49,A Panel Data Analysis of Housing Tenure Choice Decision of Millennials,2022.0,Konkuk Research Institute of Real Estate and Urban Studies,Ui-Chung Jeong; Eui-chul Chung,"This study examines the determinants of housing tenure choice decisions of Millennials. 
Using KLIPS panel data from 2014 to 2020, a correlated random effects probit model and a fixed effects logit model were estimated to control for endogeneity problem associated with time-invariant unobserved heterogeneity. Estimation results showed that net wealth, relative housing cost, marital status of household heads were major determinants of housing tenure choice decisions. Permanent income, one of key variables on the housing tenure choice, was not significant, indicating that net wealth rather than income is more important to homeownership decisions of Millennials. However, the effect of net wealth on the probability of home owning was estimated to decrease over the observation period because the increase in net wealth could not catch up with the rise of housing price. A sharp decrease of the effect of net wealth on the probability of home owning in recent years was attributable to a dramatic increase in housing price and more stringent mortgage regulations.",0.0,
82ef25545f39729d8b996e3f09c0cb6f9f887ffa,10.1109/icatc68823.2025.11407866,House Price Prediction for Sri Lanka Using Machine Learning : A Comparative Study of Algorithms,2025.0,2025 International Conference on Advances in Technology and Computing (ICATC),D. D. Melroy,Machine Learning ML has become increasingly prevalent across various domains revolutionizing tasks such as speech recognition product recommendations and predictive modeling Its applications extend to enhancing customer services and ensuring data driven decision making. In this study we propose the application of ML techniques for predicting housing prices in Sri Lanka aiming to reduce uncertainty in the volatile real estate market The proposed model analyzes a comprehensive dataset 15327 records 172 features 2015 to 2024 sourced from ikman lk ML algorithms including Linear Regression Decision Tree Regression Random Forest Regression and advanced ensemble methods are evaluated Random Forest Regression achieved the lowest RMSE of 41905267 indicating superior accuracy Feature importance analysis highlights key determinants of housing prices This research provides actionable insights for buyers sellers investors and policymakers facilitating informed real estate decisions Ethical considerations related to data privacy are also discussed it this correct,0.0,
a8ae82e36827d768d2cb4f8068ffddb9b9e4d9fd,10.54254/2755-2721/46/20241300,Prediction of second-hand house prices in Ames city based on data mining,2024.0,Applied and Computational Engineering,Chucheng Zhou,"As the secondary housing market continues to play a vital role in the global real estate industry, there is an increasing demand for accurate and efficient prediction of secondary housing prices. In this study, transaction data from the second-hand housing market in Ames, Iowa, USA, available on the Kaggle website, was utilized. A total of 79 influential feature variables, including Lot Area, Overall Quality, and Year Built, were selected to construct seven different models for predicting secondary housing prices: Linear Regression, Lasso Regression, Ridge Regression, LassoCV, RidgeCV, Random Forest, and Neural Network models. To assess the effectiveness of these models, we utilized a range of evaluation metrics including the R2 score, Mean Absolute Error (MAE), and Mean Squared Error (MSE). The results indicated that the RidgeCV model stood out among the others, displaying the most robust predictive performance with a goodness-of-fit of 90.3%. This discovery holds significant implications for improving the accuracy of secondary housing valuation.",0.0,
a9cf8e3128d8b3ab1c2afb5d5f5f625f3388b0a5,10.1088/1755-1315/608/1/012020,Research on Influencing Factors of Average Sales Price of Residential Commercial Housing in Major Cities of China,2020.0,IOP Conference Series: Earth and Environment,Yu Bai,"Housing prices are closely related to a country’s social stability, political economy, etc., and its fluctuations will also be affected by many factors. This paper collects relevant data from 35 major cities in China over the past ten years to study the effects of changes in different factors on housing prices. It mainly uses multiple regression analysis and panel regression analysis to guide residential sales prices more scientifically and effectively. It is of certain significance to promote the healthy and orderly development of the real estate market.",0.0,https://iopscience.iop.org/article/10.1088/1755-1315/608/1/012020/pdf
2d07e94774bf286ecdd5b575b99db7e22122954b,10.1111/kykl.70082,Anti‐Money Laundering Regulations and House Prices in OECD Countries,2026.0,Kyklos (Basel),Hassan F. Gholipour; Mohammed N. Abu-Alfoul; Elias Oikarinen,"The debate over the impact of money laundering on real estate prices has become a pressing issue in recent years, particularly in developed economies. The aim of this study is to examine the relationship between anti‐money laundering (AML) regulations and house prices in a sample of OECD countries over the period 2012–2023. Using panel fixed effects, two‐stage least squares (2SLS), and the GMM regressions, while controlling for key macroeconomic determinants of house prices, the findings show that house prices are lower when AML regulations are stronger.",0.0,https://onlinelibrary.wiley.com/doi/pdfdirect/10.1111/kykl.70082
e0c2da83ef0099d7d80f2ee4c5bb0717a87b5e3c,10.22630/mibe.2025.26.3.9,Cyclical Determinants of Regional House Prices in Poland,2025.0,Metody Ilościowe w Badaniach Ekonomicznych,V. Shevchuk,"The aim of the article is to present results of the study on the link between business cycle and house prices in 16 regional capital cities in Poland. Using quarterly data for the period 2010-2024, the study finds that regional business cycle effects on cyclical fluctuations in regional house prices are predominantly positive. Following an increase in the National Bank of Poland (NBP) reference rate, house prices are on a decline in 11 out of 16 regional capital cities. The effects of housing quality and the exchange rate on house prices are ambiguous.  ",0.0,https://qme.sggw.edu.pl/article/download/10698/9233
baf55874e4000184fd5923ca6950e3c3a49fcb7f,10.1108/jeas-12-2020-0218,On the asymmetries created by the Great Recession in the US real estate market,2021.0,,A. D. Fofack; S. D. Temkeng; Clement Oppong,"PurposeThis paper aims at analyzing the asymmetries created by the Great Recession in the US real estate sector.Design/methodology/approachThis paper uses a Markov-switching dynamic regression model in which parameters change when the housing market moves from one regime to the other.FindingsThe results show that the effect of real estate loans, interest rate, quantitative easing and working age population are asymmetric across bull and bear regimes. It is also found that the estimated parameters are larger in bull regime than bear regime, indicating a tendency to create house price bubbles in bull market.Practical implicationsSince three of those asymmetric variables (real estate loans, interest rate and quantitative easing) are related to monetary policy, the Fed can mitigate their impact on an interest-sensitive sector such as housing by engaging in a countercyclical monetary policy.Originality/valueThe estimated intercept and the variance parameter both vary from one regime to the other, thus justifying the use of a regime-dependent model.",0.0,
45491563758e4a1315d33eb518dfe213ac857e75,10.1139/cjce-2022-0097,Quantifying Agricultural Property Value Diminution Due to Upstream Oil and Gas Activities Using Alberta’s Abandoned Well Sites as an Example,2022.0,Canadian journal of civil engineering (Print),Ron J. Thiessen; G. Achari,"There is public perception that agricultural property value in Alberta is negatively affected by abandoned but unreclaimed oil and gas well sites. This exploratory research examines whether a difference in property values exists between those with reclaimed well sites and properties with abandoned but unreclaimed well sites (i.e., reclamation status). A total of 485 property transfer records from the provincial registry and oil and gas well information from an industry database were used in the research. Stepwise, sequential-search regression was applied to derive an optimized set of potential factors and covariates to predict per-acre agricultural property value. Property sale date, residential density, and agricultural land capability class were the covariates. Property location, well type, and reclamation status were the factors. The data analysis did not support the public perception about reclamation status but did confirm property location and the listed covariates as significant predictors of agricultural property value in Alberta.",0.0,
e88843d8526585df3a1fbc287b6a2f0067a5bb5f,10.1109/icih67754.2025.11608689,Improving Housing Price Predictions with Feature Engineering and Ensemble Models,2025.0,2025 IEEE International Conference on Innovate for Humanitarian: Tech Solutions for Global Challenge (ICIH),Shaik Ishrath Banu; A. Rao; Pattan Imran; Garikapati Sai Venkata Narasimha; Y. Lalitha; Nomula Divya,"This study presents a machine learning-based approach for predicting housing prices in the Indian real estate market. Using Kaggle’s India Housing Prices Dataset with 2.5 lakh records and 23 features, we applied feature engineering techniques such as ordinal encoding, one-hot encoding, and derived variables (e.g., property age, price per square foot). Multiple regression algorithms, including Linear Regression, Decision Tree, Random Forest, and XGBoost, were trained and compared. Among them, XGBoost achieved the best performance with an R2 score of 0.992, a Mean Absolute Error (MAE) of 9.87 lakhs, and a Root Mean Squared Error (RMSE) of 13.98 lakhs, outperforming the other models. The proposed framework was deployed as a web service using Flask, Docker, and Render Cloud, enabling real-time housing price predictions. The results indicate that ensemble methods, particularly XGBoost, provide accurate and scalable solutions for property valuation in India, offering valuable insights to real estate agents, investors, banks, and home buyers.",0.0,
5cd221bfcecba5758d5e8330ddd8358c03bac05e,10.5750/jpm.v17i1.2055,Macroeconomic Determinants of Housing Prices in Hong Kong,2023.0,The Journal of Prediction Markets,Simon M. S. So; Frankie S. L. Wan,"This article aimed to study the causal relationship between the housing prices and the macroeconomy in Hong Kong from 1998M1 to 2019M12. We explored both the long-term and short-term causalities between the housing prices, proxied by the Centa-City Index (CCI), and six selected macroeconomic variables. The results indicated the presence of causality between the housing prices and two macroeconomic variables: money supply and exchange rate index. These two variables had an impact on housing prices, regardless of short-term dynamics or long-term equilibrium. While the relationship between money supply and housing prices was found to be bidirectional, the effective exchange rate index Granger caused housing prices only. Additionally, a long-term negative correlation was observed between the housing prices and the interest rates. Our findings may help investors understand the determinants of housing prices in Hong Kong and provide policymakers with some valuable insights on how to introduce fiscal policies to stabilize housing prices.",0.0,
e36ecf152b5247b2d37aeb49876572e753b60079,10.36871/26189976.2026.04-2.016,GROSS REGIONAL PRODUCT (GRP) AS A LEADING INDICATOR OF EXISTING HOUSING PRICES IN CHINESE CITIES: A PANEL DATA ANALYSIS,2026.0,SOFT MEASUREMENTS AND COMPUTING,Jing-Mei Yang; Andrey A. Zaitsev; E. Vlasova,"This study uses panel data from 70 large and medium-sized cities in China for the period 2012–2024. Using a lagged model and robust standard errors clustered by province, we test how well provincial macroeconomic indicators can predict urban housing prices. The study finds that: (1) the provincial GRP growth rate with a one-period lagged value has a significant positive predictive effect on current urban house price growth; this result remains robust when using standard errors clustered at the provincial level; (2) the predictive power of provincial-level population, investment, and income growth is statistically insignificant; (3) after controlling for high multicollinearity among macroeconomic variables, basic multiple regression confirmed that only the provincial GRP growth rate has a highly reliable predictive power. This study demonstrates that the provincial GRP growth rate is an effective macroeconomic signal for predicting urban housing price changes. This confirms the theoretical hypothesis of the expectation anchor.",0.0,
97188e675358af620d898e595a1f5a717488c120,10.2139/ssrn.6109946,Empirical Insights into Systemic Risk: From Housing Boom to Global Financial Crisis,2026.0,Social Science Research Network,Shweta Khosla,"Provides an empirical, econometric analysis of the 2007–08 Global Financial Crisis, examining the roles of monetary policy, global savings imbalances, financial innovation, and housing market dynamics in the buildup and collapse of systemic risk. Applies time-series and multivariate econometric techniques—including regression analysis, stationarity testing, cointegration, and Granger causality—to identify statistically significant drivers of housing price inflation and bubble formation across pre-bubble, bubble, and post-bubble periods",0.0,https://doi.org/10.2139/ssrn.6109946
f28452b78c6d866b474a6f898b4685014c143469,10.1145/3558819.3565221,House Price Prediction Model Using Bridge Memristors Recurrent Neural Network,2022.0,ICCSIE,Wen-Zhao Shi,"In recent decay, the house price prediction plays important role because of it's the volatile of house price which makes significant impact on property valuation and economic growth. It characterizes are attracted the numerous researchers, businessman and people who buy or sell house towards it. The volatile of house price is occurred based on various factors like location, facility, neighborhood, etc. In this way, researchers are evaluating the factors using machine and deep learning process to analysis the information. Although, regression-based analysis has problem due to its nonlinear and linear information in neural network. Thus, we have proposed a novel Bridge Memristors Recurrent Neural Network to forecast the house price prediction in this paper. In addition, RBP algorithm is used on Bridge Memristors RNN for train the neural network in efficient manner. Besides, our proposed model carried out outstanding performance than existing models to attain the high prediction rate by analyzing the correlation coefficient.",0.0,
d0a762907f165883a496e85aac889fa52f2585a5,10.1109/i2ct61223.2024.10543370,A comparative Analyis of House Price Prediction Algorithms,2024.0,2024 IEEE 9th International Conference for Convergence in Technology (I2CT),Rahul Chauhan; Tushar Sharma; Ruchira Rawat; Rudresh Pillai; K. R. Chythanya,"This paper aims to present the implementation of two machine learning algorithms, Linear Regression and Lasso Regression for the task of predicting the price of the house located in the city of Bengaluru, India. The task of predicting house price accurately is quite difficult as it depends on a lot of factors, and needs of the buyer. For predicting these prices, we can try to create datasets which contains details of the factors that people look for while buying Houses such as size, location, bathroom etc. To analyses the data, we can usecertain algorithms such as linear regression, lasso regression etc. By using algorithms like this, we can reduce the margin of error of our model and try to make it more accurate and usable. Such models can be used by real estate agents,sellers as well as the people who want to buy house to get the best deal for them. In future,researcher can also integrate models like this with the real estate's websites like MagicBricks,99Acres to give better and more accurate recommendations to people.",0.0,
5169433946816c1edf68286657af8509d065a708,10.1002/ijfe.3115,Do Mortgage Buy‐To‐Let Investors Pay More or Less for Properties? Empirical Evidence From the UK Residential Market,2025.0,International Journal of Finance &amp; Economics,Panagiotis Petris; George Dotsis; P. Alexakis,"In this paper, we test whether mortgage buy‐to‐let investors buy houses at significantly different prices compared to other buyers. The distinctive characteristic of a mortgage buy‐to‐let transaction is that lenders require the price offered to be explicitly tied to the rental income that the property will be able to generate. To test the existence of a price differential between the two groups of buyers, we use house price data of more than 600,000 residential unit transactions that took place in England and Wales. Using data that span the period 2014–2021, our empirical findings show that mortgage buy‐to‐let investors buy houses at a significantly discounted price (discount of about 4.5%) compared to other buyers. We provide evidence that home price differentials among the two buyer groups are less pronounced in a highly competitive market, such as the London housing market. We also find that the mortgage buy‐to‐let discount was on average higher before the 3% rise in the stamp duty land tax that took place in 2016.",0.0,
ea5400fbdf6c7336c1e6af21c5b023b1bcae03e8,10.3905/jsf.2022.1.133,Shifting Drivers for US House Prices,2022.0,The Journal of Structured Finance,Francis Parisi,"Historically, US house prices track key housing and economic factors such as housing starts, housing inventory, employment, interest rates, and consumer price indices, to name a few. During the past two years, the US economy has gyrated through myriad distortions resulting from the government’s various attempts to control the pandemic. Most recently, the administration has adopted policies that have further disrupted the economy, leading to increases in consumer prices and shortages of goods. We study the potential change in the connection between US house prices and key drivers before and after the onset of the pandemic. We take several approaches to this question, including studying cross-correlations of the multivariate time series, estimating a seasonal ARIMA model, and fitting seemingly unrelated regressions. Finally, we model house prices as a univariate time series. We find some evidence of a change in the association between house prices and other economic measures from before to after the covid response.",0.0,
dbba4bff4f02779c28765158728f08db306afb86,10.54254/2754-1169/15/20230943,The Second-Hand House Price Prediction Using Multiple Linear Regression Model,2023.0,"Advances in Economics, Management and Political Sciences",Yu-Han Jin,"Analyze the influencing factors of second-hand housing and build the relevant model using the data on second-hand housing prices in 2017-2018. The R-code analysis is used to construct a prediction model of house prices, and the main factors affecting their changes are obtained. According to the significance test, the model meets the expectation and is feasible. Finally, it is concluded that the most noticeable impact on housing prices is room distribution and ladder ratio, and the least obvious is trade time.",0.0,https://aemps.ewapublishing.org/media/143aa0f29ffa41b2b20612fcf483f7c8.marked_b77ak00.pdf
7b2c1d470c93d49e39e35b2f116fc8d4160d8553,10.1109/cisce50729.2020.00104,Modeling Regional Interdependence in Business Data Based on Machine Learning Method,2020.0,"2020 International Conference on Communications, Information System and Computer Engineering (CISCE)",Yuheng Zhu,"In the business scenario, the level of product pricing or customer preferences is not only affected by the individual attributes of the product or customer, but also by the interdependency of other products or customers. For example, a customer’s preference may be more similar to its closer neighbor. This research introduces a complete system of models to study the preference interdependency among individual products or customers, so that the matrix for describing interdependence can be introduced into this model. This paper used the general Spatial Autoregressive Regression (SAR) to study these preference interdependency, which cannot be modeled with other standard machine learning methods. Moreover, an improved iterative lasso regression method is introduced to perform variable selection in the presence of interdependence. These models were illustrated by studying factors affecting Washington D. C. housing prices, where the prices are proved to be highly related to geographic networks.",0.0,
