Application of support vector regression in prediction model using genetic algorithm optimized

Abstract

No matter in any period, housing is the most basic demand of people's life, and it is closely related to people's daily life. Although many domestic and foreign experts have done research and prediction on housing prices, the causes of housing prices are complex, and the results of housing price research in different regions and different periods are very different, and most forecasting models have limitations in the use of them. Therefore, this article is based on the performance of support vector regression depends on the characteristics of key parameter selection, and uses genetic algorithm to optimize the penalty parameters, kernel function parameters and insensitive loss function of the support vector regression model. The optimized parameters are used to establish a support vector regression prediction model, and the housing price is predicted through the prediction model. The simulation results show that the convergence speed and prediction accuracy of the support vector regression prediction model optimized by genetic algorithm have been greatly improved, and the prediction results verify the feasibility and effectiveness of the model.