1# RECORD 219a22b5256e870526111fcb3590a1cdecfe72402# TITLE: Comparative Analysis of Advanced Models for Predicting Housing Prices: A Review3# YEAR: 2025.0 VENUE: Urban Science DOI: 10.3390/urbansci90200324# AUTHORS: Inmaculada Moreno-Foronda; M. Sánchez-Martínez; M. Pareja-Eastaway5# PAGES: 20 CANDIDATE TABLE PAGES (1-based): []6# ABSTRACT: Understanding the determinants of housing price movements is an ongoing subject of debate. Estimating these determinants becomes a valuable tool for predicting price trends and mitigating the risks of market volatility. This article presents a systematic review analyzing studies that compare various machine learning (ML) tools with hedonic regression, aiming to assess whether real estate price predictions based on mathematical techniques and artificial intelligence enhance the accuracy of hedonic price models used for valuing residential properties. ML models (neural networks, decision trees, random forests, among others) provide high predictive capacity and greater explanatory power due to the better fit of their statistical measures. However, hedonic regression models, while less precise, are more robust, as they can identify the housing attributes that most influence price levels. These attributes include the property’s location, its internal features, and the distance from the property to city centers.789===== PAGE 1 (score 14, numeric-paren 0, table-words 0, var-words 14) =====1011Academic Editor: Maria12Rosaria Guarini13Received: 23 December 202414Revised: 23 January 202515Accepted: 29 January 202516Published: 31 January 202517Citation: Moreno-Foronda, I.;18Sánchez-Martínez, M.-T.;19Pareja-Eastaway, M. Comparative20Analysis of Advanced Models for21Predicting Housing Prices: A Review.22Urban Sci. 2025, 9, 32. https://23doi.org/10.3390/urbansci902003224Copyright: © 2025 by the authors.25Licensee MDPI, Basel, Switzerland.26This article is an open access article27distributed under the terms and28conditions of the Creative Commons29Attribution (CC BY) license30(https://creativecommons.org/31licenses/by/4.0/).32Review33Comparative Analysis of Advanced Models for Predicting34Housing Prices: A Review35Inmaculada Moreno-Foronda 136, María-Teresa Sánchez-Martínez 137and Montserrat Pareja-Eastaway 2,*38139Department of Applied Economics, University of Granada, 18011 Granada, Spain;40inmamf@correo.ugr.es (I.M.-F.); tsanchez@ugr.es (M.-T.S.-M.)41242Department of Economics, University of Barcelona, 08034 Barcelona, Spain43*44Correspondence: mpareja@ub.edu45Abstract: Understanding the determinants of housing price movements is an ongoing46subject of debate. Estimating these determinants becomes a valuable tool for predicting47price trends and mitigating the risks of market volatility. This article presents a systematic48review analyzing studies that compare various machine learning (ML) tools with hedonic49regression, aiming to assess whether real estate price predictions based on mathematical50techniques and artificial intelligence enhance the accuracy of hedonic price models used51for valuing residential properties. ML models (neural networks, decision trees, random52forests, among others) provide high predictive capacity and greater explanatory power due53to the better fit of their statistical measures. However, hedonic regression models, while54less precise, are more robust, as they can identify the housing attributes that most influence55price levels. These attributes include the property’s location, its internal features, and the56distance from the property to city centers.57Keywords: machine learning; hedonic prices; prediction; prices; housing581. Introduction59Real estate assets serve a dual purpose: they are an essential consumer good, and their60acquisition represents the most significant investment in the portfolios of most households.61Therefore, a thorough understanding of housing price predictability is essential for making62informed investment decisions and ensuring the efficient allocation of assets.63Predicting housing prices is crucial not only for households and other market partici-64pants but also for policy design, economic research, and the broader economy, given the65macroeconomic significance of residential price trends [1]. Sustained increases in housing66prices pose a serious problem in virtually all countries, as they make it difficult for many67citizens to access housing.68However, predicting housing prices is complex due to the significant challenges in69measuring all the intrinsic and extrinsic characteristics that form part of a property [2].70Among the different variables/factors that influence housing prices are, on the one hand,71the internal variables or micro factors, which refer to the structural characteristics of72the property itself. These include specific features of the property, such as size, number73of rooms, or type of construction, as well as specific characteristics of the building and74common areas that are part of it (elevator, natural gas installations, swimming pool, or75park, among others). On the other hand, there are external variables or macro factors76that encompass all types of location and neighborhood attributes of the property, among77which accessibility and distance to essential services, the economic and social conditions of78the district where it is located, or the particularities of urbanization of the surroundings,79Urban Sci. 2025, 9, 3280https://doi.org/10.3390/urbansci902003281