House Rent Prediction Using Machine Learning in Bangladesh

AbstractBangladesh's house rental market has grown more dynamic as a result of the country's fast urbanisation, population expansion, and economic volatility. Rent prediction accuracy is still a problem for both landlords and tenants. Using publicly accessible statistics, this study uses machine learning techniques to forecast residential rental costs in Bangladesh's largest cities. Among the algorithms used were Gradient Boosting, Random Forest, and Linear Regression. In terms of capturing the intricate correlations between property attributes and rent pricing, the Gradient Boosting model performed the best, achieving an R2 score of 0.94. When it comes to rental valuation, this methodology can help stakeholders make well-informed judgements.