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

Mohamed Ibrahim Ibrahim Nor ^1,2* Buba Audu ³ Abdullahi Dahir Mohamed ⁴

• ¹ SIMAD University, Mogadishu, Somalia
• ² Institute of Climate and Environment (ICE), Mogadishu, Somalia
• ³ Buruuj Construction and Real Estate, Mogadishu, Somalia
• ⁴ Hormuud University, Mogadishu, Somalia

This study aims to investigate the influence of property value, property characteristics, cost of living, political stability, essential services, and environmental factors on residential property rental prices in Baidoa city. The research provides a comparative analysis of different modeling approaches to improve rental price forecasting. The study employs a dual-method approach, integrating hedonic regression analysis and artificial neural network (ANN) models to analyze rental values. The dataset includes key variables such as the number of bedrooms, essential services, cost of living, and environmental conditions. The predictive performance and interpretability of both models are compared to assess their effectiveness in rental price estimation. The findings indicate that rental prices are significantly influenced by the number of bedrooms, essential services such as electricity, cost of living, and environmental conditions. However, political stability and displacement were found not to have significant effects. While hedonic regression models provided clear and interpretable insights into direct predictors, ANN models demonstrated superior prediction accuracy by capturing nonlinear interactions. The ANN model's mixed performance, with 53% of cases underperforming and 47% exceeding predictions, highlights the need for improved precision in forecasting. The study underscores the importance of a mixed-method approach for rental price forecasting. Policymakers should integrate econometric and machine learning models to refine housing policies and ensure fair market regulations. Investors and property owners can utilize these findings to optimize rental pricing strategies. Additionally, real estate practitioners can benefit from data-driven decision-making, enhancing investment outcomes in emerging markets. This research contributes to the real estate valuation literature by bridging traditional econometric analysis with advanced machine learning techniques. The study validates the applicability of hedonic pricing and information asymmetry theories within an emerging market context. By incorporating economic and environmental factors into both models, the research provides a more comprehensive understanding of rental price determinants.