# RECORD 219a22b5256e870526111fcb3590a1cdecfe7240
# TITLE: Comparative Analysis of Advanced Models for Predicting Housing Prices: A Review
# YEAR: 2025.0  VENUE: Urban Science  DOI: 10.3390/urbansci9020032
# AUTHORS: Inmaculada Moreno-Foronda; M. Sánchez-Martínez; M. Pareja-Eastaway
# PAGES: 20  CANDIDATE TABLE PAGES (1-based): []
# 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.


===== PAGE 1 (score 14, numeric-paren 0, table-words 0, var-words 14) =====

Academic Editor: Maria
Rosaria Guarini
Received: 23 December 2024
Revised: 23 January 2025
Accepted: 29 January 2025
Published: 31 January 2025
Citation: Moreno-Foronda, I.;
Sánchez-Martínez, M.-T.;
Pareja-Eastaway, M. Comparative
Analysis of Advanced Models for
Predicting Housing Prices: A Review.
Urban Sci. 2025, 9, 32. https://
doi.org/10.3390/urbansci9020032
Copyright: © 2025 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license
(https://creativecommons.org/
licenses/by/4.0/).
Review
Comparative Analysis of Advanced Models for Predicting
Housing Prices: A Review
Inmaculada Moreno-Foronda 1
, María-Teresa Sánchez-Martínez 1
and Montserrat Pareja-Eastaway 2,*
1
Department of Applied Economics, University of Granada, 18011 Granada, Spain;
inmamf@correo.ugr.es (I.M.-F.); tsanchez@ugr.es (M.-T.S.-M.)
2
Department of Economics, University of Barcelona, 08034 Barcelona, Spain
*
Correspondence: mpareja@ub.edu
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.
Keywords: machine learning; hedonic prices; prediction; prices; housing
1. Introduction
Real estate assets serve a dual purpose: they are an essential consumer good, and their
acquisition represents the most significant investment in the portfolios of most households.
Therefore, a thorough understanding of housing price predictability is essential for making
informed investment decisions and ensuring the efficient allocation of assets.
Predicting housing prices is crucial not only for households and other market partici-
pants but also for policy design, economic research, and the broader economy, given the
macroeconomic significance of residential price trends [1]. Sustained increases in housing
prices pose a serious problem in virtually all countries, as they make it difficult for many
citizens to access housing.
However, predicting housing prices is complex due to the significant challenges in
measuring all the intrinsic and extrinsic characteristics that form part of a property [2].
Among the different variables/factors that influence housing prices are, on the one hand,
the internal variables or micro factors, which refer to the structural characteristics of
the property itself. These include specific features of the property, such as size, number
of rooms, or type of construction, as well as specific characteristics of the building and
common areas that are part of it (elevator, natural gas installations, swimming pool, or
park, among others). On the other hand, there are external variables or macro factors
that encompass all types of location and neighborhood attributes of the property, among
which accessibility and distance to essential services, the economic and social conditions of
the district where it is located, or the particularities of urbanization of the surroundings,
Urban Sci. 2025, 9, 32
https://doi.org/10.3390/urbansci9020032