A CSI 300 Index Prediction Model Based on PSO-SVR-GRNN Hybrid Method

Chen，Jialin1; Yang，Hanyin2

2022

10.1155/2022/7419920

Mobile Information Systems   Impact Factor & Quartile

1574-017X

1875-905X

In this article, a PSO-SVR-GRNN nonparametric hybrid model is proposed for the CSI 300 stock index to forecast the problem. Particle Swarm Optimization (PSO) is utilized to optimize the parameters of the SVR model to enhance the prediction ability of the support vector machine's regression model for the original CSI 300 Index time series. The optimized residual sequence prediction results of the General Regression Neural Network (GRNN) are then used to optimize the time series prediction. The outcomes indicate that the PSO- SVR-GRNN model can greatly improve the prediction accuracy of the CSI 300 Index time series compared with individual models such as PSO-SVR, GRNN, GA-SVR, LSTM, PSO-LSTM, and SVR.

English

First ; Corresponding

2-s2.0-85136040059

Scopus

1.School of Finance,Southern University of Science and Technology,Shenzhen,Guangdong,China
2.Zhongnan University of Economics and Law,Wuhan,China

Chen，Jialin,Yang，Hanyin. A CSI 300 Index Prediction Model Based on PSO-SVR-GRNN Hybrid Method[J]. Mobile Information Systems,2022,2022.

Chen，Jialin,&Yang，Hanyin.(2022).A CSI 300 Index Prediction Model Based on PSO-SVR-GRNN Hybrid Method.Mobile Information Systems,2022.

Chen，Jialin,et al."A CSI 300 Index Prediction Model Based on PSO-SVR-GRNN Hybrid Method".Mobile Information Systems 2022(2022).