Prediction of Apartment Price Considering Socio Economic and Crime Rates Factors in DKI Jakarta

Abstract

Investing in real estate properties in Indonesia is highly lucrative due to their consistent appreciation in value. Amongst the various property types, apartments are particularly favored for investment in limited land space. However, determining the value of apartments is often subjective and lacks quantitative measures. To address this issue, this study develops prediction models to predict rental prices and asset value based on apartment specifications, socio-economic factors, and crime rates. Machine learning models employed include Random Forest, Decision Tree, and Gradient Boosting Machine. The findings show Gradient Boosting Machine exhibits the highest accuracy in predicting apartment rental and sale prices, achieving R² values of 0.9230 and 0.8460, respectively. The study also highlights the significant influence of socio-economic factors and crime rates on the performance of the models, contributing between 0.09 and 0.22 with an average of 0.14, as indicated by the improved R² values. This study demonstrate that these models can be valuable tools for real estate investors and professionals seeking quantitative measures to determine the value of apartments. By incorporating apartment specifications, socio-economic factors, and crime rates, the models can provide objective insights into the potential rental income and asset value of apartments.