1# RECORD c2b6a75d94d2ce27d185f96ffbc7fa5ee377ffff2# TITLE: AN INTERPRETABLE ANALYSIS OF RESIDENTIAL APARTMENT PRICES IN TASHKENT USING LINEAR REGRESSION3# YEAR: 2025.0 VENUE: III-an’anaviy xalqaro ilmiy-amaliy konferensiya materiallari DOI: 10.65164/zrcja7954# AUTHORS: Abdurasul Bobonazarov5# PAGES: 6 CANDIDATE TABLE PAGES (1-based): []6# ABSTRACT: 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.789===== PAGE 1 (score 8, numeric-paren 0, table-words 0, var-words 8) =====1011 12433 13AN INTERPRETABLE ANALYSIS OF RESIDENTIAL APARTMENT PRICES IN 14TASHKENT USING LINEAR REGRESSION 15Abdurasul Bobonazarov, Khamidulla Khabibullaev 16Turin Polytechnic University in Tashkent 17e-mail: a.bobonazarov@polito.uz 18 19 20 21Abstract: Accurate understanding of residential housing price formation is essential for urban 22planning, real estate market transparency, and informed decision-making by buyers and sellers. In 23recent years, online real estate platforms have emerged as valuable sources of large-scale market data; 24however, empirical studies based on local housing data in Uzbekistan remain limited. This paper 25presents an interpretable analysis of residential apartment prices in Tashkent using multiple linear 26regression applied to real listing data collected from an online real estate platform. 27The dataset consists of 7,421 apartment listings and includes structural characteristics 28(apartment size, number of rooms, floor level, and total building floors) as well as geographic 29attributes represented by latitude and longitude. A systematic preprocessing pipeline involving outlier 30removal and train–test splitting is employed. Several linear models, including ordinary least squares, 31Ridge, Lasso, and Elastic Net regression, are evaluated and compared using standard performance 32metrics. 33Experimental results show that all linear variants achieve comparable performance, with an R² 34value of approximately 0.67 on the test set, indicating that a substantial proportion of price variability 35can be explained using linear relationships. The analysis highlights the dominant role of spatial 36location and apartment size in price formation, while regression coefficients provide clear 37interpretability of individual feature effects. Residual analysis confirms the absence of systematic 38prediction bias, with increased variability observed for higher-priced apartments. 39Overall, the findings demonstrate that simple and interpretable linear regression models provide 40a robust baseline for residential price analysis in the Tashkent housing market. The study offers 41practical insights for market participants and lays the groundwork for future extensions incorporating 42nonlinear and spatially explicit modeling approaches. 43Keywords: Residential property prices; Linear regression; Housing market analysis; Spatial 44factors; Real estate listings; Data-driven analysis; Tashkent housing market. 45INTRODUCTION 46Residential housing markets play a critical role in urban economic development, influencing 47household welfare, investment decisions, and city planning strategies. Understanding the factors that 48determine apartment prices is therefore essential for policymakers, real estate professionals, and 49individual buyers. In recent years, the rapid growth of online real estate platforms has enabled access 50to large volumes of market data, creating new opportunities for data-driven analysis of housing price 51formation. 52A common and well-established approach to housing price analysis is the use of hedonic pricing 53models, where property prices are expressed as a function of structural, locational, and environmental 54attributes. Among these approaches, multiple linear regression remains widely used due to its 55transparency, ease of interpretation, and solid theoretical foundation. Several studies have 56demonstrated that linear regression models can effectively capture key price determinants such as 57apartment size, number of rooms, building characteristics, and location variables [1-3]. Despite the 58growing popularity of complex machine learning and deep learning models, linear regression 59continues to serve as a strong baseline for housing price analysis, particularly when interpretability is 60a primary objective [4,5]. 61Recent literature has increasingly explored advanced regression techniques and machine 62learning models for housing price prediction, including regularized linear models, ensemble methods, 63