Investigating the impact of property characteristics, cost of living, and environmental factors on rental prices in Baidoa’s climate-affected real estate market: a hybrid approach using hedonic regression and neural networks DOI Creative Commons
Mohamed Ibrahim Nor,

Buba Audu,

Ateesha F. Mohamed

et al.

Frontiers in Sustainable Cities, Journal Year: 2025, Volume and Issue: 7

Published: March 19, 2025

Introduction Understanding the determinants of residential rental prices is crucial for policymakers, investors, and real estate practitioners. This study investigates influence property value, characteristics, cost living, political stability, essential services, environmental factors on in Baidoa city. Additionally, research compares different modeling approaches to enhance price forecasting. Methods A dual-method approach was employed, integrating hedonic regression analysis artificial neural network (ANN) models analyze values. The dataset includes key variables such as number bedrooms, conditions. predictive performance interpretability both were assessed determine their effectiveness estimation. Results findings reveal that are significantly influenced by services (e.g., electricity), However, stability displacement did not exhibit significant effects. While provided clear, interpretable insights into direct predictors, ANN captured nonlinear interactions demonstrated superior prediction accuracy. Nevertheless, model exhibited mixed performance, with 53% cases underperforming 47% exceeding predictions, highlighting need improved precision Discussion emphasizes importance a mixed-method Policymakers should integrate econometric machine learning refine housing policies ensure fair market regulations. Investors owners can leverage these optimize pricing strategies, while practitioners benefit from data-driven decision-making. contributes valuation literature bridging traditional advanced techniques. validates applicability information asymmetry theories within an emerging context, offering more comprehensive understanding determinants.

Language: Английский

Investigating the impact of property characteristics, cost of living, and environmental factors on rental prices in Baidoa’s climate-affected real estate market: a hybrid approach using hedonic regression and neural networks DOI Creative Commons
Mohamed Ibrahim Nor,

Buba Audu,

Ateesha F. Mohamed

et al.

Frontiers in Sustainable Cities, Journal Year: 2025, Volume and Issue: 7

Published: March 19, 2025

Introduction Understanding the determinants of residential rental prices is crucial for policymakers, investors, and real estate practitioners. This study investigates influence property value, characteristics, cost living, political stability, essential services, environmental factors on in Baidoa city. Additionally, research compares different modeling approaches to enhance price forecasting. Methods A dual-method approach was employed, integrating hedonic regression analysis artificial neural network (ANN) models analyze values. The dataset includes key variables such as number bedrooms, conditions. predictive performance interpretability both were assessed determine their effectiveness estimation. Results findings reveal that are significantly influenced by services (e.g., electricity), However, stability displacement did not exhibit significant effects. While provided clear, interpretable insights into direct predictors, ANN captured nonlinear interactions demonstrated superior prediction accuracy. Nevertheless, model exhibited mixed performance, with 53% cases underperforming 47% exceeding predictions, highlighting need improved precision Discussion emphasizes importance a mixed-method Policymakers should integrate econometric machine learning refine housing policies ensure fair market regulations. Investors owners can leverage these optimize pricing strategies, while practitioners benefit from data-driven decision-making. contributes valuation literature bridging traditional advanced techniques. validates applicability information asymmetry theories within an emerging context, offering more comprehensive understanding determinants.

Language: Английский

Citations

0