Abstract
With the development of the stock market and the improvement of people’s living standard, more and more investors enter the stock market, and how to use historical information to analyze and predict the future trend in the complex stock market has become a hot issue at present. Based on SVR model, this paper introduces a stock price prediction model on the basis of short-term and long-term ensemble learning, analyzing and verifying the ensemble learning model with a large amount of historical data of the stock price. The results of the experiment show that the ensemble learning model can effectively improve the accuracy of the SVR model in stock price prediction.