42abdec870c4441dfb16a87db51f7d5e7e19aae8,10.1109/icpics62053.2024.10796220,House Price Prediction Model Based on Multi-Strategy Improved COOT Optimization Algorithm,2024.0,"2024 IEEE 6th International Conference on Power, Intelligent Computing and Systems (ICPICS)",Ziyang Han; Xiang-wei Zhu,"The COOT optimization algorithm holds promise for optimizing machine learning algorithms and feature selection. However, its drawbacks, such as weak overall search capability and sometimes it goes to a local optimum, pose challenges when applied in practice. Aiming at the problems existing in the reference white crown chicken algorithm, a new algorithm named TLCOOT is proposed, which is based on tent Chaos Mapping and Levy Flight Strategy. This strategy changes and improves the strength of the original algorithm to jump out of partial optimal solutions. A variety of functions are used to evaluate the effect of the algorithm. The results show that TLCOOT is superior to the COOT optimization algorithm and several swarm intelligence algorithms in Best, Mean, Std and convergence curve. On this basis, TLCOOT optimized random forest house price prediction model (TLCOOT-RF) was used. The experimental results of the model verify the practicability of the proposed TLCOOT optimization algorithm.",0.0,
d0b3cf94e9762dba81ce02766c4c5a29ee5d1c74,10.25202/jakg.8.2.14,Exploring Spatial Heterogeneity in Factors for Apartment Prices in Seoul Using Moran Eigenvector Spatial Filtering Based on Spatially Varying Coefficients,2019.0,Journal of the Association of Korean Geographers,Hyeongmo Koo,"Spatially varying coefficients models have been used as a tool for exploring spatial heterogeneity in regression coefficients. But, among various spatially varying coefficients models, only a geographically weighted regression (GWR) has been used for exploring spatial heterogeneity in factors for housing prices although it suffers from its low explanatory power and high multicollinearity between local coefficients. This study applies another type of a spatially varying coefficients model based on Moran eigenvector spatial filtering (MESF) to explore factors to apartment sale prices. The analysis results are compared to those of GWR and global MESF. The result shows MESF outperforms GWR in terms of explanatory power, spatial autocorrelation in model residuals, and multicollinearity between local coefficients. In additions, a variation in local coefficients against their global coefficients suggests that exploring spatial heterogeneity is necessary for a housing price estimation model.",0.0,
35d9bc16269b7721afd2312ec1b0be20e88da492,10.1080/17421772.2022.2125177,Raising the bar (22),2022.0,Spatial Economic Analysis,Paul Elhorst; M. Abreu; P. Amaral; A. Bhattacharjee; Steven Bond-Smith; C. Chasco; L. Corrado; J. Ditzen; D. Felsenstein; F. Fuerst; P. McCann; V. Monastiriotis; F. Quatraro; Umed Temursho; D. Tsiotas; Jihai Yu,"ABSTRACT This editorial summarizes the papers in issue 17(4) (2022). The first paper combines input–output modelling with priority weighting to analyse supply-chain impacts of disasters. The second paper examines skill-based functional specialization of value chains in Brazil using interregional and international value-added measures. The third paper questions the common belief that agglomeration economies are the driving force behind cluster formation using an agent-based model. The fourth paper applies modern instrumental variables techniques to measure the impact of forced migration flows from Venezuela to Colombia on house prices. The fifth paper explores the impact of an ageing population on per capita labour income, consumption and wealth at the regional level using a multivariate spatial econometric model. The sixth paper examines the impact of neighbouring countries on migrants’ aggregate decisions to remit based on an advanced spatial econometric origin–destination model.",0.0,
f08cbd1635c5956ec2f82f52f7e78ec7958b2ff8,10.1109/igarss55030.2025.11313991,"Exploring Non-Linear Relationships Between Green Space Patterns, Accessibility and Housing Prices Using High-Resolution Remote Sensing Imagery",2025.0,IEEE International Geoscience and Remote Sensing Symposium,Zixuan Wang; Xiang Zhang,"The study of the impact of urban green space (UGS) on housing prices is closely related to people's quality of life and the real estate market. This study explores the nonlinear relationships between UGS landscape patterns, accessibility, and housing prices in both the sales and rental markets. By utilizing high-resolution remote sensing images to extract UGS data, eight landscape pattern indices and accessibility in three transportation scenarios were calculated. XGBoost and SHAP methods were applied to analyze the marginal effects of different UGS characteristics on housing prices. The results demonstrate that ecological benefits, aesthetic value, and accessibility of UGS significantly influence housing prices, exhibiting threshold effects. In particular, we revealed the complex non-linear influences of ecological benefits, aesthetic value, and accessibility (cycling, etc.) on housing prices, which provides valuable insights for UGS planning and real estate market strategies.",0.0,
dd272256b5c62e12acb593965e966cd29ec916d2,10.24149/wp2415,The Problem of Quality Change in Historical Price Statistics: An Illustrative Example Using Baedeker Travel Guides,2024.0,"Federal Reserve Bank of Dallas, Working Papers",Jarod Coulter; Braden W Strackman; M. Wynne,"The problem of accurately measuring inflation in the face of constant improvement in the quality of goods is a long-standing one in economics. This paper uses a novel dataset on the prices of the travel guidebooks published by the German publishing house Baedeker between 1832 and 1944 to construct a hedonic price index for guidebooks. Comparing these indexes to the list prices of these guidebooks, we show that the failure to adjust for improvements in the quality of the guidebooks over time imparts a substantial upward bias to measured inflation. For example, for German-language guidebooks, nominal prices increased 76 percentage points more than quality-adjusted prices between 1843-1913, suggesting an average upward bias over this period of 1.1 percentage points a year. Similarly, we find substantial average upwards bias of 1.5 and 1.7 percentage points a year for French-language guidebooks over 1859-1913 and English-language guidebooks over 1868-1913, respectively.",0.0,
d9551db9ab0b17319187807982bd7357dd4c73aa,10.52842/conf.caadria.2024.2.485,Unraveling the Dynamics of Urban Catering: Analysing the Factors in Shaping Neighbourhood Restaurants Sceneries,2024.0,CAADRIA proceedings,Yijun Xiao; Si-Nan Yuan,". This research explores the dynamics of neighbourhood restaurants distribution in Tianjin, China, against the backdrop of rapid urbanization and evolving consumer preferences. Analysing key factors such as consumer demand, transportation, location, built environment, and competition, the study utilizes count regression models to assess occurrence frequency. The investigation reveals a significant surge in community restaurants from 2018 to 2021, influencing spatial patterns. Population density, housing prices, transportation infrastructure, and built environment emerge as pivotal factors impacting neighbourhood restaurants dynamics. The Hurdle-NB model, considering both count and zero parts, demonstrates the best fit. This study contributes nuanced insights for policymakers and industry stakeholders, aiding in enhancing accessibility, sustainability, and competitiveness of neighbourhood restaurants in urban areas amidst changing urban dynamics and consumer trends.",0.0,
b9df5d29ea35f9d039b992207f5d74737b49f38b,10.1051/shsconf/202316301005,Analyzing Local Dynamics in House Pricing During COVID-19,2023.0,SHS Web of Conferences,Rui-Jia Zhang,"Covid-19 has made it possible for people to work from home. As a result, there has been an increase in the demand for space. Since many positions now allow for the possibility of working online, people realize that having a larger space at home is necessary. This paper will use mathematical methods of data analysis and regression analysis in the context of the COVID-19 outbreak to discuss whether California house prices are suffering from an epidemic of infectious diseases.",0.0,https://www.shs-conferences.org/articles/shsconf/pdf/2023/12/shsconf_icssed2023_01005.pdf
f837688daac3d3e8812cfc7947b4859326720d0b,10.1109/acit62805.2024.10876955,Using Monte Carlo Simulation for Real Estate Price Valuation,2024.0,"Automation, Control, and Information Technology",S. Eletter; G. El Refae; Saad G. Yaseen; A. Alshehadeh,"Forecasting housing prices holds considerable importance in informing planning decisions at the individual level, within industries, and across the broader economy. Experts use housing prices to assess inflationary patterns or other economic crises. Given the uncertainty in the real estate industry, this study introduces a novel method for predicting home prices using a systematic and quantitative approach. The research employed Monte Carlo Simulation to provide valuable insights for the real estate sector, enabling better decision-making through increased predictive accuracy. This study emphasized using a Monte Carlo simulation as an effective approach for predicting housing values. This study's results showed that Monte Carlo simulations provide greater accuracy than multiple regression analysis in predicting home values. The Monte Carlo Simulation has proven reliable, effectively predicting property values with notable precision, consistency, and dependability.",0.0,
e745ee5d19fcb76c22bc7aa67a9a5c88976d7b61,10.22630/mibe.2018.19.1.3,Spatial Analysis of Local Housing Real Estate Price Changes (Using Olsztyn as an Example),2018.0,,R. Cellmer; M. Zapotoczna,This paper analyses the spatial dynamism of price changes in the housing market in Olsztyn. A geographically-weighted regression was used to examine the relationship between price changes in time and features of properties that describe specific technical and functional parameters. Data from 2007-2015 obtained from RCiWN were used to construct one exponential GWR model as well as separate models for each year under analysis. The results are presented in background maps.,0.0,https://doi.org/10.22630/mibe.2018.19.1.3
34e69e5bc33931ed15d395f945460b3fbc513831,10.55186/2413046x_2025_10_6_155,MATHEMATICAL MODELING AS A TOOL FOR ANALYZING VALUE-BASED CORRESPONDENCES IN THE HOUSING MARKET,2025.0,Moscow Economic Journal,German Pushkarev; Y. Ovchinnikov; Egor Anders,"This article analyzes the main factors influencing residential property prices in the city of Perm. To quantitatively assess the impact of various apartment characteristics on their market value, methods of multiple regression and variance analysis are applied. Econometric pricing models are developed, considering both vertical differentiation (market segmentation by housing class) and horizontal (territorial) stratification. The modeling results demonstrate that in elite market segments, qualitative parameters and housing size have a decisive impact on prices, whereas in mass segments, apartment compactness and infrastructure accessibility play a significant role. Thus, mathematical modeling serves as a tool for verifying value-based correspondences in pricing: price differences largely align with variations in property characteristics. The study results can be used for price forecasting and developing strategies for balanced urban environment development.",0.0,
6ff06be88701f17286f1bfbee3f1478ba795bb0d,10.1109/icsece65727.2025.11256900,Second-Hand Housing Prediction Model Prices by Using Hybrid RF-BPNNs,2025.0,"2025 IEEE 3rd International Conference on Sensors, Electronics and Computer Engineering (ICSECE)",Mengzhen Wang; Yujie Ying,"Accurate prediction of second-hand housing prices is crucial for effective decision-making in the real estate market. This study begins by applying Principal Component Analysis (PCA) to select the most relevant 8 features. Initially, a basic Backpropagation (BP) Neural Network was used for price estimation, but it yielded suboptimal R2 scores. To improve performance, we developed an ensemble model that integrates Random Forest (RF) and BP Neural Networks. The RF models generate additional predictive features, which are combined with the original dataset to form an enhanced feature set. Configurable BP neural networks were then trained on this augmented dataset. Further improvements were achieved by training 10 such model and combining their predictions by 4 distinct boosting methods, resulting in a best R2 score of 0.9108. Our results demonstrate the effectiveness of this hybrid approach in achieving high accuracy for second-hand housing price prediction.",0.0,
453ff855ff18dc1d3ac86f4841c7d22aaa7c2dbe,10.34925/eip.2020.122.9.250,Using artificial neural networks to evaluate residential real estate in two different regions,2020.0,Экономика и предпринимательство,Ю. В. Трифонов; А. Л. Сочков,"Целью работы являлась разработка многослойного персептрона для оценки жилой недвижимости двух регионов, находящихся в ведении одного отделения банка. Использован метод обратного распространения ошибки для обучения сети. Синтезирован многослойный персептрон, позволяющий проводить оценку квартир, расположенных в двух разных регионах со средней относительной погрешностью 4,81%. Сеть предназначена для банковских online сервисов оценки жилой недвижимости в городах Нижний Новгород и Казань.
 The aim of the work was to develop a multi-layer perceptron for evaluating residential real estate in two regions managed by the same Bank branch. The method of error back propagation is used for network training. A multi-layer perceptron was elaborated that allows evaluating apartments located in two different regions with an MAPE of 4.81%. The network is designed for online banking services for residential real estate valuation in the cities of Nizhny Novgorod and Kazan.",0.0,
705ade6af361d428f62909a69e5002a84927fdf2,10.1109/compas67506.2025.11381637,Towards Developing an AI-Enhanced Blockchain-Based Real Estate Management System,2025.0,"2025 IEEE 2nd International Conference on Computing, Applications and Systems (COMPAS)",J. Ferdousi; Israt Jahan Oishi; Solaiman Islam Naiem; Shadman Azad Rivan; Zohirul Islam; Muhammad Nazrul Islam,"This article proposes a platform with Artificial Intelligence (AI) for explainable house price prediction and blockchain-enabled smart contracts for secure and transparent property transactions. The three contributions of this work are: (i) a system architecture that combines explainable AI models with decentralized ownership transfer, (ii) cross-comparison of machine learning and deep learning baselines including XGBoost, LSTM, and Transformer-based models, and (iii) a case study on the apartment data of Dhaka city to demonstrating the viability of the platform. Although the Ethereum’s smart contracts ensure automated and verifiable transfers; the article continues to examine scalability problems (e.g., gas cost) and law enforceability. The test outcomes reveal improved prediction accuracy, improved user trust through interpretability, and improved transaction workflows, making the system a compelling foundation for real estate practice modernization.",0.0,
59f95b9e83799fe13df130dda300f00a16b5dd73,10.1080/13563475.2025.2541818,Analysis of house price fluctuations in a speculative housing market: Evidence from three Metropolitan Cities in Turkey,2025.0,International Planning Studies,Leyla Alkan Gökler,"ABSTRACT This research shows how to implement an instrument for detecting house price speculation in an emerging economy like Turkey. There had been a steady and extraordinary increase in house prices in Turkey in the last few years- out of reach of most income groups. Therefore, understanding the dynamics behind the increasing housing prices in Turkey will contribute significantly to the literature in terms of revealing the different aspects of speculative housing markets. The reasons for rising house prices are examined by conducting a multiple linear regression model with six independent variables and Housing Unit Prices as the dependent variable. The results of the study revealed that house prices have increased more than the CPI, and that housing remains severely unaffordable in the country. The results present some evidence of the process of speculation as a possible determinant of house prices as prices rise out of line with most fundamentals.",0.0,
930280281d0e0d8cd8fe356bf3e7de5ada0c3654,10.33203/mfy.1258125,Türkiye'de Yeni Konut Fiyat Endeksini Etkileyen Faktörlerin Analizi,2023.0,Maliye Finans Yazıları,Nurgün KOMŞUOĞLU YILMAZ,"This study investigates the relationship between the weighted average interest rates applied to housing loans, housing construction labor cost and housing unit prices, and the housing price index for new dwellings for the period 2015-2021. In the time series, a structural break was detected in February 2019. In the results of the regression analysis, differences were determined for the January 2015-January 2019 period and the February 2019-August 2021 period.",0.0,https://dergipark.org.tr/en/download/article-file/2981137
6c4762b55724cbdd2d2fc71e03c555f3b56f9595,10.1111/deve.12415,"Land Value, and Urban Transport and Amenities: Evidence From Antananarivo, Madagascar",2024.0,Developing economies,Atsushi Iimi,"Although urbanization is an engine of growth, many African cities are overly crowded with massive traffic congestion and high housing prices, pushing the poor away to unfavorable settlements or remote suburban areas and making them commute long. The paper sheds light on the relationship between land value and urban attributes in a rapidly growing African city, Antananarivo, Madagascar. It shows that the land value gradient is steep with an elasticity of −0.78 with respect to trip time to the city center. Thus, housing prices are overshooting. Better urban planning is needed through improving transport accessibility by minibus. Other urban infrastructure services, such as piped water and garbage collection, and urban amenities are also important to add to land values. Spatial heterogeneity is found across different locations in the city. While some areas require clean water and climate resilience, others need more city amenities, such as parks.",0.0,
fd97800f011a1e5cb3c785a29afda2bf7b24c254,10.55041/ijsrem59281,Explainable AI System for Interpreting Machine Learning Predictions using LIME and SHAP,2026.0,INTERNATIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT,I. Raskar; Aditya Joshi; Anushka P. Kalbhor; Arpit A. Gade; Divya D. Madane,"Abstract - This paper presents a proof-of-concept system for Explainable Artificial Intelligence (XAI) using Local Interpretable Model-agnostic Explanations (LIME) and Shapley Additive explanations (SHAP). The system is designed to interpret predictions made by black-box machine learning models in two real-world scenarios: house price prediction (regression) and loan approval prediction (classification). A baseline machine learning model is trained for each task, and both LIME and SHAP are applied to generate local and global explanations. The system demonstrates how feature contributions influence predictions and converts them into human-readable explanations. The results show that SHAP provides consistent global insights, while LIME offers intuitive local interpretations. The proposed approach enhances transparency, trust, and interpretability in AI systems.




Key Words:  Explainable AI(XAI), LIME, SHAP, Machine Learning, Interpretability.",0.0,
47ece02e91f447ac4bf8c4fb7b6fd3f096ebb063,10.68465/jrem.2026.1.2.65,Property-Value Perceptions among Nearby Residents Using Seongnaecheon : An Exploratory Field Survey,2026.0,Journal of Real Estate Markets,Chan-Woong Lim,"This study explores how nearby residents perceive the relationship between Seongnaecheon’s waterfront environment and property values. A field survey of 50 residents was conducted in July 2026 using non-probability quota sampling. Descriptive statistics and nonparametric and parametric tests were applied. 
Residents generally perceived housing near Seongnaecheon as having a relative price advantage. This perception was positively associated with additional-payment intention (ρ = .395, Holm-adjusted p = .008), whereas perceived importance of the stream to future property values showed no significant association. Walking time was also unrelated to additional-payment intention or overall evaluation. 
