Predicting House Rental Prices in Ghana Using Machine Learning

TL;DR

This paper evaluates machine learning models for predicting house rental prices in Ghana, finding CatBoost most effective with an $R^2$ of 0.876, and identifies key features influencing prices.

Contribution

It introduces a comprehensive approach to housing price prediction in Ghana using advanced machine learning models, highlighting the superior performance of CatBoost.

Findings

CatBoost achieved an $R^2$ of 0.876.

Location and property features are key price drivers.

The study offers insights for real estate stakeholders.

Abstract

This study investigates the efficacy of machine learning models for predicting house rental prices in Ghana, addressing the need for accurate and accessible housing market information. Utilising a comprehensive dataset of rental listings, we trained and evaluated various models, including CatBoost, XGBoost, and Random Forest. CatBoost emerged as the best-performing model, achieving an $R^2$ of 0.876, demonstrating its ability to effectively capture complex relationships within the housing market. Feature importance analysis revealed that location-based features, number of bedrooms, bathrooms, and furnishing status are key drivers of rental prices. Our findings provide valuable insights for stakeholders, including real estate professionals, investors, and policymakers, while also highlighting opportunities for future research, such as incorporating temporal data and exploring regional variations.