House Price Prediction Using Ensemble Learning Techniques

Abstract

With the rapid increase in the world population, people's demands for houses are increasing day by day. Housing markets have an important place in the economy of a country, and this is also an important indicator of the welfare level of society. Accordingly, it is necessary to examine and change the prices of the houses in the housing sector in detail. From this point of view, in this study, price estimation will be made using machine learning techniques by making use of the public dataset containing information about houses with different characteristics in the district of California. The resulting house price estimation will be developed with ensemble learning techniques. According to the results obtained, the AdaBoost Regressor ensemble model is obtained with the best performance value of 0.118 RMSE. Finally, the project will be integrated into the web interface for house price estimation.