These findings suggest that Seongnaecheon may function as a neighborhood amenity associated with residents’ perceptions of property value. However, the results represent exploratory perceptions rather than evidence of actual property-price effects.",0.0,
b1b194946e7ca389f953d6c6cd4472102bac4ea4,10.1177/297765702022s222,A Decision Tree Based Model for Predicting the Value of Homes in Boston Using The ‘R’ Tool,2022.0,"Journal of Real Estate, Construction &amp; Management",Sameer Jain; Sachin Jain,": In the construction industry, analytics has modified the underlying trend of data processing and forecasting. It has the ability to derive actionable insights in the industry from massive amounts of data that are produced on a regular basis. In industry, a large amount of structured and unstructured data is generated, and using this data, we could assist a company in making a game-changing decision. Senior management is eager to take advantage of vast amounts of historical real estate data in order to gain insights into different facets of this burgeoning industry. Land size, distance, location, crime rate, age etc. are all variables to consider. We'll use the Boston Housing dataset, which was compiled by the US Census Service and includes data on housing in Boston, Massachusetts. The dataset contains 506 cases and 13 attributes. The aim of this paper is to develop a decision tree-based model for predicting home values in Boston.",0.0,
6898c97490acfe692d4c6c80ee696d78727feb4f,10.1109/ictacs59847.2023.10389820,An Ensemble Regression Model to Predict a Rent of House,2023.0,2023 3rd International Conference on Technological Advancements in Computational Sciences (ICTACS),Rahul Bhandari; Sanjay Singla; Daulat Sihag,"In today's era, assessing property values has become essential for multiple sectors, including real estate, taxation, the economy, and the stock market. The price of a house is closely intertwined with factors such as population and geographical location and necessitates the incorporation of additional data for accurate individual price predictions. In a contemporary setting, property prices are heavily influenced by a variety of factors within the economy and society. The current study focuses on the application of ensemble algorithms for predicting real estate and housing prices. These algorithms encompass bagging regression, histogram boosting, stacking, and ridge regression. To evaluate the prediction accuracy, the research examines the root square and root mean square error scores of the training models. The most noteworthy achievement in this study is an accuracy of 83.74%, achieved through the use of bagging regression.",0.0,
fc0bbdbf1e415dfb75ee691cb2550ca8e6e7cb42,10.1109/taai54685.2021.00018,Housing Price Prediction by Using Generative Adversarial Networks,2021.0,International Conference on Technologies and Applications of Artificial Intelligence,Chia-Fen Hsieh; Tzu-Chieh Lin,"Housing price forecasting is a highly complex and vitally important field of research. Recent advancements in deep neural network technology allow researchers to develop highly accurate models to predict financial trends. Deep learning has recently achieved great success in many areas due to its powerful capabilities in the data processing. For instance, it has been widely used in financial areas such as stock market prediction, portfolio optimization, financial information processing, and trade execution strategies, etc. In this paper, we proposed a novel architecture of Generative Adversarial Network (GAN) with the Long Short-Term Memory (LSTM) for forecasting the price of houses. To train and evaluate our methodology. The dataset was House Sales in King County, USA, which includes several pings, floor or room age, etc. In the analysis of this input information, the network model will output the predicted house price.",0.0,
2a15263c822b4d72ccd70cb7615d75ab6130676f,10.64751/ajmimc.2026.v5.n2(2).357,REALESTATE HOUSEPRICE PREDICTION,2026.0,American Journal of Management and IOT Medical Computing,Prateek Kumar Kar; Debaprasad Mahala; Mohapatra Girashree Sahu,"The rapid growth of AI-driven real estate analytics and increasing complexity of property valuation have created significant demand for intelligent house price prediction systems. Traditional valuation methods rely heavily on manual analysis and market expertise, which are time-consuming and inconsistent. This paper presents the design and implementation of an AI-Based Realestate Houseprice Prediction System that leverages Machine Learning, Data Analysis, Regression Models, and predictive analytics to estimate property prices accurately. The system analyses features such as location, area, number of bedrooms, amenities, market trends, and property images to generate accurate predictions. A web-based dashboard allows users to input property details and instantly receive estimated house prices. Experimental results demonstrate improved prediction accuracy and efficient performance for real-world real estate applications.",0.0,
95b102f25a0dd434ad885a8141ce3562b9eccd2d,10.4236/am.2014.521320,The Virtual Repeat Sale Model for the House Price Index for New Building in China,2014.0,,Weihua Jin; Sheng-Ping Jin,"By using the characteristics of the new building in China, this article constructs the virtual repeat sale method to produce virtual repeat data which is similar to the repeat sale model on the house price index. Case-Shiller procedure and OFHEO method are used to calculate the house price index for new building in China. A discussion is given and furthering models are needed to take advantage of the virtual repeat sale data.",0.0,https://content.scirp.org/pdf/am_2014121110553152.pdf
31b8bbfad2a106402c0804ddd9afe49d1e14bfa0,10.58809/mnxd3037,Impact of Housing Prices on Unemployment,2022.0,John Heinrichs Scholarly &amp; Creative Activities Day,William Daniel; Null Null,"The study attempted to identify if there was a statistically significant link between the unemployment rate in the U.S. and the change in average costs for houses in the U.S. Using data collected by the Federal Reserve and a ordinary least sum regression, it was determined that there was a statistically significant link where upon a 1 % increase in house prices indexed to 1/1/2012 caused a 0.056% decrease in unemployment.",0.0,https://scholars.fhsu.edu/cgi/viewcontent.cgi?article=1205&context=sacad
7f3edbe76b32a1ad7e5bf17986d4c70fe9ed44f7,10.1080/1540496x.2018.1517644,Evaluation of Housing Price Control Policies Based on a Sensitivity Analysis and Nonstationary Markov Chain Simulation: Empirical Evidence from China,2018.0,Emerging markets finance & trade,Chang Liu; Dongtao Lin; Ji-Jian Fan; Xiaosu Li; Pan Chen,"ABSTRACT This study evaluates housing price control policies in China between 2006 and 2016. A panel regression is employed to diagnose the explicit effects of these policies on housing supply and demand, followed by a nonstationary Markov model and t-copula to assess the policy sensitivity of the real-estate sector and the banking sector. This paper presents two important discoveries. First, total social welfare, represented by the sector fundamentals, is extremely sensitive to even tiny shocks from policy adjustments. Second, the current policies effectively restrain the supply of housing but not housing demand. As a result, the current policies fail to achieve their intended outcome by, on the one hand, driving up housing prices with a declining supply of housing and stable demand and, on the other, harming total social welfare. The empirical economic conditions in China are consistent with our findings.",0.0,
492e85009fb19d707755e7f8c4411ec5288d1120,10.1080/00036846.2026.2710409,When cointegration misleads: regional evidence on the determinants of housing prices in China,2026.0,Applied Economics,Li-Ping Gao; G. Gueye; Hyeongwoo Kim; J. Son,"Using data from 29 regional housing markets in China, this study examines the long-run relationships between housing prices and key macroeconomic variables. Conventional cointegration methods can be misleading, as estimated coefficients often contradict standard demand–supply theory even when statistical tests indicate cointegration. Among the variables, only real income consistently explains regional housing price dynamics, whereas real interest rates and building costs fail to do so consistently across markets. Region-specific models reveal substantial heterogeneity and are both statistically robust and economically meaningful. Panel cointegration tests that account for cross-sectional dependence fail to detect cointegration when such heterogeneity is ignored. These findings highlight the limitations of uniform national approaches and underscore the need for tailored, region-specific housing policies.",0.0,
4518721f959c7b0123164103f41e6415067df0da,10.1109/aisc56616.2023.10085127,A Strategic Alternative to Predicting Property Investment Value Through Random Forest and Gradial Enhancing,2023.0,Artificial Intelligence and Symbolic Computation,Anubhav Sony; Aarju,"The good investment instruments include the following items gold, stocks, and real estate. Investment in real estate in particularly has increased significantly. Developments in home prices are important for both sellers and buyers because they provide insight into the health of the economy. Property expenses are influenced by a variety of variables, including location, bedroom count, and floor layout. The cost of housing is also influenced by a property's proximity to roads, major highways, schools, retail centers, and local job possibilities. Normal home prediction becomes challenging, hence other methods for predicting house prices have been created. The least transparent sector in our society is real estate. Daily fluctuations in housing prices occur, and they are sometimes overstated instead of based on appraisal. Our group's primary objective is to predict housing values using actual information.",0.0,
0f5e03574c733a8f3b3b7cb160cb8b32374386d7,10.14801/jkiit.2021.19.5.7,US House Price Prediction Using Two-Stage k-Means Clustering,2021.0,The Journal of Korean Institute of Information Technology,Jeongwook Kim,"This study proposes the two-stage k-means clustering method improving the existing k-means clustering method and compares its prediction performance with various machine learning techniques. The two-stage k-means clustering is a method that searches for the cluster close to a prediction target in order to increase prediction accuracy and computational efficiency. This method is applied to the US house price time-series data. As a result, it shows the predicted value that is closer to the actual house price than the predicted values of other machine learning techniques. Furthermore, it shows the stable predicted value despite the use of a relatively small-size cluster, which suggests that the accuracy and stability of prediction can be simultaneously improved through the two-stage k-means clustering method and that the practicality of this technique can be valid as the size of the data is not sufficient",0.0,
0539558f884fdea91d0bb2dd020c956f70a567f7,10.1080/13504851.2012.705421,A consumer demand approach to estimating the education quality component of housing cost,2013.0,,Sofia N. Andreou; Nicoletta Pashourtidou,A consumer demand-based approach is proposed for estimating the shadow price of education relative to housing for households with children in state schools. This approach can be used together with or in place of a hedonic approach in countries in which the location of households is not disclosed in publicly available data. An empirical illustration is provided using UK data from the family expenditure surveys.,0.0,https://ktisis.cut.ac.cy/handle/10488/26592
6cf7109a76bc0d2699a5fedaa77fa34e9be510f1,10.54091/krepa.2024.25.3.96,Determinants of Rent and Revenue in New Town Neighborhood Commercial Facilities: A Case of Sejong Special Self-Governing City,2024.0,Korea Real Estate Policy Association,Seongmin Cho; Jae-ho Chung,"This study analyzes factors influencing neighborhood commercial facilities in Sejong Special Self-Governing City's new town development districts. Using data from the second half of 2023, the study examines how building, location, population, and urban planning characteristics affect commercial facilities' performance through multiple regression and GWR(Geographically Weighted Regression) analyses. Results show that proximity to government complex positively influences both rent and sales, while residential population demonstrates a similar positive effect. Significantly, higher commercial area ratios negatively impact both metrics, indicating that oversupply weakens market function. GWR analysis reveals these relationships vary spatially across regions. This study provides policy implications for optimal commercial area planning in new town development and practical insights for private developers.",0.0,
ad15fcd0be4aa0b26e2d1fe53d80246935f7f4f8,10.1109/adsssc67751.2026.11582632,House Price Prediction Using Support Vector Machine in Kerala: A Web-Based Approach,2026.0,2026 International Conference on AI-Driven Solutions for Sustainable Smart Cities: Challenges and Opportunities (ADSSSC),K. M. Aliaskar; K. N. Haneefa; N. Anitha; R. Afmitha; M. Anjana; S. Sivambika,"This paper explains how to create a web-based application to predict housing costs in Kerala. The tool will provide users with the ability to assess homes’ fair market values based on certain characteristics (geographical location, size, number of bedrooms, distance from City Centre, etc.). The tool is designed to increase the transparency of the real estate market in Kerala as well as give users accurate data to make better decisions when buying or selling a home. Housing prices will be predicted using Support Vector Machines (SVMs). The predicted housing pricing application will be developed in Python and Django using several open source Machine Learning (ML) Libraries and will have an interactive user interface that allows for real-time housing price predictions. The experimental and simulation results indicate that the predicted housing pricing system provides accurate and efficient predictions.",0.0,
d300b921d750a58d0305f218b301c6186beeb5aa,10.1111/1540-6229.70052,From battlements to boom: The enduring influence of historical walled city on housing prices,2026.0,Real Estate Economics,Zhenyu Lin; E. Hui; Huan Yang,"
 This study explores the long‐term economic effects of a unique form of historical architectural heritage—the city wall—on modern urban spatial structure. Using a Spatial Regression Discontinuity Design, the research compares housing prices on both sides of the Nanjing city wall, one of China's largest and best‐preserved urban fortifications. Results show a significant and consistent price premium for properties just inside the walls. Further analysis indicates that this premium is not solely due to the wall's heritage value, nor is it caused by a simple barrier effect or agglomeration dynamics on either side of the boundary. Instead, it stems from deep‐rooted path dependence within the city: early investments in the internal road network and the build‐up of local amenities, which together maintained a persistent urban structure and produced lasting capitalization effects within the wall.",0.0,
c71b688427842b1e1c2e7b5400ef26cdb5cbfb0c,10.1109/dcabes52998.2021.00047,Quantile Regression Method of House Price Index for Newly Building Condominiums in China,2021.0,2021 20th International Symposium on Distributed Computing and Applications for Business Engineering and Science (DCABES),Li-Rong Ai; Sai He; Sheng-Ping Jin,"The house price index plays a very important role in the real estate economy due to it is an indicator of real estate price changing. Aiming at the compilation model of China's new ordinary residential housing price index based on the matching set of upright adjacent floors, the parameter estimation method is improved, and the ordinary least square regression (OLS) is replaced by quantile regression to eliminate the extreme sensitivity of least square regression to outliers. This paper puts forward the quantitative index to evaluate the advantages and disadvantages of different methods to compile house price index, and makes an empirical analysis of the above ideas based on the loan data of commercial banks. The conclusions we got are more consistent with the actual results, more stable, and in line with the requirements of the third generation of housing price index compilation methods.",0.0,
d168a54a79dca9e1800dd13e818f5afc4c2eb261,10.1145/3557738.3557856,DESIGN AN AGILE OF MACHINE LEARNING TO PREDICTIVE HOUSE PRICING AND TARGETING SEGMENTED MARKET,2022.0,ICONETSI,J. Wijaya; Heru Purnomo Ipung; M. Soetomo,"Because of too high expectations or having a wrongly segmented target market, the developer hasn't received a good response from the target market. Developers need a new marketing tool that is based on data. The use of machine learning systems as marketing tools to help solve the problems in house price prediction is an important topic in the real estate industry. The design of machine learning will use CRISP-DM as a framework and to analyze using linear regression and random forest as the best possible accuracy. Besides that, to find a potential market, we will use K-Means as a clustering method. The modeling and experiments to design a machine learning engine that can predict a range of selling prices using linear regression can give maximum accuracy and analyze the target market. The research focusing on different attributes will bring different dominant attributes to the table too.",0.0,
ee956a3ad6a23a7cfa98a11c56d151908d9edb21,10.47750/cibg.2021.27.03.076,A Mechanism For Forming An Affordable Housing Market: Russian And International Characteristics,2021.0,Journal of Contemporary Issues in Business and Government,V. Morozov; L. Morozova; E. Kabanova; E. Vetrova; Tatiana A. Evstratova,"Today, the formation of the affordable housing market is one of the priorities of Russia’s socioeconomic policy. Its significance is due to the severity of the housing problem, deformations of the forming housing market, which are speculative in modern conditions with a constant rise in housing prices, and further limiting of its availability for the majority of the Russian population. The relevance of the study is confirmed by the high social significance of housing as a commodity, the presence of significant socioeconomic contradictions in the housing sector as well as the need to find ways to attract significant investment in the housing sector. Currently, about 83% of the housing stock is privately owned, about 13% is in social rent, and 4% in commercial rent. This structure is not effective enough, as it reduces the business and life activity of a large part of the population.",0.0,
631af1f44ecf156bd5eb4560c439bc1b390c3c51,10.47053/jdc.300922,The impact of forced displacement on housing and urban settlement in host communities,2022.0,,Semih Tumen; Joint Data Center on Forced Displacement,"Findings in the literature suggest that the sudden and often massive nature of refugee inflows, combined with the fact that housing supply is mostly unresponsive in the short-term, has the potential to affect housing prices and generate substantial changes in housing preferences, neighborhood quality/amenities, mobility patterns of hosts, and attitudes toward refugees in receiving areas. The interaction between the location preferences of refugees and the actions taken by hosts in response to refugee inflows may lead to residential segregation, urban poverty, high economic inequality, and unsustainable cities in the long-term. Policy lessons suggest options like transforming camps (that may have become socioeconomically attractive locations) into sustainable settlements, utilizing voucher programs, and incentivizing government-financed housing solutions for refugees.",0.0,
c7060b7364d2cf0dd30794b6b1ed2a7de38c8753,10.1080/09599916.2022.2119878,The impact of cash financing on housing prices: a theoretical framework and empirical evidence from a volatile United States market cycle,2022.0,Journal of Property Research,R. Aroul; J. Hansz,"ABSTRACT This study examines cash financing transaction price implications over a 12-year United States (U.S.) housing market cycle centred around the 2008 Housing Crisis, a period of unprecedented transaction price volatility. We establish theoretical reasoning and empirical confirmation of the mortgage contingency pricing effect, operationalised as a cash financing discount. We document that cash discounts are associated with market conditions, price levels, and improvement sizes and conditions. Larger empirical cash discounts are related to greater market distress, lower price levels, smaller improvement sizes, and inferior improvement conditions. We conclude that a one-size-fits-all rule-of-thumb is not appropriate when estimating cash financing pricing impacts. Finally, additional research is encouraged across different market conditions and in non-U.S. markets.",0.0,
94e589f5c194d8cba0629e0e84d3171e393f6c64,10.22158/jepf.v3n1p17,The Influence Factors of the House Price—The Cross-Sectional Analysis of the Consumers Factors Based on the 35 Cities in 2014,2016.0,,Wei Zhang,"This dissertation investigates the relation between the consumers and the price development on the housing market in 2014 based on cross-sectional analysis of the consumers’ factors. Based on the result of the correlations analysis and regression analysis, balance of savings deposit of Urban and rural residents per person affect to the dependent variable of the house price.",0.0,https://doi.org/10.22158/jepf.v3n1p17
7b4aee2056fa837423b38e5b8acf04bb72c062a3,10.1109/icccbda69573.2026.11676545,Exploring Factors Influencing Second-Hand Housing Market Prices Through Multi-Source Data Integration: A Case Study of Chongqing Liangjiang New Area,2026.0,2026 11th International Conference on Cloud Computing and Big Data Analytics (ICCCBDA),Lin-Hui Yan; Liang-Ming Wen,"To reveal the price formation mechanism and structural characteristics of the secondary housing market following the administrative restructuring of Chongqing Liangjiang New Area, this study utilized 18,000 initial property listings from the Fang.com platform. After preprocessing, 16,015 valid samples were obtained and systematically analyzed using data mining methods. By constructing multiple linear regression and random forest regression models, we found that the random forest model achieved an $\mathbf{R}^{\mathbf{2}}$ of 0.7132 on the training set and 0.6535 on the test set, demonstrating significantly higher predictive accuracy than linear regression. Feature importance analysis further revealed that building area and distance to subway stations are the core variables influencing housing prices, collectively contributing nearly 70% of the importance weight.",0.0,
18702e52345f925bd07faab5be25ae00d2d5190a,10.1145/3393527.3393540,Multi-Domain Global Correlation Degree Branching Entropy Method for Microblog Text Word Segmentation,2020.0,ACM Turing Celebration Conference,Jinlian Du; Xueyun Jin; Peng Wang,"Word segmentation is a basic topic in the field of natural language processing, and improving the accuracy of word segmentation is a key problem. With the popularity of microblog, accurate word segmentation for microblog text has become a hot spot. However, microblog texts often contain information about multiple related domains, ambiguous words in multi-domain will lead to the decline of word segmentation accuracy. Based on the model theory of word vector and branching entropy, this paper proposes a multi-domain global correlation degree branching entropy method for microblog text word segmentation. This model is applied to microblog text about house price topic in Beijing. The precision, recall and F-measure of this method are compared with branching entropy model proposed by Zhang[6], and the experimental results show that our method outperforms it.",0.0,
