Research and prediction of Shanghai-Shenzhen 20 Index Based on the Support Vector Machine Model and Gradient Boosting Regression Tree

摘要

The non-stationarity, non-linearity and multi-factor influence of financial index series makes it more difficult to predict. In order to achieve a more accurate stock index prediction, this paper selects a public data set provided by a well-known securities company to predict the CSI 20 Index (CSI20) based on the gradient-enhancing regression tree model and support vector machine model. RMSE, MAE, and MAPE are selected as the indicators to evaluate the differences in the forecasting ability of the two models in the financial sector. The results of this study can help investors to adopt effective investment strategies and reduce investment risks.