An Ensemble Approach for Predicting The Price of Residential Property

Abstract

Today, determining the rent for a property is crucial given that the cost of housing increases annually. Our future generation requires a straightforward method to forecast future property rent. Various factors influence the price of a house, including its physical condition, location, and size. This study utilizes web scraping techniques to collect data from pertinent websites for analytical and predictive purposes. Employing an ensemble strategy, the research predicts housing rents in Bangalore. Seven ensemble models of machine learning algorithms, such as Random Forest, XGBoost, Support Vector Regression (SVR), and Decision Trees, are integrated into the analysis. The objective was to determine the optimal model by evaluating their performance scores obtained from a comparative analysis.