d40078b40dc2f359296a6603bfeb24858f526d5f,10.61173/y03ccd21,The COVID-19 Pandemic’s Impact on Shenzhen’s Real Estate Market: A Case Study of Cities Rotated: Shanghai and Beijing,2025.0,Finance &amp; Economics,M. Fang,"This study explores the effect of pandemic policies on the Shenzhen metropolitan real estate market, with discussions about similar policies in Shanghai and Beijing. The assessment is devoted to the year 2020 and prior and is guided by the data deriving from property prices, transaction volumes, and the turnover of homes through the secondary housing market. Although things were not going well everywhere, the degree of the corresponding changes in the cities was closely related to the specific administrative measures implemented in every city. The research emphasizes the fact that Shenzhen’s differentiated market characteristics as well as the preemptive usage of policy measures led to important shifts in new construction projects, which will have far-reaching impacts on future urban development policy-making in other mega cities in mainland China.",0.0,
08e8ff8f51f13b8bdd99b29a8af97128f8d6b702,10.1007/978-1-4842-6500-0_6,Model Evaluation,2020.0,Applied Data Science Using PySpark,Ramcharan Kakarla; S. Krishnan; Sridhar Alla,"Many people try to develop models to perform a certain task (for example, predicting house prices). Often times, these models cannot represent 100 percent of reality. In our example, we cannot exactly predict a house price all the time. However, it does not mean that our model is garbage. In general, all statistical and machine learning models face this problem. Then, why build one in the first place? Even though we cannot represent reality 100 percent, we can still model useful behavior and represent reality closely enough. In our example, we can use demographic information like zip code to predict price, and this model can perform better than randomness. This lays the foundation for this entire chapter. You need to make sure that this idea is planted well, because everybody cares about the insight that you bring to the table based on your model.",0.0,
d6e394b39690559fcf56412ae424ec49aa67e0ed,10.22423/kreus.2026.19.1.25,The Spatial Impact of the GTX-A Partial Opening on Apartment Prices: The Case of Dongtan New Town,2026.0,Konkuk Research Institute of Real Estate and Urban Studies,J. Seo; Sang-Min Lee,"This study examines the effect of the partial opening of the Great Train Express-A (GTX-A) Suseo–Dongtan section on real apartment prices in Dongtan New Town. Using apartment transaction data from November 2022 to August 2025, a difference-in-differences model was estimated with the treatment group defined as areas within a 1km radius of Dongtan Station, and a distance-interval interaction model was applied to examine the spatial distribution of the opening effect. The results show a statistically significant increase in real apartment prices near the station following the partial opening, with the estimated coefficients declining as distance from the station increased. These results suggest that accessibility gains are capitalized into housing prices even before full-line completion, offering implications for station-area apartment price policy.",0.0,
3765704578cad6233ac37a6b2b16bc7c28fd3a47,10.1080/03610918.2024.2446325,Tests for spatial dependence and temporal heterogeneity in time-varying coefficient spatial autoregressive panel data model,2025.0,Communications in statistics. Simulation and computation,Ti-Zheng Li; Yundi Tan,"Abstract Time-varying coefficient spatial autoregressive panel data model is a powerful tool to simultaneously deal with spatial dependence and temporal heterogeneity in spatial panel data analysis. However, little work has been devoted to related statistical inference issues, which largely limits the application scope of the model. In this paper, we develop two generalized-likelihood-ratio-statistic-based bootstrap tests to detect spatial dependence of the response variable and temporal heterogeneity of the regression relationship, respectively. The simulation studies show that both tests are of accurate size and satisfactory power, and are quite robust to non-normality of error distribution. A house price data set is finally analyzed to demonstrate the application of the proposed tests in detecting spatial dependence and temporal heterogeneity.",0.0,
955e47397d4f0bca58f3f244868aeb61ed3c0325,10.1177/14727978251358642,A method for predicting house prices in Beijing based on deep learning algorithm,2025.0,Journal of Computational Methods in Sciences and Engineering,Yun-Xing Wang; Xiao-Hua Chen; Yang Liu; Zhicheng Wen,"The trend of market house prices is influenced by various factors, and house price prediction algorithm remains a very classic and challenging nonlinear problem in data analysis. Analyzing various factors that may affect market house prices can help to provide a more accurate assessment of future trends in house prices. Multiple nonlinear regression is suitable for analyzing data affected by many factors. It is more efficient and practical to predict the house price by multiple independent characteristics than only one independent variable. This article is based on a deep learning algorithm and uses the PaddlePaddle experimental platform to learn about the past period of house sale prices and other related data in Beijing. Multiple nonlinear regression methods are used to analyze the data and predict the future house price trend in this region.",0.0,
cad4660b3043692c5ff46aec533e4cee4536b3b3,10.5935/1808-2785/rem.v20n1p.173-202,Os determinantes fundamentais dos preços dos imóveis residenciais: um estudo para o Brasil,2023.0,Revista de Economia Mackenzie,Guilherme Moreira da Costa Lopes; Ari Francisco de Araujo; Luiz Carlos Day Gama,"This study aims to analyze the main determinants of housing prices in Brazil. Considering that real estate are very heterogenic different methodologies were adopted in order to analyze the residential real estate market, both from a macro and micro perspective. In the first approach, models by Pooled OLS, Fixed Effects and Random Effects were estimated",0.0,http://editorarevistas.mackenzie.br/index.php/rem/article/download/15777/11936
e414d68bdc4a00c57adbae8e59a8b31fab1fb72e,10.1109/mlise57402.2022.00027,Channel exchange network model for house price prediction,2022.0,2022 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE),Yuantao Li; Rui Zhang; Jie Wang; Jia-Hao Shi,"As an important indicator of economic development, house price prediction is a hot issue in the field of business and research in urban computing. However, due to a variety of influencing factors and sparse transaction records, how to construct a housing price prediction framework is still a challenging problem. However, the existing machine learning and deep learning methods lack consideration of multi-source factors. Therefore, this paper uses the method based on channel exchange network to solve the problem of urban house price prediction. This paper also considers the space-time factors, regional factors and housing price expectations. In this paper, a neural network framework based on channel switching network is designed to capture these factors, and the characteristics of different model training are fused through channel switching",0.0,
d894812a17afa5a597e4f95bfc6698868e5eff78,10.36095/banxico/di.2024.18,Housing Price Gradients in Mexico City During the COVID-19 Pandemic,2024.0,,D. Mayorga; Karla Hernández; Jorge Pérez Pérez,"We estimate the slope of the housing price gradient -the relationship between prices and
distance to the center or employment density- in Mexico City, using administrative and survey data on housing prices in from 2019 to 2022. Our estimates rule out statistically significant changes in the slope
of the housing price gradient after 2020 Q1 with respect to the pre-pandemic period. The Mexico City
case contrasts with developed-country cities, where the housing price gradient flattened during the
COVID-19 pandemic, with housing price increases in the suburbs relative to central areas. Possible
mechanisms behind the lack of gradient change in Mexico city could include differences in pandemic
restrictions relative to other countries, a reduced potential for remote work, lack of access to finance housing purchases, and housing supply shocks.",0.0,
d43cb8b58778b03db2f4c5579de73e4a8dbf4ebc,10.1109/icdiss68238.2025.11320610,A Comparative Study of Predictive Analytics Techniques in Big Data Analysis,2025.0,2025 International Conference on Digital Innovations for Sustainable Solutions (ICDISS),Udita Shukla; Anjali Sharma; Sonal Pathak,"A key part of getting valuable insights from complex datasets in today's world of ever-increasing data is predictive analytics. This study uses the prediction of housing prices as a case study to compare six contemporary and conventional machine learning techniques: Random Forest, Support Vector Regression, Gradient Boosting, Decision Tree, Linear Regression, and Extreme Gradient Boosting (XG Boost). When compared to traditional statistical techniques, the results demonstrate the higher accuracy and consistency of ensemble-based techniques, especially XG Boost. In addition to performance assessment, the study discusses how predictive analytics is changing in 2025 and how cutting-edge techniques like federated learning, transformer-based models, and Auto ML with Neural Architecture Search are changing forecasting skills.",0.0,
b3cd25f18ea4f3318e0559e02e9258be23c8d3fa,10.1109/icspe62629.2024.10924379,House Price Prediction Using ML,2024.0,2024 International Conference on Sustainable Power & Energy (ICSPE),Anurag Kumar; Kalyani Singh; A. Raj; Aryan Shakya,"With the use of several Python modules, this project gives us a general idea of how to forecast home prices using several machine learning models. This suggested model offers the most accurate prediction and is thought to be the most accurate model for determining home prices. This gives a quick overview that is necessary to forecast the cost of a home. Using the datasets we will utilize in our proposed model, this study aims to explain what and how the house pricing model functions with the aid of machine learning techniques. Finding the right moment to purchase a property and figuring out The purchase price of a house in a certain area is helped by a price forecast.The objective of this machine learning task on house price prediction is to develop a machine learning model based on data in order to forecast house.",0.0,
d73949b9e8302e61295272aeea270858b7664d2a,10.1117/12.2655351,Research on prediction model of second-hand house price,2022.0,Conference on Intelligent and Human-Computer Interaction Technology,Yin Haoran,"With the rapid development of China's economy, the real estate industry has become an important topic of livelihood issues in China in recent years. This paper mainly takes the second-hand house price in Beijing as the data source, analyzes the status quo of the second-hand house price in each district, and studies the housing price prediction problem according to the properties of the second-hand house in the region, floor, year, layout and so on. In this paper, the housing price is predicted by linear regression model and decision tree regression model respectively, and the prediction results are scored by R2_Scroe scoring method, and the results are 0.66 and 0.79 respectively. Experimental results show that the prediction effect of decision tree regression model is better than that of linear regression model.",0.0,
6fd6c05d44ed0f229522a17ae8a0ea990680defc,10.51244/ijrsi.2025.120800153,"Predictive Modelling and Statistical Analysis of Housing Prices in Lagos State, Nigeria",2025.0,International journal of research and scientific innovation,Odukoya E. A.; Oyelakin O. P.; Lawal O. J.,"This study delves into housing market analysis and price prediction, leveraging statistical modeling and machine learning techniques to uncover patterns and forecast property prices. The housing market is influenced by diverse factors such as location, property features, economic indicators, and market trends, necessitating a comprehensive analytical approach. Using a dataset comprising historical housing prices and relevant attributes, the study employs exploratory data analysis to identify key determinants of property values. The findings highlight significant predictors of housing prices and demonstrate the potential of predictive analytics in guiding buyers, sellers, and policymakers. This research offers valuable insights into market dynamics and contributes to data-driven decision-making in real estate",0.0,
b9ca1245f97f4e5fa9f69ed8caa4ab616400af96,10.1109/icce-taiwan58799.2023.10226936,Urban Second-Hand Housing Price Evaluation System Based on Bayesian Probabilistic Model,2023.0,2023 International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan),Zhaojun Tang; Ping Zhang; Xinjing Qin; Bin Cheng; T. Liu,"Combining data mining technology into housing price evaluation problem has increased great attention in recently years because it improves the prediction accuracy. To facilitate the application, this paper builds an urban secondhand housing price evaluation system based on our Bayesian probabilistic model under location submarket division. Using urban data such as house location, surrounding environment and point of interest (POI) information, a prediction model is constructed based on the second-hand house transaction data crawled from the network. It helps users get the price as well as location, POI information and characteristic attributes of the target house, and query suitable houses meeting some given requirements. The system provides visual display of query results and evolves by using query results.",0.0,
a6743af461f14f287478afb12ee37c9afbc583ab,10.1111/acfi.13269,Low‐ frequency versus high‐frequency housing price spillovers in China,2024.0,Accounting &amp; Finance,Jian Yang; Zheng Li; Zi-Liang Yu,"Applying a novel high‐dimensional frequency‐domain‐based spillover index approach, this paper explores low‐frequency versus high‐frequency housing price spillovers among 70 Chinese cities. Intensive interactions among these cities were dominated by high‐frequency spillovers around the end of 2015, while low‐frequency spillovers have dominated since 2016. This coincided with dramatic changes in government policies, particularly the abolition of the ‘one‐child’ policy. Furthermore, city‐level economic factors were the primarily significant determinants of high‐frequency housing price spillovers within several months, while education was a major determinant of low‐frequency housing price spillovers in China, which was consistent with the distinction between work‐based and education‐based migration in China.",0.0,
9db0686f82f1f1fffba29212d0b81db0294f343d,10.24957/hsr.2023.31.4.109,A Study on the Impact of Hospitality Property Prices: A Comparison between Pre-COVID-19 and Ongoing Period,2023.0,Korean Association for Housing Policy Studies,Jiseon Lee; Yeon-Jae Lee; Seong-won Lee,"This study investigated the factors influencing hospitality property prices in the context of COVID-19. Previous research primarily focused on luxury hotels, and it lacks a comprehensive analysis of the entire hospitality sector. The study analyzed transaction data of 586 hospitality properties nationwide from 2018 to 2021. We model all the regional economic, physical, locational, and market characteristics. We use pooled OLS specification with all the interacting variables with COVID-19 period (2020 and 2021) dummy variables. 
We found that both the residential areas dummy and annual growth of the apartment price index showed positive signs during the COVID-19 period. This study shows that hospitality properties were sold during the period as a residential alternative, such as conversion to officetel.",0.0,
95c832bc28fe9ebe94055ece7fdc2cff0b39b445,10.1109/ickecs65700.2025.11035241,Predicting House Prices Using Various Machine Learning Algorithms,2025.0,2025 International Conference on Knowledge Engineering and Communication Systems (ICKECS),Rithvik Manohar; R. Janarthanan; S. Pavithra,"The research uses the Ames dataset from Kaggle for predicting house prices. It applies six different machine learning models. These are XGBoost Regressor, Support Vector Regressor, Decision Tree Regressor, Random Forest Regressor, Bagging Regressor, and Gradient Boosting Regressor. All the above models have been used with different features of property, including lot size, building type, and year built. Hyperparameter tuning optimized model performance; a comparative analysis shows better accuracy and robustness, especially with complex feature interaction, with methods being Random Forest and Gradient Boosting. The results in this paper emphasize the effectiveness of those models in the field of predictive real estate analytics and suggest valuable insights for future applications and research.",0.0,
5450419c6a46f3356f91add995e949a9dacd25e0,10.1109/icteasd57136.2023.10585192,Supervised Machine Learning Approach to Housing Market,2023.0,2023 International Conference for Technological Engineering and its Applications in Sustainable Development (ICTEASD),Izat Hakimi Mohd Ismayatim; Hanis Najiah Zakaria; I. Ramadhani; N. Abdullah; Fakhitah Ridzuan; W. A. Mustafa; Mohammed Al-Farouni,"Understanding the multifaceted factors influencing housing prices is crucial for facilitating informed decision-making among diverse stakeholders, including homebuyers, sellers, investors, and policymakers. Therefore, the primary objective of this research is to develop a predictive model for housing prices utilizing regression analysis. By leveraging machine learning techniques, such as regression and classification analysis, this study aims to uncover the intricate relationships between various factors and housing prices, ultimately providing valuable insights to stakeholders involved in the real estate market. Through rigorous data analysis and model development, this research seeks to enhance understanding and contribute to more accurate predictions in the realm of housing price dynamics.",0.0,
74ff267d8452744f196dde43f090e7c74cbf4168,10.51765/tayod.1421771,Comparison of expert opinion and artificial neural network models in housing price prediction,2024.0,Türkiye Arazi Yönetimi Dergisi,S. Yalpır; Erol Yalpir,"Bu çalışmada Ankara ili, Yenimahalle ilçesi, Batıkent Bölgesi sınırları içerisinde bulunan konutların öznitelik verileri ve coğrafi konumlarının taşınmaz değerine olan etkileri incelenmiştir. Veri seti düzenlenirken Coğrafi Bilgi Sistemlerinden faydalanılmıştır. Çalışma kapsamında nominal değerleme ve Yapay sinir ağları (YSA) modellemede kullanılmıştır. Bölgedeki taşınmazların elde edilebilecek en yüksek hassasiyet ve en yüksek doğrulukta taşınmaz değer haritaları oluşturularak değer tespitleri yapılmıştır. Modellemede YSA ile daha başarılı piyasa sonuçları tahmin edilmiştir. Nominal değerlemede ise uzman görüşü ile oluşan matematiksel modelin piyasa değerini tahmininin göz ardı edilemeyecek başarı elde ettiğini ve gelecekte modelin güncellemelerle sürdürülebilir olduğu gözlemlenmiştir",0.0,
9b1ab5f72bd8f0381fb36ae4fa7f6e6abaf3fe06,10.1109/iciss66954.2025.11389339,Smart City Ai for Homebuyers: Personalized Recommendations Derived From Historical Property Records,2025.0,International Conferences on Information Science and System,Davy Ronald Hermanus; S. Supangkat; Fadhil Hidayat,"This work proposes a personalized real estate recommendation system to enhance smart city public services by combining human-centered design ideas with machine learning concepts. Trained on past housing data from Bandung, Indonesia, the Random Forest Regressor in the system forecasts house prices. Via an interactive Streamlit interface, users assign preference weights for elements including architecture, location, and security. After that, the model ranks properties depending on a compatibility score obtained from preference matching and SHAP-based explainability and forecasts house prices. In line with ethical, open, and citizen-centric Smart City design, evaluation measures reveal great accuracy ($R^{2}=0.94$, MAPE $=22.01 \%$), and the system is fully deployed for public usage.",0.0,
56353d1ed3e0c3aadf4a612c2013d043eb7bd67e,10.1080/09720510.2020.1845469,Using real estate data to improve business student interpretation in regression,2021.0,,M. Devkota; E. Howington,"Abstract Multiple regression is a statistical technique used in many disciplines for the purpose of predicting a quantitative dependent variable. In this regard, business and economics are not exceptions. Hence, it is critical for business and economics students to understand regression methodology, write regression models and prediction equations, and interpret the results correctly. However, business and economics students often struggle with these very skills. This paper identifies and discusses several topics in regression analysis where students struggle with understanding and interpretation and suggests strategies instructors can use to explain these concepts. A real-world data set describing housing prices in Mount Pleasant, South Carolina, USA in 2017 is used for examples.",0.0,
87f08bce76f5913e565072d94837959199e06c94,10.1109/icuis67429.2025.11380639,AI-Driven House Price Prediction for Bangalore Region,2025.0,2025 5th International Conference on Ubiquitous Computing and Intelligent Information Systems (ICUIS),Sushmitha Megharaj Doddamani; Vaishnavi Savalagi; R. N,"Accurate prediction of house prices plays a crucial role in the real estate industry and aids stakeholders in making informed decisions. The process involves analysing a wide range of features such as location, size, number of rooms, and nearby amenities. By applying machine learning techniques, particularly Linear Regression, Random Forest, and XGBoost algorithms, the prediction process becomes more efficient and reliable. Among these models, XGBoost demonstrated the highest accuracy in estimating housing prices. The analysis includes data preprocessing, feature selection, and performance evaluation using metrics like RMSE and R2 score. The findings highlight the effectiveness of ensemble learning methods in delivering precise outcomes for property value estimation.",0.0,
5e3046a4a44e5bb73de057b26db5200058055700,10.1109/icuems50872.2020.00042,"How does Air Quality Affect Housing Price? – Evidence from Meishan, Sichuan Province",2020.0,2020 International Conference on Urban Engineering and Management Science (ICUEMS),Xue-Dong Liang; Yi Liu; Xing-Jiang Li,"Air pollution has become a major problem in China, and the impact of air quality on housing price has become more and more serious. By adopting the commodity house data of districts and counties in Meishan in 2016, this paper uses the “characteristic price model” to obtain the marginal willingness to pay (MWTP) of the consumer for buying houses under the improved air quality. The research shows that when the air quality index decreases drops by one unit, consumers are willing to pay an additional 494.9648 yuan for the improvement of air quality. Taking into consideration the different consumption levels of buyers, the marginal willingness payment level of buyers which corresponds to the price of each quantile house are obtained through the quantile regression model.",0.0,
