Real estate price forecasting based on SVM optimized by PSO

Abstract

The real estate market has a close relationship with us. It plays a very important role in economic development and people's fundamental needs. So, accurately forecasting the future real estate prices is very significant. Support vector machine (SVM) is a novel type of learning machine which has been proved to be available in solving the problems of limited sample learning, nonlinear regression, as well as, better to overcome the “curse of dimensionality”. However, the selected parameters determine its learning and generalization. Thus, it is essential to determine the parameters of SVM. Compared to ant colony algorithm, grid algorithm, genetic algorithm, particle swarm optimization (PSO) is powerful and easy to implement. Therefore, in the study, real estate price forecasting by PSO and SVM is proposed in the paper, where PSO is chosen to determine the parameters of SVM. The real estate price forecasting cases are used to testify the forecasting performance of the proposed PSO–SVM model. The experimental results indicate that the proposed PSO–SVM model has good forecasting performance.