Application of machine learning in analysing historical and non-historical characteristics of heritage pre-war shophouses / Nur Shahirah Ja’afar and Junainah Mohamad

Real estate is complex and its value is influenced by many characteristics. However, the current practice in Malaysia shows that historical characteristics have not been given primary consideration in determining the value of heritage property. Thus, the accuracy of the values produced is questionable. This paper aims to see whether the historical characteristics give significance values toward shophouses at North-East of Penang Island, Malaysia. Several Machine Learning algorithms have been developed, namely Random Forest Regressor, Decision Tree Regressor, Lasso Regressor, Ridge Regressor and Linear Regressor. The result shows that the Random Forest Regressor with historical characteristics is the best fitting model with higher values of adjusted R-Squared (R²) and lowest value of Root Mean Square Error. This indicates the historical characteristics contribute to the significance value of heritage property. By considering historical characteristics, it can contribute to the accuracy of the value predicted.