38142911c368fc889db521fc8a3097c5e5477913,10.1628/jite-2025-0010,Metrics Matter,2025.0,Journal of Institutional and Theoretical Economics,Gary Sweeten,"Lenders are greatly increasing their use of Automated Valuation Models to confirm property value and to streamline the lending process, by using the AVM as a property value screen in home-equity lending. As the market has grown, so has the number of commercially available AVMs. Each AVM has different performance characteristics, geographic coverage, and confidence scores. For the most powerful risk management, lenders must understand the statistical performance characteristics of the AVM they use. That also means understanding Forecast Standard Deviation. The benefit of FSD is that it statistically links the confidence scores of an AVM to the AVM's forecasts of property value. Just how important is FSD, and how do you determine if your AVM supplies it accurately?",0.0,
7c133e01957a598c90d11b36fa9d8771350dc9a4,10.1002/isaf.70019,Lost in the Modeling Stage: A Comparative Analysis of Machine Learning Models for Real Estate Data,2025.0,Intell. Syst. Account. Finance Manag.,Ian Lenaers; L. De Moor,"Machine learning dominates automated property valuation, yet comprehensive comparisons of predictive models remain scarce. This study compares 28 rent prediction models using 79,735 Belgian residential rental properties from 2022. Predictive performance is evaluated with traditional and alternative metrics for train data, test data, and across deciles. The results confirm that tree‐based ensemble models outperform others, with stacking and averaging yielding superior results at a higher computational cost. Furthermore, middle‐range rents show better predictive accuracy than extremes. Traditional and alternative metrics provide consistent findings. These insights aid real estate stakeholders seeking to enhance their expert systems for real estate price modeling.",0.0,
62eb591fe5c6c1def56d0f198842d011358b788e,10.15396/eres2010_297,IS A RECOVERY OR A BUBBLE?: WHAT HAPPENED TO CHINA'S REAL ESTATE MARKET?,2010.0,,Yajuan Cao; Chung Yim Edward Yiu,"China's National Bureau of Statistics said that the annual growth of housing price reached 24% in 2009 after the financial tsunami. Is it a recovery or a bubble? What makes the housing price increasing so quickly? Price-to-Income Ratio is by far the commonest measurement method to housing affordability. And the relatively high housing price-to-income ratio in Asian cities, especially in Mainland China has been aroused many researchers' attention. In this research, the writer use panel regression based on monthly data from 2005 to 2009 of Mainland China cities, to analyze the driving factors of housing price-to-income ratio and also housing price and household income separately. And the test results suggest that the housing price boom might lead to a bubble.",0.0,
5be82af55989931f991fbf6f78fbea93a05bd3de,10.35453/nedjr-ascn-2022-0001r3,ANALYSING HOUSE PRICE PREDICTIONS ACCORDING TO LIVING STANDARDS BASED ON MACHINE LEARNING METHODS,2022.0,NED University Journal of Research,Khalid Mahboob; Nida Khalil; Saniah Rehan,"There is a lack of reliable economical methods for forecasting house prices for those who wish to buy a house according to their living standards. This paper presents details of predictive analytics for house pricing in three different towns of Karachi, Pakistan according to different living standards based on machine learning (ML) methods. The purpose of this study is to determine which data set features contribute greatly to the accuracy of the predictions when experimenting with selected predictive techniques. The house price value has been analysed using five different ML methods. A model selection has been made by comparing the accuracy of the techniques based on some performance metrics and the best technique was used to predict the house price value.",0.0,
e18d6f0609bfcfe9c11f3b7f25079abd0b07166c,10.1177/13548166261462676,Causal impacts of tourism on housing markets in Mediterranean destinations: From financial crisis to post-pandemic era,2026.0,Tourism Economics,L. Moreno-Izquierdo; J. Perles-Ribes; Agustina Romero; T. Torregrosa-Martí; Aimée Torres-Penalva,"This paper analyses the relationship between the evolution of residential rental and housing prices and tourism activity. We focus on four Spanish Mediterranean destinations over a time frame that covers the two major global shocks of recent decades: the Financial Crisis and the COVID-19 pandemic. Methodologically, the study employs a non-interventionist quasiexperimental design based on an Interrupted Time Series framework, allowing us to assess how the structural characteristics of each destination—together with tourism-related and structural factors shaping property markets—act as amplifiers or dampeners of housing price dynamics across different tourism specialisation models. From these results, relevant policy implications can be derived.",0.0,
4fbee1cd63ad04297da344f6c6135fbe06cb9c88,10.1111/1540-6229.70011,National Football League franchise departures and nearby home prices,2025.0,Real Estate Economics,Brad R. Humphreys; Geoffrey Propheter,"Research shows that US professional sports facilities positively impact nearby house prices. New facilities typically have existing teams, complicating the separate assessment of the impact of teams and facilities. Existing research analyzed departures of the National Basketball Association (NBA) teams, but arenas host many nonsporting events. These results may not generalize. We exploit the relocation of two National Football League (NFL) teams to investigate the impact of team departures on home sales. Difference‐in‐differences and repeat‐sales models indicate that proximity to one team is consistent with it being housing amenity while proximity to the other is not. Differences in urban form may be a key explanation for this heterogeneity.",0.0,
e0e5c1687186c65086fbce96f95791c277ca4a50,10.1109/iccasit53235.2021.9633656,Research on Influencing Factors of Residential House Using Improved Genetic Algorithm Model and BP neural Network Model,2021.0,2021 IEEE 3rd International Conference on Civil Aviation Safety and Information Technology (ICCASIT),Heng-Xin Ju; Shi-Peng Wang; Xiaohan Wu,"Real estate has been an important part of the Chinese economy. It is of great significance to study the factors influencing commercial, residential housing prices for stabilizing economic growth. In this paper, we designed a new index set according to the principle of economics. On this basis, we proposed a Back Propagation neural network model based on genetic algorithm optimization. The experimental results show that the improved BP neural network based on Genetic Algorithm has a better fitting effect than the traditional fitting model and BP neural network model, and MSE decreases by 35.6% and 14.5%, respectively. Through the improved model, we can reference the study of housing prices, real estate buyers, and investors' decision-making.",0.0,
d85c0567b113878d0abab319e4fc0c1c654a301e,10.1111/1540-6229.70066,Targeted tax relief and house prices: New evidence of capitalization,2026.0,Real Estate Economics,Patrick S. Smith; Mark Thibodeau,"
 Florida's property tax system caps annual assessed value growth and allows homeowners to transfer accumulated tax benefits between homesteads. These features create cross‐sectional variation in buyers' tax liabilities, allowing us to test whether house prices capitalize property tax relief while holding local amenities, public goods, and neighborhood characteristics constant. Using three complementary measures of property tax relief, we find consistent evidence that expected tax savings from the accumulation and transferability of these benefits are capitalized into transaction prices. These results suggest that policies aimed at reducing ongoing ownership costs may unintentionally worsen housing affordability by inflating house prices.",0.0,
4e0f5f33fa3bd6c26232a544bfdd68d4c89bd7d6,10.1145/3677779.3677831,Housing price prediction based on multiple regression algorithms,2024.0,"Proceedings of the International Conference on Modeling, Natural Language Processing and Machine Learning",Jiangang Wang; Xiao-Yan Wang; Zixuan Cao,"Obtain relevant property data through the network and preprocess the data, including viewing the correlation between features, removing outliers, performing normal distribution processing, filling in missing values, etc. Multiple regression algorithms such as elastic regression, lasso regression, ridge regression, and gradient boosting regression were used for modeling, and a stacked model was established on this basis. By comparing the root mean square error of the single model and the stacked models established by different models, the results show that the training effect of the single model is not as good as that of the ensemble model, so the stacked model is selected to predict the house price, which achieves the expected effect.",0.0,
9368cf0ec24a7b61c1bab13db1944e42e8cd3c90,10.1109/aiiot58121.2023.10174563,Predictive Analytics for Real Estate During COVID-19 Pandemic,2023.0,2023 IEEE World AI IoT Congress (AIIoT),Kanika Sood; Si-Jie Shang; Nima Nijad,"In this work we analyze the real estate market to study the impact of COVID-19 on housing prices in United States Metropolitan statistical area from January 2020 to April 2022. We build multiple machine learning and ensemble methods, including Linear Regression, KNN (k-nearest neighbors), SVM (Support Vector Machine), Random Forest, LightGBM (Light Gradient Boosting), and XGBoost (Extreme Gradient Boosting) for performing the predictive analytics. We also compare the performance of each model and determine which model has the best performance using well established performance metrics. Our analysis indicates that the ensemble technique: LightGBM outperforms all the other models in making predictions for the real estate market.",0.0,
3b61ae6e608effd006774ff7d20b0f0a9290e8c8,10.1109/i-coste63786.2024.11024733,Spatial Characteristics of CA: A Narrative into San Francisco,2024.0,2024 International Conference on Sustainable Technology and Engineering (i-COSTE),F. H.,"This study delves into the spatial characteristics of housing prices within California, with a specific focus on San Francisco. We explore various models to predict housing prices based on different feature sets, including coordinate and noncoordinate attributes. Through extensive analysis, we find that incorporating geographic coordinates significantly enhances the predictive accuracy of housing prices. Utilizing a neural network model, we achieve nearly 100% accuracy in predicting the, the quartile of median housing prices, underscoring the complexity and influence of location-specific features. Finally, we utilized iSLFN algorithm for developing a precise price prediction model and describing communities characteristics.",0.0,
ec8c445a590bc8c403096ec0be9a4fed7f26c187,10.1111/1467-8462.12547,Contradictory Results: Reassessing the Impact of Loan‐to‐Value Restrictions on House Price Inflation,2024.0,Australian Economic Review,Antony Andrews,"Using Bayesian Structural Time Series analysis, this study examines the causal impact of loan‐to‐value (LTV) restrictions imposed by the Reserve Bank of New Zealand in October 2013. By incorporating state‐space components, such as local linear trend, seasonality and regression, counterfactual values of house price indices are predicted. Surprisingly, the study reveals that the implementation of LTV restrictions had no significant effect on national house price indices, contradicting prior Central Bank studies that reported a nearly 3 percentage‐point decrease in housing cost inflation. This contradictory evidence challenges existing perceptions of the effectiveness of LTV restrictions in curbing house price inflation.",0.0,
e86b71f295ab70d604cbc16f28d3b80674d5a6a4,10.55041/isjem01418,PREDICTIVE MODELING FOR HOUSING PRICE TRENDS USING HISTORICAL DATA,2024.0,International Scientific Journal of Engineering and Management,Vidya sree P,"In ""Predictive Modeling for Housing Price Trends Using Historical Data,"" data analysis and predictive techniques are used to forecast future real estate pricing trends. By examining factors like location, size, economic indicators, and interest rates, this method creates predictive models. The aim is to provide valuable insights for real estate stakeholders, aiding decision-making in buying, selling, or investing in properties. These models assist in risk assessment and strategic planning, offering crucial insights for navigating the dynamic real estate market Key Words: Predictive Modeling, Housing Price Trends, Historical Data Analysis, Regression Analysis, Data Preprocessing, Feature Engineering, Model Deployment",0.0,
b01b56a3497e3173669e33f9a49300a4e5dd0c67,10.5817/cz.muni.p280-0068-2022-41,Sdílené ubytování a jeho vliv na ceny nemovitostí: Případová studie z Prahy,2022.0,25th International Colloquium on Regional Sciences,Filip Emmer,"This work focuses on short-term rentals, which is essetnial part of the sharing economy. This particular segment and its impact on the property prices has been frequently discussed in both mass media and the academic research. The aim of this study is to identify whether or not short term rentals have statistically significant impact on the property prices. To fulfill the main research aim, multiple OLS regression model is applied. Results of this method indicate that Airbnb has local impact and contributes to price rise in areas with significant amount of short-term rental supply. On the other hand, model provides no evidence of impact on the whole city of Prague, which was selectí as a basis for this study.",0.0,
0ed50c8ec2872ac705642c937da09a50a8525350,10.1109/bdicn55575.2022.00114,A housing price prediction method based on neural network,2022.0,"2022 International Conference on Big Data, Information and Computer Network (BDICN)",Yu-Chen Ni,"This paper proposes a housing price prediction model based on the neural network for the problem of rising housing prices. First, the data are read from Kaggle, then the data are collected for preprocessing, and 10 relevant features are obtained and the data are normalized for each feature. Then build the model, train and configure the model. After that, the loss function and optimization algorithm are set using the stochastic gradient descent method. After the model is trained on the data set, a housing price prediction model is obtained. The experimental results show that the prediction model can accurately predict housing prices, and can make a more scientific reference for the trend of housing prices.",0.0,
70b7f297b80806d606892bccc590dd3b2cac2409,10.3368/le.102.4.040325-0023r1,We Love Green,2026.0,Land Economics,Marine Coinon; Rachel Guillain; S. Legras,"Abstract Agricultural landscapes generate a complex bundle of positive and negative local externalities. This article estimates the impact of the type of farming (organic versus conventional) on residential property prices in France, using an exhaustive database of 2.9 million housing transactions merged with geolocalized land use data, and a dual identification strategy (buffer and distance-based). The results establish a clear hierarchy of preferences. At short distances, proximity to conventional agriculture is a significant baseline disamenity and organic farming is a mitigating factor. This premium increases with the extent of the organic landscape and is most pronounced in periurban areas.",0.0,
ae012ea924873256cfc3d6615d34e7ec5109f642,10.1109/csce60160.2023.00297,Improved Machine Learning Approach for Shanghai City's Secondhand Housing Price Prediction,2023.0,"2023 Congress in Computer Science, Computer Engineering, & Applied Computing (CSCE)",Guang Hu; Yue Tang; R. Yi,"This paper presents an improved machine learning approach for prediction of second-hand housing prices in Shanghai. It firstly builds the random forest model and the XGboost model with Shanghai second-hand housing transaction data, and then analyses the challenges in the improvement of the models' prediction accuracy and generalization performance. In the light of that, it introduces the Lasso model for variable selection, and deletes three variables with insignificant regression coefficients, and then rebuilds the random forest and XGboost prediction models. The experimental results show that the prediction accuracy and the generalization performance of the models is well improved.",0.0,
aef3c35f56b14d8ef4f2a8231afce1eeaa36a403,10.2139/ssrn.4280776,Housing Wealth and Overpayment: When Money Moves In,2022.0,Social Science Research Network,Darren Aiello; Jason D. Kotter; G. Schubert,"We construct a novel dataset tracking households across property purchases covering 25 years of moves within the U.S. We find that information frictions in residential real estate markets cause movers with larger exogenous housing wealth to overpay for their next house, relative to both time varying local prices as well as time invariant characteristics of the property itself. These housing wealth driven overpayments are associated with larger positive price impacts to the immediately surrounding neighborhood and are larger for local movers relative to non-local movers. The aggregate effect of housing wealth inflows is to increase commuting-zone-level house price growth.",0.0,
e40c154da2987eaf6612ca0abf0e9ff60c9af555,10.1109/iccrd54409.2022.9730362,Factors Affect the House Price,2022.0,International Conference on Computer Research and Development,Minhong Shao,"The object of this paper is to evaluate whether house age and the distance between a house and the nearest metro station could affect housing price, within a given area. A sample of 414 houses in New Taipei City, Taiwan has been selected. Multiple linear regression has revealed a linear relationship between house price, house age, and distance to a metro station. However, scatter plots suggest that the linear regression model might not be the best model to explain the relationships between house price and the two independent variables because I use several scatter plots which show that quadratic models are much better to explain the relationships than linear models.",0.0,
826cbd53f328d497d0fcae54a0b290ebff89e9bf,10.3368/le.102.2.112724-0114r1,Fires in the Built Environment and Residential Market Demand,2025.0,Land Economics,Jihwan Kim; Jayash Paudel; Hanbyul Ryu,"Abstract Using nationwide data on multifamily residential transactions in South Korea, we investigate how large-scale fires in the built environment affect housing markets. We make use of geospatial data and apply a difference-in-differences research design to show that fires in an apartment complex cause an approximately 9% decline in housing prices over a one- to two-month period. In contrast, fires that occur slightly farther away or in nonresidential buildings have no significant effect. Text mining analysis further suggests that greater media coverage—often associated with fires in nonresidential structures—does not necessarily result in larger price declines.",0.0,
9fefd0dc1e6bfd44d77914decc4a6c4fb82c639f,10.21005/pif.2025.64.c-05,THE IMPACT OF CARDINAL AND ORDINAL DIRECTION EXPOSURE AND STRUCTURAL ATTRIBUTES ON PRICES IN THE PRIMARY HOUSING MARKET IN WARSAW,2025.0,Space&amp;FORM,Hubert Horynek,"First aim of the research was to determine which structural attributes have the greatest impact on
housing prices. The second was to determine to what extent the exposure of windows to specific
cardinal and ordinal directions affects prices. Structural attributes clearly affect offer prices. The exposure of windows to specific directions is an additional, significant factor. The better the access to
sunlight, the higher the prices per square meter. Two-sided flats provide little information as north
exposure reduces the prices so much that south exposure correlates with relatively low prices. Corner flats analysis has much greater explanatory power.",0.0,
baafbd5988095d36f31bc7d2e66f84acd3b5d5e5,10.1177/08912424241309843,A Threshold Analysis of the Effect of House Prices on U.S. Local Labor Markets,2025.0,Economic development quarterly,J. Akosa; Michael J. Osei,"This paper uses a threshold regression model to examine whether the effect on total employment of an exogenous change in tradable sector employment differs in systematic ways depending on the average house price. The results based on data from 321 U.S. metropolitan areas suggest the presence of a threshold effect. The local employment multiplier increases with the average house price until some house price threshold level beyond it decreases, suggesting that affordable local housing markets not only help attract companies but also allow local economies to maximize the benefits from location-based development policies aimed at creating more jobs.",0.0,
cf1e9446191aa4f5ae8f114187bd46421d546251,10.7148/2020-0197,Estimating Relationships In Multi-Dimensional Data Sets By Means Of Asymmetric Fuzzy Regression,2020.0,European Conference on Modelling and Simulation,Raphael A. Krauthann; Tobias Kruse; Hinnerk Jannis Mueller; Michael Stumpf; P. Rausch,"In spite of all progress of AI and Machine Learning, making predictions based on real-world data is still a challenging task. For this purpose, Tanaka’s approach of symmetric fuzzy linear regression is explained, and open issues are outlined. These issues occur if the instances of data sets are not symmetrically distributed. For this purpose, new solutions based on enhancements of Tanaka’s approach are discussed. A real-world scenario for predicting house prices is used to illustrate the ideas. It is shown that the new asymmetric approach works at least as well as the symmetric version but is superior in certain situations. 1",0.0,
ea04faa3629d6ec5277a775909d75463bd04b9e8,10.1109/icaiccit68829.2025.11433976,Smart House Price Prediction: Evaluating Crime Rates and Employment Trends Using Machine Learning Algorithms,2025.0,"2025 3rd International Conference on Advances in Computation, Communication and Information Technology (ICAICCIT)",Rakeshreddy; Payamvineesha; Kambleavinash; Kumar Reddy; M. Jagdish,"This study proposes a Flask-based machine learning system to improve house price prediction by incorporating crime rates and employment trends — two critical socioeconomic factors often neglected in existing models. The key contribution of this work lies in integrating these external indicators into a Random Forest-based prediction pipeline, significantly enhancing accuracy over traditional attribute-based models. By deploying the system as an interactive web tool, the study also bridges the gap between predictive analytics and real-world usability, enabling dynamic, real-time price estimations for diverse stakeholders.",0.0,
f4c81e71c4a136632ee711fd9168f8cde85d5892,10.1080/13504851.2023.2203449,Determinants of county-level rent levels: a Bayesian model averaging approach,2023.0,Applied Economics Letters,Richard J. Cebula; James W. Saunoris,"ABSTRACT This paper uses Bayesian Model Averaging (BMA) to account for model uncertainty and to identify the robust determinants of county-level rent levels for a panel of 111 counties and independent cities in Virginia from 2008 to 2017. Of the fifteen determinants tested, the results show that single-family home prices, per capita education spending, and educational attainment are robust and positively associated with rent levels, while unemployment rate, population density, labour force participation, and the percent of the population that is Latino are robust and negatively associated with rent levels.",0.0,
98c898b2934173b5b85a465830976d7f568ce0af,10.55041/ijsrem39973,HOUSE PRICE PREDICTION USING ML: A Review,2024.0,INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT,P. M.; Sharan U Hiremath; Shreya K. U.; Tejaswini H; Vidya N. S.,"In today's society, everyone wants a home that fits their lifestyle and budget while still providing the
facilities they require. House values fluctuate a great deal, indicating that they are typically overstated. Many
criteria must be considered when projecting house prices, including the location, number of rooms, carpet area,
age of the property, and other fundamental local features. This study seeks to forecast house prices based on all of
the main factors that go into deciding the price.
