Optimization of Prediction Results Based on Ensemble Methods of Machine Learning

Abstract

Analysis and evaluation of socio-economic processes based on intellectual models leads to effective results. The use of intelligent systems for real estate valuation and price prediction is very important nowadays. As a result, investors can effectively finance their projects. The main objective of this study is to develop Voting ensemble regression and Gradient Boosting Algorithms based on several machine learning algorithms to predict real property prices. Mean absolute deviation (MAE), root mean squared error (RMSE) and coefficient of determination (R-squared) were calculated to check the accuracy of the developed model and algorithms. Algorithms developed on the basis of ensemble methods have been found to give much better results than among the standalone Machine learning models. Based on the developed model and algorithms, an effective method of real estate assessment and price prediction for investors is proposed.