1# RECORD 23c746a3cf2275575136860a11ab1116e38d22282# TITLE: Modeling residential property prices in emerging climate-responsive urban markets: a hybrid modeling framework for Baidoa City-Somalia3# YEAR: 2025.0 VENUE: Frontiers in Built Environment DOI: 10.3389/fbuil.2025.16152294# AUTHORS: Mohamed Ibrahim Nor; S. N. Hussein5# PAGES: 14 CANDIDATE TABLE PAGES (1-based): []6# ABSTRACT: This study aims to examine the determinants of residential property prices in Baidoa’s climate-responsive real estate market. It investigates both linear and non-linear interactions among key variables to enhance property valuation models and inform urban development strategies. A hybrid-methods design was adopted, integrating a hedonic regression model with an artificial neural network (ANN) framework. The analysis utilizes a stratified random sample of 118 residential properties from the Baidoa Housing Survey, capturing diverse features such as property size, number of bedrooms, proximity to the central business district (CBD), safety, age, and air quality. Model performance was evaluated using standard metrics (e.g., R2, MSE, MAE) along with diagnostic tests and 5-fold cross-validation. The hedonic regression model explained 74.2% of the variance in property prices, with key variables showing significant influences. The ANN model further reduced prediction errors by approximately 20%, effectively capturing complex non-linear relationships among the predictors. Compared to the baseline linear hedonic regression model, the ANN achieved approximately a 20% reduction in mean squared error (MSE), with performance improvements validated through 5-fold cross-validation and supported by 95% confidence intervals. The results underscore the importance of strategic urban planning interventions such as improving neighborhood safety, enhancing infrastructure near the CBD, and boosting environmental quality. These insights offer practical guidelines for policymakers and real estate practitioners to foster sustainable urban growth and more accurate property valuations. This research uniquely combines traditional econometric methods with advanced machine learning techniques, yielding a hybrid model that outperforms conventional approaches. Its application to Baidoa—a rapidly urbanizing city facing distinct socio-environmental challenges—adds novel perspectives to climate-responsive real estate market analyses. The study bridges the gap between classic hedonic pricing theory and contemporary neural network methodologies, providing both theoretical and empirical contributions. It extends current understanding of urban housing market dynamics and offers a robust analytical framework that can be adapted to similar emerging urban contexts.789===== PAGE 1 (score 8, numeric-paren 0, table-words 1, var-words 6) =====1011TYPE Original Research12PUBLISHED 11 July 202513DOI 10.3389/fbuil.2025.161522914OPEN ACCESS15EDITED BY16Wei Lang,17Sun Yat-sen University, China18REVIEWED BY19Hasim Altan,20Prince Mohammad bin Fahd University,21Saudi Arabia22Tadeusz Jędrzejczyk,23Medical University of Gdansk, Poland24*CORRESPONDENCE25Mohamed Ibrahim Nor,26m.ibrahim@simad.edu.so27RECEIVED 20 April 202528ACCEPTED 23 June 202529PUBLISHED 11 July 202530CITATION31Nor MI and Hussein SN (2025) Modeling32residential property prices in emerging33climate-responsive urban markets: a hybrid34modeling framework for Baidoa City-Somalia.35Front. Built Environ. 11:1615229.36doi: 10.3389/fbuil.2025.161522937COPYRIGHT38© 2025 Nor and Hussein. This is an39open-access article distributed under the40terms of the Creative Commons Attribution41License (CC BY). The use, distribution or42reproduction in other forums is permitted,43provided the original author(s) and the44copyright owner(s) are credited and that the45original publication in this journal is cited, in46accordance with accepted academic practice.47No use, distribution or reproduction is48permitted which does not comply with49these terms.50Modeling residential property51prices in emerging52climate-responsive urban53markets: a hybrid modeling54framework for Baidoa55City-Somalia56Mohamed Ibrahim Nor1* and Shuaib Nour Hussein2571Institute of Climate and Environment (ICE), SIMAD University, Mogadishu, Somalia, 2Graduate School,58SIMAD University, Mogadishu, Somalia59This study aims to examine the determinants of residential property prices in60Baidoa’s climate-responsive real estate market. It investigates both linear and61non-linear interactions among key variables to enhance property valuation62models and inform urban development strategies. A hybrid-methods design63was adopted, integrating a hedonic regression model with an artificial neural64network (ANN) framework. The analysis utilizes a stratified random sample of 11865residential properties from the Baidoa Housing Survey, capturing diverse features66such as property size, number of bedrooms, proximity to the central business67district (CBD), safety, age, and air quality. Model performance was evaluated68using standard metrics (e.g., R2, MSE, MAE) along with diagnostic tests and 5-69fold cross-validation. The hedonic regression model explained 74.2% of the70variance in property prices, with key variables showing significant influences.71The ANN model further reduced prediction errors by approximately 20%,72effectively capturing complex non-linear relationships among the predictors.73Compared to the baseline linear hedonic regression model, the ANN achieved74approximately a 20% reduction in mean squared error (MSE), with performance75improvements validated through 5-fold cross-validation and supported by7695% confidence intervals. The results underscore the importance of strategic77urban planning interventions such as improving neighborhood safety, enhancing78infrastructure near the CBD, and boosting environmental quality. These insights79offer practical guidelines for policymakers and real estate practitioners to80foster sustainable urban growth and more accurate property valuations. This81research uniquely combines traditional econometric methods with advanced82machine learning techniques, yielding a hybrid model that outperforms83conventional approaches. Its application to Baidoa—a rapidly urbanizing city84facing distinct socio-environmental challenges—adds novel perspectives to85climate-responsive real estate market analyses. The study bridges the gap86between classic hedonic pricing theory and contemporary neural network87methodologies, providing both theoretical and empirical contributions. It88extends current understanding of urban housing market dynamics and offers89Frontiers in Built Environment900191frontiersin.org92