Keywords: Machine learning, Supervised learning, linear regression, model, Ridge regression",0.0,
878ce08a6eeabdc87e9777cfa2d6dbec4c0aa6e6,10.12677/gser.2025.141014,Neighborhood Environmental Impacts of Residents’ Low-Carbon Transportation—An Investigation of Hangzhou as a Low-Carbon City Pilot Zone,2025.0,Geographical Science Research,Li-Yue Jin; Wen-Le Zeng; Nina Cai; Liang Zhang,"Residents’ transportation decisions are closely linked to carbon reduction targets. Focusing on the neighborhood environment for residents’ travel, the study selects typical neighborhoods in Hang-zhou, and summarizes the spatial environment characteristics from multiple dimensions, such as land use composition, transportation facility configuration, neighborhood house price, public life service facilities, and neighborhood green environment, and explores the relationship between residents’ low-carbon travel behavior and the neighborhood spatial environment. It is helpful to",0.0,
b4cb621d411693e41acd452211dd18e4dcf00310,10.1109/iccsc62048.2024.10830341,Real Estate Price Prediction Model Analysis Using Machine Learning,2024.0,IEEE International Conference on Circuits and Systems for Communications,Kapil K. Rajput; N. Bahadure; Amit Kumar Mishra; Manoj Diwakar; Sumita Lamba,"The research illustrates use of ML algos in the field of housing price prediction. The models have been analyzed on real datasets downloaded from Kaggle created by Amitabha Chakraborty. We know that the source on the research of ML prediction in India are scarce, but we encounter conditions which pose need of efficient methodologies to solve this problem. This research gives a glance about the use of ML techniques on the dataset. After careful analysis of data processed and running tests in multiple ways, the results indicate the best suited algorithms for this work.",0.0,
5278e0252b9caf8450691bcef2e1f4b3e71a046c,10.1155/2023/9891083,Retracted: Prediction and Analysis of Housing Price Based on the Generalized Linear Regression Model,2023.0,Computational Intelligence and Neuroscience,Computational Intelligence and Neuroscience,[This retracts the article DOI: 10.1155/2022/3590224.].,0.0,https://downloads.hindawi.com/journals/cin/2023/9891083.pdf
4bd2eb32f66789b92181e5c9bd7cece6b38999ee,10.56726/irjmets47584,PRECISION IN PROPERTY: ADVANCED REGRESSION MODELS FOR ENHANCED HOUSE PRICE FORECASTING,2023.0,International Research Journal of Modernization in Engineering Technology and Science,A. Gund; S. Gaikwad,.,0.0,http://dx.doi.org/10.56726/irjmets47584
45c65b5ccba85b2b0e413039422ff9b86b972752,10.1007/s00168-012-0543-z,Understanding the impact of trails on residential property values in the presence of spatial dependence,2012.0,The annals of regional science,O. Parent; Rainer Vom Hofe,,0.0,https://papers.ssrn.com/sol3/papers.cfm?abstract_id=2285731
2469c31ee76b38d5bd52bb7f18e02f433ca0ebb9,10.1007/s10901-019-09690-y,"Administrative hierarchy, housing market inequality, and multilevel determinants: a cross-level analysis of housing prices in China",2019.0,Journal of Housing and the Built Environment,Rong-Hui Tan; Qingsong He; Ke-Hao Zhou; Yan Song; Hengzhou Xu,,0.0,https://cdr.lib.unc.edu/downloads/02871c17j
c45a04529a5e13ac11524e995bb127e2a0eddd53,10.2139/ssrn.3801591,Hedonic Price Index Number for New One-Family Detached Houses in Finland,2021.0,Social Science Research Network,Antti Suoperä; J. Vuorio,,0.0,https://doi.org/10.2139/ssrn.3801591
dc62559c7277c98eb69e08ddaaaa54f66ed22947,10.1007/s11146-017-9600-9,Wireless Towers and Home Values: An Alternative Valuation Approach Using a Spatial Econometric Analysis,2017.0,Journal of real estate finance and economics,Ermanno Affuso; J. Cummings; Huubinh B. Le,,0.0,https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3172263
efea80c945cd0caa21f11ef5939d10ff9d755deb,10.2991/aebmr.k.220307.035,Machine Learning-based Models for House Price Prediction in Provincial Administrative Regions of China,2022.0,Proceedings of the 2022 7th International Conference on Financial Innovation and Economic Development (ICFIED 2022),Xiafei Ding; Weiyan Wang; Yi-Qian Zhang; Xiaoyuqian Zhong,,0.0,https://www.atlantis-press.com/article/125971699.pdf
fb46f09b30a18fe6d5ef8d896a32fc4deecc3211,10.1371/journal.pone.0339146,Retraction: Optimization of house price evaluation model based on multi-source geographic big data and deep neural network,2025.0,PLoS ONE,,,0.0,https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0339146&type=printable
3ac46c8c9a9d1cc3106efaeba23de4aa7a8188ab,10.46632/daai/2/4/2,Enhancement in House Price Prediction using Advanced Regression Technique,2022.0,4,,,0.0,https://doi.org/10.46632/daai/2/4/2
90c40c6969271ec97c8a8400379234bc355c95fc,10.15396/eres2023_90,Housing prices as location determinants of Coworking Spaces in non-urban areas – a comparative approach between UK and Germany,2023.0,29th Annual European Real Estate Society Conference,Fernanda Henriques da Silva; Husain Vaghjipurwala; Thomas Vogl,,0.0,https://eres.architexturez.net/system/files/P_20230425232222_0496.pdf
66a65afa5298d1d6d0bd053f827221a779eb2a95,10.5220/0014379000004918,Predicting House Price with multiple LASSO Regression and Linear Regression,2025.0,Proceedings of the 3rd International Conference on Computer Science and Mechatronics,Nuo Cheng,,0.0,https://doi.org/10.5220/0014379000004918
d0376066fc82eec8da102d891dc028fab921c9cf,10.5220/0012991000004601,Research on Housing Prices Forecasts Based on A Multiple Linear Regression Model,2024.0,"Proceedings of the 1st International Conference on Innovations in Applied Mathematics, Physics and Astronomy",Yiwen Wang,,0.0,http://dx.doi.org/10.5220/0012991000004601
8d7d1a3fe693274b24ee99e453e9c10db2b67bfb,10.2139/ssrn.4333188,Evaluation of Railroad Noise – The Proximity to Railroads and Its Effect on House Prices,2023.0,Social Science Research Network,Patrick Thiel,,0.0,https://doi.org/10.2139/ssrn.4333188
8fbd66059d714aa0ed810fca8981507535512405,10.1017/s016354840000042x,USING MULTIPLE LISTING SERVICE DATA TO ANALYZE DETERMINANTS OF RESIDENTIAL PROPERTY VALUES,1972.0,,J. Penn; G. Irwin,,0.0,http://ageconsearch.umn.edu/record/158052
b63e11a930bda6346adac374d189af5807770f8d,10.24210/kapm.2010.24.3.005,Housing Price Estimation using Spatial Econometrics Models : Focused on the Real Transaction Housing Price in the Busan,2010.0,,Kim， Sung Woo,,0.0,https://doi.org/10.24210/kapm.2010.24.3.005
2dc7e31185bf1cf3df91fe07e91780ca4e3622f7,10.3837/tiis.2025.04.002,Predicting Housing Price in Seoul using Explainable AI (XAI) and Machine Learning,2025.0,KSII Transactions on Internet and Information Systems,Hae Jung Chun; Hui U. Lee; B. Lee,,0.0,"https://itiis.org/digital-library/manuscript/file/102442/TIIS Vol 19, No 4-2.pdf"
2585bec8a6a8e1b093adbd26c9ecf6cb4d53e2e5,10.32520/stmsi.v15i2.5726,House Price Prediction using the Random Forest Regression Algorithm,2026.0,SISTEMASI,Fika Halimah Balqis; Qurrotul Aini,,0.0,https://sistemasi.ftik.unisi.ac.id/index.php/stmsi/article/download/5726/1150
7c9da61ded87721102ca7cc60e06fe8bd79ca687,10.2139/ssrn.3014547,The Determinants of House Prices in Australian Capital Cities,2017.0,Social Science Research Network,Abbas Valadkhani,,0.0,https://doi.org/10.2139/ssrn.3014547
36381c0d9eba33d8b04209483e5f53e367c8e388,10.13052/rp-9788743808268a104,"Advanced Machine Learning Techniques for Predicting House Prices: A
Comparative Analysis",2025.0,"First International Conference on Computer, Computation and Communication (IC3C-2025)",Gautam Kumar,,0.0,https://www.riverpublishers.com/pdf/ebook/chapter/RP_9788743808268C104.pdf
93a959319d751f298301e0b785f4c63907951778,10.55248/gengpi.234.5.39837,An Approach to Predict House Price Using Machine Learning,2023.0,International Journal of Research Publication and Reviews,Ankit Tripathi; Ankit Rai; V. Agrawal,,0.0,http://dx.doi.org/10.55248/gengpi.234.5.39837
a7735fcd00c918cdad9d7596e360292911169f8d,10.2139/ssrn.5477008,Forecasting House Prices and Rents: Combining Dynamic Factor Models with Machine Learning,2025.0,Social Science Research Network,R. Trojanek; A. van de Minne,,0.0,https://doi.org/10.2139/ssrn.5477008
7220da292deae36951ca2a9de359484d3db23c0f,10.1016/j.gecco.2026.e04413,Prime real estate for a top predator: Housing prices and park proximity predict nest-site selection of an urban hawk,2026.0,Global Ecology and Conservation,Jia-Kai Wang; Lee-Lien Wang; Die-Hua Tsai; Si-Min Lin,,0.0,https://www.sciencedirect.com/science/article/pii/S235198942600363X/pdf
7177b4352c4af7284a09d8b95fa8bc4ab8f3a401,10.15793/kspr.2010.67..003,"Trends of Determinants of Housing Price in Seoul, Korea: A Quantile Regression Analysis",2010.0,,J. Lim,,0.0,https://doi.org/10.15793/kspr.2010.67..003
0ec1e7c629b8d1975f1556930a2ba9be7b8cac5e,10.55041/ijsrem62604,Prediction of House Prices using Machine Learning Techniques,2026.0,International Journal of Scientific Research in Engineering and Management,Yogesh Yogesh,,0.0,https://doi.org/10.55041/ijsrem62604
02437e50728fb744309d82e321792a0d5d850f58,10.5220/0015031500005056,The Influencing Factors of Second-Hand Housing Prices in Beijing Based on Machine Learning Models,2026.0,"Proceedings of the 1st International Conference on Applied Mathematics, Physics and Digital Simulation",Si-Cheng Li,,0.0,https://doi.org/10.5220/0015031500005056
7e5a519ed4d1d110d853cde142b31b316c797b5b,10.2139/ssrn.257641,"Capitalization of Parent, School, and Peer Group Components of School Quality into House Price",2005.0,,D. Haurin; David M. Brasington,,0.0,https://doi.org/10.2139/ssrn.257641
766b6e5fb2c62b60c51050aa40bef897f3ebdf33,10.61186/jvfc.4.3.1,Study the Effect of Exchange Rate Volatility on House Price in Iran (Exponential GARCH and Quantile Regression Approach),2023.0,Journal of Future Cities Vision,R. Aleemran; S. A. Aleemran,,0.0,http://dx.doi.org/10.61186/jvfc.4.3.1
518ba78f2902bb654a1c69a0482dc1d326ccfae6,10.26438/ijcse/v10i1.4548,House Price Prediction through Machine Learning Technique,2022.0,International Journal of Computer Science and Engineering,C. Patidar,,0.0,https://doi.org/10.26438/ijcse/v10i1.4548
68e1bd94fca50f9d2152f75488046841d80e92fe,10.5220/0014871300005130,The Comparative Analysis of Five Machine Learning Models for House Price Prediction,2024.0,Proceedings of the 2nd International Conference on Financial Management and the Digital Economy,Yue Wu,,0.0,https://doi.org/10.5220/0014871300005130
5fa8b8c8c2cfa9c052abf7601c92fda3abd2ebcd,10.2139/ssrn.4096393,Valuation of House Prices Using Predictive Machine Learning Techniques,2022.0,Social Science Research Network,Meghana Tribhuwan; S. Godse,,0.0,https://doi.org/10.2139/ssrn.4096393
5a2df7042187ef3f9805a183d9eb9b2aa7c9a103,10.5220/0014884400005130,Machine Learning Approaches for Predicting Seattle House Prices,2024.0,Proceedings of the 2nd International Conference on Financial Management and the Digital Economy,Xin-Bei Chen,,0.0,https://doi.org/10.5220/0014884400005130
5df1dc5f6c85f973973e1a5da5ec5159f042daa8,10.12677/sa.2016.53030,基于增强回归树的房价影响因素分析—以波士顿地区为例 Factor Analysis of Housing Price Based on Boosting Regression Tree—Taking Boston as an Example,2016.0,,Jia Sheng,,0.0,https://doi.org/10.12677/sa.2016.53030
44c815ae72d5549d70c5587925f2562528ed0580,10.4108/eai.26-5-2023.2334435,Machine Learning based Comparative Study on House Price Prediction Task,2023.0,"Proceedings of the 2nd International Conference on Mathematical Statistics and Economic Analysis, MSEA 2023, May 26–28, 2023, Nanjing, China",Ru Hu,,0.0,http://eudl.eu/pdf/10.4108/eai.26-5-2023.2334435
79f7c75eb746bd897d6f7938f2a6165dd60997a5,10.5220/0014879100005130,"Exploring Determinants of Housing Prices: Take Beijing, Shanghai, Chongqing Housing Prices as Examples",2024.0,Proceedings of the 2nd International Conference on Financial Management and the Digital Economy,Qi An; Zhenglun Hu; Tian-Yi Ma,,0.0,https://doi.org/10.5220/0014879100005130
6e92d22246fa9883a3e7c89a428985128df6ddab,10.15818/ihss.2018.19.1.345,Analysis of long and short term influencing factors of Chinese housing prices - Considering market size and market characteristics,2018.0,,Sheng-Wen Zhao; Jungil Park,,0.0,https://doi.org/10.15818/ihss.2018.19.1.345
ba1601dcfd5d633c3e8a4afa2bd043a80598d06f,10.61784/wjebr3076,A HOUSING PRICE PREDICTION MODEL BASED ON BACKPROPAGATION NEURAL NETWORK,2025.0,World Journal of Economics and Business Research,,,0.0,https://doi.org/10.61784/wjebr3076
d0e3f2aa78de04bf20436c8f57ef3ae22a9f28ef,10.2139/ssrn.3770895,"House Price Estimation with Alternative Data and Machine Learning: A Case Study of Residential House Prices in Surrey, Canada",2021.0,Social Science Research Network,Da-Zhai Dong; Dongyi Wang,,0.0,https://doi.org/10.2139/ssrn.3770895
ca6ff999d046595f6c5a93bb4d89d22b894c5403,10.4108/eai.17-11-2023.2342672,House Price Prediction Based on Machine Learning --Taking Beijing House Price Data as an Example,2024.0,"Proceedings of the 5th International Conference on Economic Management and Model Engineering, ICEMME 2023, November 17–19, 2023, Beijing, China",Yuhong Xu,,0.0,http://eudl.eu/pdf/10.4108/eai.17-11-2023.2342672
b6aa2ce5d1d7bdc192a9da54779d311bb7b5e810,10.2139/ssrn.4549920,A Quantile Spatial-Autocorrelated Difference-in Differences (QSDID) Regression Analysis of Housing Price Changes Distributions Near Urban Rail Transit Stations,2023.0,Social Science Research Network,M. Diao; Daniel P. McMillen; T. Sing,,0.0,https://doi.org/10.2139/ssrn.4549920
9c2092fdcf05884505177de80451862874b1d9dc,10.4108/eai.5-8-2020.2301209,Determinant Factors of House Price Using Regression Analysis,2020.0,,Zeni Rusmawati; Rieska Maharani; Dedy Surahman,,0.0,https://doi.org/10.4108/eai.5-8-2020.2301209
be6ae1fe5f379c1f93d4a901418767ac34145360,10.56975/ijrar.v13i2.334066,House Price Prediction System Using Linear Regression,2026.0,International journal of research and analytical reviews,Saraswathi Akkapalli; V. S. Kumar; Nagaraju Kongari,,0.0,http://www.ijrar.org/download1.php?file=IJRAR26B2304.pdf
bf21de9b1f5f1428583e2c5ec9c177461647cfce,10.15818/ihss.2017.18.3.251,Inter-regional Spillover Effect Analysis of Housing Prices in China - focusing on time-varying Characteristics,2017.0,,Sheng-Wen Zhao; 정일 박,,0.0,https://doi.org/10.15818/ihss.2017.18.3.251
04ddb87254dfda2ac191cf941806a8a8f90a215e,10.2139/ssrn.3801618,Hedonic Price Index Number for New Blocks of Flats and Terraced Houses in Finland,2021.0,Social Science Research Network,Yrjö Vartia; Antti Suoperä; J. Vuorio,,0.0,https://doi.org/10.2139/ssrn.3801618
5e6352e6979d5c3adcde40933a8af5b1d2dde147,10.21608/rijcs.2025.402309.1367,"Evaluating the Impact of Resampling Methodologies on Multiple Regression Performance in Housing Price Analysis: A Comprehensive Empirical Study of Bootstrap, Stratified, and Systematic Sampling Techniques",2025.0,مجلة راية الدولية للعلوم التجارية,Dr.Heba Mahmoud Elsegai; Dr.Amr El Daba,,0.0,https://rijcs.journals.ekb.eg/article_441585_1b949c9dee0bdcad242157e3aeda39e8.pdf
a9bf441cc2610737fcd4fb88281f2535769c2b86,10.2139/ssrn.5426334,주택가격 기대심리의 특징과 시사점 (Characteristics and Implications of Housing Price Expectations),2025.0,Social Science Research Network,Wooseok Kim; In Do Hwang; Jae Won Lee,,0.0,https://doi.org/10.2139/ssrn.5426334
5b2925c4115ae077e3520830b821189ea292873e,10.5120/ijca2026926592,Integrated Framework for House Price and Price-Zone Prediction with Natural Language Processing Chatbot,2026.0,International Journal of Computer Applications,Rodiah S.; Diana Tri Susetianingtias; Eka Patriya,,0.0,https://doi.org/10.5120/ijca2026926592
ac4ab6e708ce7260a85be06dd8caf411c17b95f9,10.15396/eres2025_154,Determinants of housing price evolutions for the French sub-markets,2025.0,31st Annual European Real Estate Society Conference,Carmelo Micciche,,0.0,https://eres.architexturez.net/system/files/eres2025_154_paper_P_20250115173355_6632_k.pdf
c52ec0d2d3e4326743f17f4732cadbe804e12452,10.2139/ssrn.968073,Anticipated Capitalization of the Santiago Metro System on Housing Prices,2006.0,,Claudio A. Agostini; G. Palmucci,,0.0,https://doi.org/10.2139/ssrn.968073
27a46e9bfff4c6abfd04f61c9cc5346f386785b6,10.1068/a140609g,Featured graphic. Parental ‘choice’ and sociospatial segregation in a UK city: access to the best state-funded secondary schools for Black Somali pupils,2015.0,,S. Easton,,0.0,https://journals.sagepub.com/doi/pdf/10.1068/a140609g
62f2f0cfd57683ec1543970a1d07b515988358aa,10.4236/me.2025.163016,Economic and Social Attributes of Sold Homes Inside a House Price Bubble in Two Inner-City Neighbourhoods since 2020,2025.0,Modern Economy,A. Phipps,,0.0,https://www.scirp.org/pdf/me2025163_27203922.pdf
ca00e2f7b4ae0ec78bef7df6906587c6b1f4ff0c,10.46254/ap01.20210120,Compare Python Script and JMP JSL Script on the Housing Price Regression Models,2021.0,Proceedings of the International Conference on Industrial Engineering and Operations Management,Jason Chu; Mason Chen,,0.0,http://www.ieomsociety.org/china2021/papers/120.pdf
00aa0c2b8747a62ceaafa8bfb7c9cfe88f68fba3,10.2139/ssrn.4649168,Hedonic Price Index Number for Blocks of Flats and Terraced Houses in Finland,2023.0,Social Science Research Network,Antti Suoperä; Johanna Kaila; Henri Luomaranta,,0.0,https://doi.org/10.2139/ssrn.4649168
9d56372e8d98e104cc9870182b688c13914ac685,10.1109/icbds58040.2023.10346417,Comparative Analysis of Regression Techniques for Accurate House Price Prediction Using Machine Learning: A Statistical Analysis Method,2023.0,2023 IEEE International Conference on Blockchain and Distributed Systems Security (ICBDS),Tanu Patel; Jyoti Sahu; M. K,"Accurate house price prediction is crucial in real estate. This research aims to build a reliable house price prediction model using regression techniques. We evaluate model performance through 3-fold cross-validation and employ the mean R2 score as the evaluation metric, measuring predictive capacity. The top-performing model undergoes hyperparameter tuning. Our findings shed light on the effectiveness of regression techniques in house price prediction, identifying the most accurate model.",0.0,
doi_10_1061__asce_0733_9488_1999_125_1_55_,10.1061/(asce)0733-9488(1999)125:1(55),Forecasting House Rental Levels: Analytical Rent Model versus Neural Network,1999.0,Journal of Urban Planning and Development,Arun Kumar; Ankur Sinha; Nitin Tomar; Atanu Adhikari,,0.0,
11a42a7041dd072af502d2f5447e2e4876a0bffd,10.15396/eres2016_329,Overcoming the split incentive barrier in the rental housing market: Germany’s approach of green premiums in rent regulation.,2016.0,,M. Vaché,,0.0,
a812ae7903db53458b6a6770ab798efffe9f0b70,10.15396/eres2014_126,Assessing the impact of public amenities on house prices in the Greek islands,2014.0,,Dimitra Kavarnou; Anupam Nanda,,0.0,
581195405bf37ba6e1c94668e2456e9822faafd8,10.1177/0734242x251360560,Living near dumpsites: A machine learning and econometric assessment of how environmental conditions shape rental prices,2025.0,Waste Management Research,Cosimo Magazzino; Tanzila Akmal; Tulia Gattone,,0.0,
dd86149e74ddbdb565232bf65020c9f1acc0b54a,10.15396/eres2017_373,Determinants of rents in the French private rental housing sector,2017.0,,Camille Grivault; Ingrid Nappi-Choulet; J. le Gallo; Marie-Laure Breuillé; Kassoum Ayouba,,0.0,
613bb548ec32e59ff97057cc62a9f793acba62fd,10.1007/s10901-014-9421-6,The influence of urban and natural amenities on second home prices,2014.0,Journal of Housing and the Built Environment,Pia Nilsson,,0.0,
61f3be3ac1097e97c06dd8fc0da58b70f2bc40cc,10.22423/kreus.2021.14.1.89,The Impact of Station Attributes on Housing Prices in Seoul Metropolitan Region,2021.0,Konkuk Research Institute of Real Estate and Urban Studies,S. Bae; Jae-won Lee,,0.0,
5e973805983f52df2f7abc1402bcb00a24f89bb3,10.19172/kreaa.24.2.4,A Study on Housing Price Determinants in Metropolitan Cities Using Panel Analysis: Focusing on Private Consumption and SOC,2018.0,The Journal of Korea Real Estate Analysists Association,Junhyun Gong; Joo-Hyung Cho,,0.0,
c653c6384ea88a44bed6ee65ba75bf0384d146e7,10.25436/e2vc71,Examining geographical generalisation of machine learning models in urban analytics through street frontage classification and house price regression,2021.0,,S. Law; P. Jeszenszky; K. Yano,,0.0,
6b4f541caa0b5974948e7e5e6ec37aedd224b479,10.12677/pm.2025.1510244,Analysis of Factors Influencing Housing Prices in Hefei Based on LASSO Regression and Ridge Regression,2025.0,Pure Mathematics,Bang-Ji Wei,,0.0,
c44e35d2a3cc668e4f694b81448d6d26ab564897,10.61463/ijset.vol.13.issue2.434,House Price Prediction Using Machine Learning Teachniques,2025.0,International Journal of Scientific Engineering and Technology,P. Ajay,,0.0,
709f6f7e84bea6cad730a5d3e5f4458d3308b52f,10.25236/ajcis.020302,Analysis of Commodity Housing Price Based on Partial Least Squares Regression,2019.0,,Qimeng Tao,,0.0,
beade792d1a98d9b4d97a7dd3c2dcb463ec2509d,10.1007/978-981-33-6969-6_60,Assessment of Real House Price Using Machine Learning,2021.0,,S. Shukla; Samir Kumar Pandey; U. Bharadwaj; A. Yadav,,0.0,
