Machine Learning Price Prediction on Green Building Prices

Abstract

In the era of Industry 4.0, Machine Learning models have become increasingly popular and influential as they are often used to solve different prediction and classification problems in various industries and including the real estate industry. However, to obtain the best combination of these approaches for a good of Green Building (GB) price predictor model, it is important to be identify and require extensive empirical experiments work by identifying the best parameters configurations, techniques, and algorithms. GB is known as a potential approach to improve the performance of the building. Where in Malaysia involving five distinctly different assessment criteria namely, Energy Efficiency (EE), Indoor Environment Quality (EQ), Sustainable Site Planning & Management (SM), Material & Resources (MR), Water Efficiency (WE). This paper provides a report of an empirical study that model building price prediction based on GB dataset that covered Kuala Lumpur District, Malaysia. The experiments used five common algorithms namely Linear Regression, Decision Tree, Random Forest, Ridge and Lasso that tested on a set of real estate building datasets. The result showed the Decision Tree Regressor outperforms the other four algorithms on the test dataset.