700d36012270dbeae3c14f6a53db2c23dedeb41a,10.1061/9780784485910.128,The Impact of Shopping Mall Attributes and Social Media Dynamics on Residential Property Prices in Shanghai,2025.0,ICCREM 2024,Yi-Ming He,,0.0,
ed13100093d1e46e147a7080460517946ac465af,10.1007/978-3-030-36178-5_51,Forecasting Housing Prices by Using Artificial Neural Networks,2019.0,,T. Yeşil; Fatma Akyüz; U. Kose,,0.0,
dbc2167e7e54e6a92a33b89ebcf13d42f389117e,10.1504/ijcee.2025.147775,Forecasting real housing price returns of the USA using machine learning: the role of climate risks,2025.0,International Journal of Computational Economics and Econometrics,Bruno Tag Sales; Hudson S. Torrent; Rangan Gupta,,0.0,
694b8ff13bb200164e3aa835dc8c036aedca7a99,10.1007/978-3-032-30521-3_6,Determinants of Housing Prices in Portugal: A Municipal-Level Analysis,2026.0,Communication Systems and Applications,Maria J. Ferreira; Aldina Correia; Vanda Lima; Diogo Ribeiro,,0.0,
7e2862e10e9483d76eea88d53849c36600d4d5cc,10.1007/s12061-026-10008-z,Identifying Urban Centers and Modeling Nonlinear Housing Price Gradients in a Polycentric Metropolitan Region: Geographically Weighted Regression and Tree-Based Approaches in the Seoul Metropolitan Area,2026.0,Applied spatial analysis and policy,Changhyo Yi; Seongho Kim; Byung-hun Yun,,0.0,
48fe142597e1e95bb862d52f7402f47d07607407,10.15396/eres2024-202,The Central Business District Proximity Effect on Housing Prices: a Bucharest Case Study,2024.0,30th Annual European Real Estate Society Conference,C. Ciora; E. Ionașcu; I. Anghel,,0.0,
72d14d46adb2b6cca99a2e09a1bf07a1842c6d4f,10.22313/reik.2017.15.4.41,Predicting Housing Price Using Spatial Panel Data Models in Korea,2017.0,,Hae Jung Chun,,0.0,
baa7e49f00a98b4f9127b7bfab6df0234a98601f,10.11648/j.ijebo.20160406.12,Research on the Capitalization Effect of Local Public Goods in House Price and Its Spatial Heterogeneity in Zhengzhou,2017.0,,Xueying Zong; Ling-Yun Shi,,0.0,
b272bc0afd0d6ad1e6ba910be8ecf1b438d0f997,10.12677/sa.2023.124106,Research on the Housing Prices in Beijing Based ON Spatial Econometric Model,2023.0,Statistics and Application,文彦 曹,,0.0,
43db59c255b6815c44541c5fa334e6dfd62cffab,10.15396/eres2026_252,Nowcasting Transaction-Based House Price Indices Using Web-Scraped Listings and MIDAS Regression,2026.0,32nd Annual European Real Estate Society Conference,R. Trojanek; Luke Hartigan; Miriam Steurer; Norbert Pfeifer,,0.0,
42319d65a54991a13578f82bb92daf6ba3940daf,10.15396/eres2018_108,Public transport proximity impact on property value. Evidences from Bucharest residential market,2018.0,,S. V. Gomes; C. Ciora; I. Anghel,,0.0,
c39dd07aae77bd11a2176291e209c989ea85ee55,10.1007/s12061-026-09990-1,"The Impact of Urban Renewal on Neighborhood Housing Prices: A Spatial Effects and Differential Analysis in Nanjing City, China",2026.0,Applied spatial analysis and policy,Li-Fang Zhang; Jia-Jia Liao; Ying Li; Pin-Hua Jin; Shu-Qi Li; Ye-Ting Fan,,0.0,
9beafa6308c63566243aa947e4908a83952cc320,10.1007/978-3-030-62743-0_61,Spatial Econometric Analysis of House Prices in Guangdong Province Based on Big Data,2020.0,SPIoT,Yibing Lai; Qing-Hui Sun,,0.0,
059849a9595ee14ed145e6ac3f6b193ab874bdfe,10.15396/eres2012_254,Building age as a factor affecting spatial autocorrelation in housing prices,2012.0,,D. Lo,,0.0,
546d2806dd7a1be9c8f72a0e51edeaf9e59fab5a,10.19172/kreaa.31.1.3,Housing Price Determinants and Forecasts: The Case of Jeonbuk State Apartments,2025.0,Journal of the Korea Real Estate Analysts Association,Seulki Lee; Young Min Kim; W. Chung,,0.0,
599145ce04ff673c626c1591f97036cf7ed24689,10.12677/mm.2022.128128,A Study on the Characteristics and Influencing Factors of Housing Price Spatial Differentiation Based on POI Data—A Case Study of Chengdu City,2022.0,Modern Management,Yu-Run Fan,,0.0,
56867888762c2189d8b647d668e2497665fa9211,10.1007/978-981-15-3977-0_33,Capitalization of Urban Public Service Based on Urban Administrative Hierarchy: Evidence of Housing Prices from 281 Cities of China,2021.0,,Jun-Hua Chen; Siyu Chen; D. Zheng; Yanhui Hao,,0.0,
57874d59666a6ca0c32d32dd0110005216e04344,10.1063/5.0319431,Enhancing the prediction of house price using XGBoost regression with random forest to improve accuracy,2026.0,AIP Conference Proceedings,Dr. N. Uday Kiran; Gomathi,,0.0,
3ba6cf1bc1886f1dff53cfa2287537ccca8e624b,10.15396/eres2015_246,A study of English house price data with spatial dependence,2015.0,,I. Nase,,0.0,
3d81da232b1ab1fef90241f7ad6ca7b2ce21eba9,10.1007/978-3-662-46994-1_72,Distribution and Determinants of Housing Prices in Polycentric Mountainous Cities: The Case of Chongqing,2015.0,,Meng-Wei Wang; Yong Liu; Xiu-Hua Liu,,0.0,
24d668bf44a16a357d92a9d091c726e3069fa2d3,10.5593/sgemsocial2017/52/s19.025,PREDICTING HOUSE PRICES USING BOTH GEOGRAPHICALLY WEIGHTED REGRESSION AND KRIGING METHODS,2017.0,,A. Timofeeva,,0.0,
51e9fdbb63d3da2ef77dc8b5fb7c69f296b77f46,10.15396/eres2025_103,"Determinants of house prices in France: Demographics, Planning and Monetarization",2025.0,31st Annual European Real Estate Society Conference,R. Languillon; Arnaud Simon; Guillaume Toussaint; Mathieu Obertelli,,0.0,
2dff1bea50f2d99c79992fa392afb781fea68824,10.22645/udi.2020.6.30.033,DETERMINANTS OF APARTMENT RENTS IN THE SEOUL METROPOLITAN REGION: SPATIAL ECONOMETRIC APPROACHES,2020.0,,Dong-Sung Lee,,0.0,
cd23d14ced11ec6963003d0c3964f936f8ca5104,10.21447/jup.2020.11.3.109,Analysis of Determinants and Validation on Standard Official Housing Price in Seoul,2020.0,The Korean Association of Urban Policies,S. Jeong; Hoon-Gill Lee; Young-Min Lee; Joo-ah Lee,,0.0,
947ac0410b42b38c95d5757dcc414dabbd804c81,10.12677/ass.2020.98156,Application of Nonparametric Regression in House Price Forecast,2020.0,Advances in Social Sciences,Yun-Ying Lin,,0.0,
cb3624e149a1715fdd002911814ec1d7028b48e4,10.36700/kruma.2020.3.33.1.93,The Effect of Distance to Coastal Space by Type on Housing Price: Focused on Incheon,2020.0,,Jong-Woo Lee; Ah-Hyeon Bae; Sungjo Hong,,0.0,
d1955fc6989745c66031791e7d882bef45d56784,10.1007/978-3-032-32026-1_43,Geospatial Analysis of Short-Term Rentals as Determinant of Housing Prices in French Municipalities,2026.0,WorldCIST,Ricardo Barranco; Riccardo Curtale; Nuno Antonio; Sérgio Guerreiro,,0.0,
c49b3dbdfe0fb3be46d27f6b4e389aac3ceb4901,10.19172/kreaa.27.1.3,Impact Analysis of Housing Price Determinants in Redevelopment Area,2021.0,,Jae-won Lee; Sangyoub Lee,,0.0,
c686a1fcd40c5e48dd8545bcfe2e7e863e223d74,10.17208/jkpa.2017.10.52.6.91,A Study on the Features of the Typical Demand and Spatial Distribution according to Choice Model of the Apartment Maintenance in Seoul : Focused on Floor Area Ratio and Housing Price,2017.0,,In-Joung Ryu; Jin Nam,,0.0,
db4b323e4388d593ae6f47cf83203a61a6b058a5,10.1109/icmse.2008.4669128,The spatial distribution of real estate taxes impacts on housing price in China,2008.0,2008 International Conference on Management Science and Engineering 15th Annual Conference Proceedings,Xue-Jun Du; Ci-Fang Wu; Zhong-Hua Huang,,0.0,
d5398ebb21c08c2181e594fd3d849dfc54f73391,10.1117/12.837792,Spatial and temporal variations in residential housing prices in Beijing,2009.0,Other Conferences,Yan Zhang; Meng Lv; Z-H Yin,,0.0,
d3057570b4423eb398e5f2c51de36f619b2051ab,10.15396/eres2004_512,Determinants of inter-urban housing prices in Turkey,2004.0,,Berna Keskin; V. Dokmeci,,0.0,
d420268453d3cbe9917262e14afaaa4accf3a7ff,10.4135/9781036209353,Learn About Regularized Regression Using Python With Housing Price Data Retrieved From Kaggle,2025.0,,Vinaytosh Mishra,,0.0,
d8e9cd95db70ab98a13283330711f4a0d04616d6,10.22313/reik.2020.18.2.27,Dynamic Characteristics of Housing Price in Seoul Using Panel VAR Model,2020.0,,Hyun Mi Lee; Hae Jung Chun,,0.0,
99d9963d6c4294ddb5396a23121be92c7345ca00,10.1061/9780784413135.096,The Comparative Analysis of the Commercial Housing Prices in Beijing and Harbin Based on the Stepwise Regression Model,2013.0,,Peng-Yang Li; Beibei Shen,,0.0,
1e029313cdd3243ab89cea94636164ac43d4b257,10.56726/irjmets99694,VISION-DRIVEN HOUSE PRICE ESTIMATION USING CONVOLUTIONAL NEURAL NETWORKS,2026.0,International Research Journal of Modernization in Engineering Technology &amp; Science,,,0.0,
009f3e75cb2ceb764a21a798d89702840c03fec9,10.15396/eres2025_84,Predicting House Price Indices: A Machine Learning Approach Using Linked Listing and Transaction Data,2025.0,31st Annual European Real Estate Society Conference,"J. Schmid; He Cheng; Francisco Amaral; Zdrzalek, Jonas",,0.0,
7550d7ba89b985b2b39c6b27b73c62c6e26ec32f,10.1063/5.0277314,Evaluating the impact of features on house prices with lasso regression compare to polynomial regression,2025.0,AIP Conference Proceedings,Poondla Dharmendra; S. Saravanan,,0.0,
76f5a7ef14702b2e333ffa2278732fcef815ebcd,10.1061/9780784482308.087,Spatial Characteristics and Influencing Mechanism of Housing Price in Polycentric Mountainous City: A Case Study of Chongqing Central City,2019.0,ICCREM 2019,Chao Mao; Lin-Lin Zhang,,0.0,
6fb45a9ff50fa09de1a593122d0997eaa66cbc81,10.15781/t2125qs5c,Overview of machine learning methods in predicting house prices and its application in R,2018.0,,Wei-Ta Chen,,0.0,
7b071895cc806dc50e0a2ac12361e1edccb4d30e,10.5281/zenodo.3956571,Determining House Price Using Regression,2020.0,,A. Chakraborty,,0.0,
ac58a9aa7c116a06b40a1d3f58b2af3467d7db59,10.1049/icp.2025.4761,Machine learning-based forecasting of residential property prices in Mumbai,2026.0,IET Conference Proceedings,Rishi V. Badhe; Sujata R. Kolhe; Digvijay R. Borse; Mitesh M. Diwase,,0.0,
97c34145109223f193aa5a24a8bc139c90d2a128,10.1007/978-981-16-1335-7_41,House Price and Renovation Prediction Analysis Using Different Machine Learning Algorithms,2021.0,Sixth International Conference on Intelligent Computing and Applications,M. Karthik; M. Krishna; A. Posonia,,0.0,
679f855f7434eb89a11299e1dc7164f104e998c3,10.1063/5.0265756,Efficient house price prediction using deep belief network compared over random forest with improved accuracy,2025.0,AIP Conference Proceedings,K. S. M. Reddy; V. Karthick,,0.0,
3349beaa77a122ef206926764af55fc428deee28,10.1049/icp.2026.3178,Explainable machine learning driven analysis of housing price formation: a case study of Chengdu High-Tech Zone,2026.0,IET Conference Proceedings,Sha Lou; Ling Yang; De-Hua Zhang,,0.0,
7a63114e45c19f9ddb619d57022a27ff38405c50,10.22423/kreus.2022.14.2.83,Variation of Apartment Housing Price Affected by the Line Attributes of Seoul Metropolitan Urban Railway System,2022.0,Konkuk Research Institute of Real Estate and Urban Studies,S. Bae; Jae-won Lee,,0.0,
7935fa9bf891b0920519316d57ab68ff41882152,10.22313/reik.2018.16.4.179,An Analysis on the Effects of Household Consumption Expenditure on Household Characteristics According to the Change of Housing Price,2018.0,Residential Environment Institute Of Korea,Jin Woo Kim; S. Kim,,0.0,
7bf61f840c21fcab3e49b8fcce5153c45960ba9f,10.15396/eres2022_135,Amenities and Housing Price Growth in Short-Term-Rental Target Cities,2022.0,28th Annual European Real Estate Society Conference,Paloma Taltavull de La Paz; Albert Saiz,,0.0,
2788a8d968fdaa9dd1e3810ded0c93293bcea2c0,10.37642/jkremr.2021.24.10,A Study on Housing Price Prediction Using Machine Learning,2021.0,Journal of the Korea Real Estate Management Review,Hae-jung Chun,,0.0,
2d86170814c2a141ae7c0ea918ed08fe8b7ac6e1,10.15396/eres2024-207,Forecasting House Prices And Rents: Combining Dynamic Factor Models and Machine Learning,2024.0,30th Annual European Real Estate Society Conference,Farley Ishaak; Hilde Remøy; Peng Liu; Egbert Hardeman,,0.0,
61ab71967d3cb90e765c1b69e4c0d4e71f258085,10.1007/978-981-15-1420-3_110,"Prediction of Housing Prices Using Machine Learning, Time Series ARIMA Model and Artificial Neural Network",2020.0,,S. Mangaleswaran; S. Vigneshwari,,0.0,
572a109e217196301894dbcba22974293db8cdad,10.23977/gefhr2021.001,Prediction of house price based on genetic algorithm to optimize BP neural network,2021.0,,Xiao-Qiang Song; Xiaojing Zhang; Jing-Ru Chen,,0.0,
5182af40957682dc47575a45fed4e9cb4d623377,10.1080/00036846.2026.2669657,DSGE versus machine learning in housing price forecasting: evidence from Korea,2026.0,Applied Economics,Jongho Kang; Jihun Kim; Woojin Park; Doojin Ryu; Yong-Uk Song,,0.0,
f0c3ad26f55f1996137dcedfbbe778964f6e194a,10.15396/eres2011_320,House price determinants in Germany and Sweden - panel data analysis.,2011.0,,Sviatlana Anop,,0.0,
870a300f936a9ca994d90b12185abed776904b47,10.19172/kreaa.28.1.1,A Study on Effective Demand and Supply to Determine Housing Price: Panel Regression Model Analysis for 7 Metropolitan Cities,2022.0,The Journal of Korea Real Estate Analysists Association,Junhyun Gong,,0.0,
e78632e0b0989b741040b49c199b7db131ff956d,10.15396/eres2013_62,Measuring Determinants of House Prices: Listing Behaviour in Italian Real Estate Market,2013.0,,E. Fregonara; P. Semeraro,,0.0,
e6fcb848a876b58bc818572a9fa0790d6e3a3940,10.1016/j.apgeog.2026.104173,Non-linear distance decay of urban amenities in housing prices: Evidence from explainable artificial intelligence in a hyper-dense city,2026.0,Applied Geography,T. Gebeyehu; Peng-Yu Zhu,,0.0,
860f7c773228044bd121dd7375b8b6c24f97aa21,10.1063/5.0265920,Improved prediction accuracy of house price using decision tree over polynomial regression,2025.0,AIP Conference Proceedings,Pammi Chandu; N. B. Devi,,0.0,
f5053584cc181abf44c98f1e5adda60c55735f14,10.30776/jes.42.2.6,An Analysis of long-run determinants of housing prices: focusing on the sales price of Korean apartments,2024.0,Journal of Economic Studies,Junghee Park,,0.0,
18ee6023e73e19baf97f8305f30f6f2e806f5503,10.15396/eres2013_344,Spatial spillover effects of housing prices: An empirical study of Hong Kong,2013.0,,D. Lo,,0.0,
ace0c9fd9b86b90269f9eb81e7d56b54d9e296ee,10.5659/jaik_pd.2014.30.11.159,"The Effects of Apartment Complex Characteristics on Housing Value - Focused on Apartment complexes in Suseong-gu, Deagu City -",2014.0,,Keonggu Hong,,0.0,
5af5254946fa6fd330a2e28a31920cec8c38dc44,10.1109/icee.2012.1594,The Improvement of Residential Hedonic Price Model in Macro Aspect,2012.0,International Conference on E-Business and E-Government,Hong Shen; Zhi Wang; Zhen-Zhen Jiang,,0.0,
3db13f9e1270905cc117dfa89f4959bfb403027c,10.22313/reik.2019.17.4.59,The Effects of Household Characteristics on Consumption Expenditure by Housing Price Fluctuation Trends Using Multiple Regression Analysis,2019.0,Residential Environment Institute Of Korea,Jin Woo Kim; S. Kim,,0.0,
3fd72ce84179a8e5a85cef8e487a98f7efaa4811,10.56726/irjmets80330,FORECASTING HOUSE PRICE USING REGRESSION MODEL,2026.0,International Research Journal of Modernization in Engineering Technology &amp; Science,,,0.0,
3ae9ee70d434a26153b894ae057b604c99e014b1,10.1007/978-3-031-78943-4_23,Performance Analysis of Forecasting Residential Property Prices Through Ensemble Regression Approaches,2023.0,International Conference on Innovations in Bio-inspired Computing and Applications,M. Subramaniam; P. Selvakumar; Anusha Sakthivel; Madhumita Dharshinee Gunasekaran; K. Kumar; A. R. Mahendran,,0.0,
ed3434d792d9465e0c8695d6fb35a87d4f5d5c75,10.12815/kits.2023.22.1.39,Estimation of Economic Value of Public Housing Parking Lot : Focusing on the Hedonic Price Approach in the Case of Hanam City,2023.0,The Journal of The Korea Institute of Intelligent Transport Systems,Eunnyeong Heo; Sung-Won Choi,,0.0,
0ea3472086b77ecbffd3ff44e753ad4dfa356369,10.1007/s11146-016-9591-y,Cash and Distressed House Sales Price Discounts: Dual Sample Selection Spatial Interdependence Approaches,2016.0,Journal of real estate finance and economics,Alan Tidwell; A. Jauregui; V. Sah; Andrew Narwold,,0.0,
301d475e67f5f2177460ddaf8c327e1a63273df6,10.15396/eres2024-099,The Impact of Proximity to Enclosed Fresh Food Market on Housing Prices in Hong Kong,2024.0,30th Annual European Real Estate Society Conference,Wing-Chau Kwong; E. Liusman; Y. Wong,,0.0,
30244e109cd2d83f685be6613c68952e95014dc5,10.1109/iciii.2013.6703605,Determinants of intercity house price difference in Shaanxi Province,2013.0,"2013 6th International Conference on Information Management, Innovation Management and Industrial Engineering",B. Guo; Han-Yue Xiao; Liang-Hao Pan,,0.0,
2ba59ec9ca1aa1cac0fb071abc3dffca0828f1c6,10.1007/s10614-025-11162-1,A Stochastic Differential Oligopoly Game for Housing Characteristics in Investment Decisions,2025.0,Computational Economics,Bilgi Yilmaz,,0.0,
bb096e7f73d980ba8abc8d084d0ddf515236b708,10.2495/iceee140191,The application of housing hedonic price model using kernel principal component analysis,2014.0,,He-Yong Wang; Jinjiong Lan,,0.0,
2d3d6c497876dfd9b8966e3f062a4b5ebbf8f65d,10.22423/kreus.2017.9.2.111,"A Study on Determinants of Single-detached Housing Price -Focused on the Sales Price in Guro-gu, Seoul-",2017.0,,Kyutai Lee; H. Ha; Seon-Ju Song,,0.0,
doi_10_1609_aies_v9i4_43303,10.1609/aies.v9i4.43303,"The Geography of Algorithmic Judgment: LLM Intermediaries, Place Identity, and Racial Steering in Housing Search",2026.0,arXiv,Hana Samad; Trung Lam; Christoph Mügge-Durum; Michael Akinwumi,"Large language models (LLMs) are rapidly assuming an intermediary role in housing search through the integration of listing platforms within conversational interfaces, mediating access to information, search, and recommendations within urban settings. We expand on prior work on racial steering in LLMs by conducting a behavioral audit of seven open-weight and closed-source LLMs across four U.S. cities, testing location recommendations across three iterative prompting conditions that progressively add lifestyle preference context and reflect fair housing paired-testing methodologies. We find that steering is an emergent behavior of the model's interpretive license rather than primarily a static property. Steering results from the interaction of a user's identity, preference articulation, and the spatial logic that a model has internalized about learned representations of place, preference, and opportunity in a given city, and how different types of users relate to it. While steering was present, it was not uniform in direction or magnitude across evaluated conditions. Preference-conditioned testing often increased or reconfigured the number of models that exhibited steering behaviors",,https://arxiv.org/pdf/2606.06694v2
doi_10_1111_2041_210x_70140,10.1111/2041-210x.70140,Optimizing Image Capture for Computer Vision-Powered Taxonomic Identification and Trait Recognition of Biodiversity Specimens,2025.0,arXiv,Alyson East; Elizabeth G. Campolongo; Luke Meyers; S M Rayeed; Samuel Stevens; Iuliia Zarubiieva; Isadora E. Fluck; Jennifer C. Girón; Maximiliane Jousse; Scott Lowe; Kayla I Perry; Isabelle Betancourt; Noah Charney; Evan Donoso; Nathan Fox; Kim J. Landsbergen; Ekaterina Nepovinnykh; Michelle Ramirez; Parkash Singh; Khum Thapa-Magar; Matthew Thompson; Evan Waite; Tanya Berger-Wolf; Hilmar Lapp; Paula Mabee; Charles Stewart; Graham Taylor; Sydne Record,"1) Biological collections house millions of specimens with digital images increasingly available through open-access platforms. However, most imaging protocols were developed for human interpretation without considering automated analysis requirements. As computer vision applications revolutionize taxonomic identification and trait extraction, a critical gap exists between current digitization practices and computational analysis needs. This review provides the first comprehensive practical framework for optimizing biological specimen imaging for computer vision applications. 2) Through interdisciplinary collaboration between taxonomists, collection managers, ecologists, and computer scientists, we synthesized evidence-based recommendations addressing fundamental computer vision concepts and practical imaging considerations. We provide immediately actionable implementation guidance while identifying critical areas requiring community standards development. 3) Our framework encompasses ten interconnected considerations for optimizing image capture for computer vision-powered taxonomic identification and trait extraction. We translate these into practical implementation checklists, e",,https://arxiv.org/pdf/2505.17317v2
doi_10_1007_978_3_030_67661_2_10,10.1007/978-3-030-67661-2_10,Knowledge Elicitation using Deep Metric Learning and Psychometric Testing,2020.0,arXiv,Lu Yin; Vlado Menkovski; Mykola Pechenizkiy,"Knowledge present in a domain is well expressed as relationships between corresponding concepts. For example, in zoology, animal species form complex hierarchies; in genomics, the different (parts of) molecules are organized in groups and subgroups based on their functions; plants, molecules, and astronomical objects all form complex taxonomies. Nevertheless, when applying supervised machine learning (ML) in such domains, we commonly reduce the complex and rich knowledge to a fixed set of labels, and induce a model shows good generalization performance with respect to these labels. The main reason for such a reductionist approach is the difficulty in eliciting the domain knowledge from the experts. Developing a label structure with sufficient fidelity and providing comprehensive multi-label annotation can be exceedingly labor-intensive in many real-world applications. In this paper, we provide a method for efficient hierarchical knowledge elicitation (HKE) from experts working with high-dimensional data such as images or videos. Our method is based on psychometric testing and active deep metric learning. The developed models embed the high-dimensional data in a metric space where d",,https://arxiv.org/pdf/2004.06353v1
doi_10_1016_j_promfg_2020_05_141,10.1016/j.promfg.2020.05.141,Computer Vision Toolkit for Non-invasive Monitoring of Factory Floor Artifacts,2020.0,arXiv,Aditya M. Deshpande; Anil Kumar Telikicherla; Vinay Jakkali; David A. Wickelhaus; Manish Kumar; Sam Anand,"Digitization has led to smart, connected technologies be an integral part of businesses, governments and communities. For manufacturing digitization, there has been active research and development with a focus on Cloud Manufacturing (CM) and the Industrial Internet of Things (IIoT). This work presents a computer vision toolkit (CV Toolkit) for non-invasive digitization of the factory floor in line with Industry 4.0 requirements for factory data collection. Currently, technical challenges persist towards digitization of legacy systems due to the limitation for changes in their design and sensors. This novel toolkit is developed to facilitate easy integration of legacy production machinery and factory floor artifacts with the digital and smart manufacturing environment with no requirement of any physical changes in the machines. The system developed is modular, and allows real-time monitoring of production machinery. Modularity aspect allows the incorporation of new software applications in the current framework of CV Toolkit. To allow connectivity of this toolkit with manufacturing floors in a simple, deployable and cost-effective manner, the toolkit is integrated with a known manuf",,https://arxiv.org/pdf/2005.06037v1
doi_10_1016_j_future_2016_12_033,10.1016/j.future.2016.12.033,"Midgar: Detection of people through computer vision in the Internet of Things scenarios to improve the security in Smart Cities, Smart Towns, and Smart Homes",2017.0,arXiv,Cristian González García; Daniel Meana-Llorián; B. Cristina Pelayo G-Bustelo; Juan Manuel Cueva Lovelle; Néstor Garcia-Fernandez,"Could we use Computer Vision in the Internet of Things for using pictures as sensors? This is the principal hypothesis that we want to resolve. Currently, in order to create safety areas, cities, or homes, people use IP cameras. Nevertheless, this system needs people who watch the camera images, watch the recording after something occurred, or watch when the camera notifies them of any movement. These are the disadvantages. Furthermore, there are many Smart Cities and Smart Homes around the world. This is why we thought of using the idea of the Internet of Things to add a way of automating the use of IP cameras. In our case, we propose the analysis of pictures through Computer Vision to detect people in the analysed pictures. With this analysis, we are able to obtain if these pictures contain people and handle the pictures as if they were sensors with two possible states. Notwithstanding, Computer Vision is a very complicated field. This is why we needed a second hypothesis: Could we work with Computer Vision in the Internet of Things with a good accuracy to automate or semi-automate this kind of events? The demonstration of these hypotheses required a testing over our Computer Vis",,https://arxiv.org/pdf/1701.02632v3
doi_10_1016_j_iswa_2023_200176,10.1016/j.iswa.2023.200176,Propensity-to-Pay: Machine Learning for Estimating Prediction Uncertainty,2020.0,arXiv,Md Abul Bashar; Astin-Walmsley Kieren; Heath Kerina; Richi Nayak,"Predicting a customer's propensity-to-pay at an early point in the revenue cycle can provide organisations many opportunities to improve the customer experience, reduce hardship and reduce the risk of impaired cash flow and occurrence of bad debt. With the advancements in data science; machine learning techniques can be used to build models to accurately predict a customer's propensity-to-pay. Creating effective machine learning models without access to large and detailed datasets presents some significant challenges. This paper presents a case-study, conducted on a dataset from an energy organisation, to explore the uncertainty around the creation of machine learning models that are able to predict residential customers entering financial hardship which then reduces their ability to pay energy bills. Incorrect predictions can result in inefficient resource allocation and vulnerable customers not being proactively identified. This study investigates machine learning models' ability to consider different contexts and estimate the uncertainty in the prediction. Seven models from four families of machine learning algorithms are investigated for their novel utilisation. A novel concept",,https://arxiv.org/pdf/2008.12065v1
doi_10_1145_3570991_3571060,10.1145/3570991.3571060,DIGITOUR: Automatic Digital Tours for Real-Estate Properties,2023.0,arXiv,Prateek Chhikara; Harshul Kuhar; Anil Goyal; Chirag Sharma,"A virtual or digital tour is a form of virtual reality technology which allows a user to experience a specific location remotely. Currently, these virtual tours are created by following a 2-step strategy. First, a photographer clicks a 360 degree equirectangular image; then, a team of annotators manually links these images for the ""walkthrough"" user experience. The major challenge in the mass adoption of virtual tours is the time and cost involved in manual annotation/linking of images. Therefore, this paper presents an end-to-end pipeline to automate the generation of 3D virtual tours using equirectangular images for real-estate properties. We propose a novel HSV-based coloring scheme for paper tags that need to be placed at different locations before clicking the equirectangular images using 360 degree cameras. These tags have two characteristics: i) they are numbered to help the photographer for placement of tags in sequence and; ii) bi-colored, which allows better learning of tag detection (using YOLOv5 architecture) in an image and digit recognition (using custom MobileNet architecture) tasks. Finally, we link/connect all the equirectangular images based on detected tags. We s",,https://arxiv.org/pdf/2301.06680v1
doi_10_1016_j_spasta_2020_100470,10.1016/j.spasta.2020.100470,Maximum Likelihood Estimation of Spatially Varying Coefficient Models for Large Data with an Application to Real Estate Price Prediction,2020.0,arXiv,Jakob A. Dambon; Fabio Sigrist; Reinhard Furrer,"In regression models for spatial data, it is often assumed that the marginal effects of covariates on the response are constant over space. In practice, this assumption might often be questionable. In this article, we show how a Gaussian process-based spatially varying coefficient (SVC) model can be estimated using maximum likelihood estimation (MLE). In addition, we present an approach that scales to large data by applying covariance tapering. We compare our methodology to existing methods such as a Bayesian approach using the stochastic partial differential equation (SPDE) link, geographically weighted regression (GWR), and eigenvector spatial filtering (ESF) in both a simulation study and an application where the goal is to predict prices of real estate apartments in Switzerland. The results from both the simulation study and application show that the MLE approach results in increased predictive accuracy and more precise estimates. Since we use a model-based approach, we can also provide predictive variances. In contrast to existing model-based approaches, our method scales better to data where both the number of spatial points is large and the number of spatially varying covari",,https://arxiv.org/pdf/2001.08089v5
doi_10_1109_tmm_2017_2710804,10.1109/tmm.2017.2710804,Image Based Appraisal of Real Estate Properties,2016.0,arXiv,Quanzeng You; Ran Pang; Liangliang Cao; Jiebo Luo,"Real estate appraisal, which is the process of estimating the price for real estate properties, is crucial for both buys and sellers as the basis for negotiation and transaction. Traditionally, the repeat sales model has been widely adopted to estimate real estate price. However, it depends the design and calculation of a complex economic related index, which is challenging to estimate accurately. Today, real estate brokers provide easy access to detailed online information on real estate properties to their clients. We are interested in estimating the real estate price from these large amounts of easily accessed data. In particular, we analyze the prediction power of online house pictures, which is one of the key factors for online users to make a potential visiting decision. The development of robust computer vision algorithms makes the analysis of visual content possible. In this work, we employ a Recurrent Neural Network (RNN) to predict real estate price using the state-of-the-art visual features. The experimental results indicate that our model outperforms several of other state-of-the-art baseline algorithms in terms of both mean absolute error (MAE) and mean absolute percen",,https://arxiv.org/pdf/1611.09180v2
doi_10_1177_0739456x16664789,10.1177/0739456x16664789,New Insights into Rental Housing Markets across the United States: Web Scraping and Analyzing Craigslist Rental Listings,2016.0,arXiv,Geoff Boeing; Paul Waddell,"Current sources of data on rental housing - such as the census or commercial databases that focus on large apartment complexes - do not reflect recent market activity or the full scope of the U.S. rental market. To address this gap, we collected, cleaned, analyzed, mapped, and visualized 11 million Craigslist rental housing listings. The data reveal fine-grained spatial and temporal patterns within and across metropolitan housing markets in the U.S. We find some metropolitan areas have only single-digit percentages of listings below fair market rent. Nontraditional sources of volunteered geographic information offer planners real-time, local-scale estimates of rent and housing characteristics currently lacking in alternative sources, such as census data.",,https://arxiv.org/pdf/1605.05397v4
doi_10_1109_ieem_2017_8290312,10.1109/ieem.2017.8290312,Development of an Entropy-Based Feature Selection Method and Analysis of Online Reviews on Real Estate,2019.0,arXiv,Hiroki Horino; Hirofumi Nonaka; Elisa Claire Alemán Carreón; Toru Hiraoka,"In recent years, data posted about real estate on the Internet is currently increasing. In this study, in order to analyze user needs for real estate, we focus on ""Mansion Community"" which is a Japanese bulletin board system (hereinafter referred to as BBS) about Japanese real estate. In our study, extraction of keywords is performed based on the calculation of the entropy value of each word, and we used them as features in a machine learning classifier to analyze 6 million posts at ""Mansion Community"". As a result, we achieved a 0.69 F-measure and found that the customers are particularly concerned about the facility of apartment, access, and price of an apartment.",,https://arxiv.org/pdf/1904.11797v1
69da03c28aaa1e7d33a4ef729574d5b49121b468,10.1080/00036846.2019.1696937,Heterogeneity and fine wine prices: application of the quantile regression approach,2020.0,,Charles-Olivier Amédée-Manesme; Benoît Faye; É. Le Fur,"ABSTRACT This study addresses the price heterogeneity of the five first growths of Bordeaux. We apply the quantile regression (QR) approach with market segmentation based on wine bottle price quantiles. We compute the hedonic price of wine attributes for various price segments in the market. This approach is applied to a major dataset comprising approximately 50,000 transactions over the 2003–2017 period. The findings indicate that the relative hedonic prices of several wine attributes differ significantly among deciles. The implications of our results are manifold. Vintage and Parker grades have a strong impact on the variation in wine prices, and there is a hierarchy among the five first growths of Bordeaux. There is also a premium commanded by the reputation and experience of an auction house. Since the financial crisis of 2012–2013, investors have considered that the five first growths are overrated, save for the most expensive wines; for those most expensive ones, investors prefer scarcity to liquidity. These results are of import to several actors in the fine wine market: investors, for example, could use the findings herein to better diversify their wine portfolio, while auc",23.0,https://corpus.ulaval.ca/bitstreams/0f176fa3-dfaf-41b4-8314-5aa8bb310165/download
48704da357bdacd42ead54c7c242998536f513ad,10.2139/ssrn.3603837,Jane Beats Them All: Price Formation and Financial Returns to Investing in Rare Books,2020.0,Social Science Research Network,Heinrich W. Ursprung,"I report historical prices and estimate financial returns to investing in rare books. My sample consists of 25 fiction titles recommended by Clifton Fadiman in his 1960 Lifetime Reading Plan. Relying on prices realized at American and British auction houses between 1975 and 2018, I use hedonic regressions to estimate the average rate of return to each of the 25 titles. Jane Austen’s novel Pride and Prejudice tops the returns to all other titles. I then construct for the entire sample of rare books price indices based on various specifications with a view to identifying the most efficient way of computing rare book price indices for larger samples of books. Estimating the financial return to investing in rare books in general, I arrive for the boom period 1975-2007 at a real rate of return of about 4.6%, which exceeds similar estimates for investing in fine art. In a comparison with the returns in 1975-2007 of almost 9% from the US stock market, investing in rare books is justified only by substantial nonpecuniary returns. JEL-Codes: G110, Z110.",18.0,https://doi.org/10.2139/ssrn.3603837
fec340f80e723608a04e960494b35dfe4a69444b,10.2478/ceej-2025-0001,Comparative Analysis of Hedonic Wage and Discrete Choice Models in Valuing Job Safety,2025.0,Central European Economic Journal,Nan Zhang,"Abstract This is the first study to compare the hedonic wage and discrete choice models in the context of real job market choices. The hedonic wage method is the most widely adopted approach in estimating the value of marginal changes in mortality risks (or value of a statistical life, VSL). Alternatively, the discrete choice model offers a framework for valuing non-market goods, often used in choice experiments involving hypothetical job selection scenarios. This study employs both the hedonic wage and discrete choice models, using real market data from Taiwan‘s Panel Survey of Family Dynamics (PSFD 2016-2018), to examine workers‘ industry choices and infer their willingness to pay for job safety. By comparing the estimation results from the discrete choice model and the hedonic wage model, this study finds that the marginal willingness to pay (MWTP) for risk reduction estimated from discrete choice models is unreasonably large and therefore prefers the hedonic wage model in estimating the value of job safety. The findings of this study contribute to the literature comparing the hedonic model and the discrete choice model in evaluating environmental goods, which are mainly conduct",1.0,https://sciendo.com/pdf/10.2478/ceej-2025-0001
e4dbe798deeb7bb12347946d35d27dcf26003dd7,10.1111/jors.70027,Decomposing Variations in Quality of Life Through Amenities: Evidence From Korean Cities,2025.0,Journal of Regional Science,Heepyung Cho,"
 We estimate the quality of life (QOL) across Korean cities and decompose the cross‐sectional and temporal variations in QOL through amenities. Using administrative housing transaction data, a city's revealed‐preference QOL is estimated from its cost of living relative to its wage level. Seoul, the biggest city in Korea, had a significantly high QOL in 2019, and its QOL continuously increased from 2015 to 2019. Based on a hedonic framework, households are willing to pay more for denser, more educated, and warmer cities. Decomposing QOL using amenities chosen by LASSO, we find that a large portion of the cross‐sectional variation in QOL across cities is attributable to human‐made amenities. We also show that most temporal variation in QOL can be accounted for by amenities, particularly their increasing value.",1.0,https://doi.org/10.1111/jors.70027
e2cefa2df09279ce534acb1e9e0f5991e38a2e5f,10.1007/s10640-026-01110-4,Heterogeneous Individual Valuations of a Mild Climate,2026.0,Environmental and Resource Economics,Jan K. Brueckner,"This paper explores heterogeneous individual valuations of an important amenity, climate mildness, using a traditional Rosen-Roback empirical framework. It does so by including interaction terms between the amenity and worker characteristics in an hedonic wage regression that also includes a housing-price measure. The results suggest that non-young workers (those in the mid-age and old groups) value a mild climate more than do young workers, matching the usual view that the tolerance for cold weather declines with age. The findings also suggest that, like their highly educated counterparts, workers with low education levels also highly value a mild climate, with workers in the middle range of education having a lower valuation. These findings, which contradict the view that only better-off individuals care about amenities, could reflect the lower burden in mild weather of the manual work done by the less educated. In addition to presenting these empirical findings, the paper further contributes by presenting new analytics for the Rosen-Roback model in a setting with individual heterogeneity.",0.0,https://link.springer.com/content/pdf/10.1007/s10640-026-01110-4.pdf
bd2ebef2106505c66eee42290c5014da8679a71f,10.29321/maj.10.a00779,SOIL QUALITY VS FARMLAND PRICES IN THE NILGIRIS,1998.0,Madras Agricultural Journal,S. C; R. C; K. C,"The present investigation was carried out to analyse the influence of qualitative and quantitative attributes on farmland pricing behaviour in Katteri and Jagathala watersheds in the Nilgiris district, Tamil Nadu. A total number of 120 respondents was contacted for the present study. The results obtained from the hedonic regression clearly demonstrated the influence of soil depth, soil wetness, percentage of crop lands, soil quality etc. on farmland prices. The choice variables viz. community housing, farm size, population change, population density and the interaction terms involving population density and soil quality did not show any significant impact on crop land price. The study further showed that the above variables explained 82 percent change in farmland price. The findings obtained would be useful for the land owners in making investment decisions on soil conservation based on the significance of the influencing variables on farmland price. The outcome of the research findings can be used in deciding the level of subsidies to be extended by the Government for conservation projects.",0.0,http://masujournal.org/store_file/archive/85-7-9-433-437.pdf
e800891d7597db8e13065ac16fe182a4a38d6c38,10.1002/ajae.70060,Public lands and urban quality of life,2026.0,American Journal of Agricultural Economics,S. B. Akhundjanov; P. Jakus,"
 Federal and state‐owned public lands occupy a significant proportion of many U.S. urban regions, contributing to two highly‐valued, nontradable goods: viewscapes and outdoor recreational opportunities. Yet, public lands have not been adequately addressed in the urban quality‐of‐life (QOL) literature. We argue that much of the previous literature has (1) used a geographic level of aggregation that has not been extensive enough to capture all the public lands that influence wage and housing equilibria, (2) often defined public lands measures too narrowly and has excluded over 50% of public land influencing hedonic equilibria, and (3) has rarely attempted to control for public lands endogeneity when quasi‐experimental approaches are infeasible. Using GIS and Census data for U.S. urban areas, along with instruments rooted in the 19th century land disposal policies, we estimate how publicly owned federal and state lands contribute to urban QOL. Our preferred specifications are based on Bureau of Census defined Combined Statistical Areas that are linear in public land variables, and the results are robust regardless of geographic aggregation and model specification. Welfare calculation",0.0,