- 期刊
Stock prediction method based on integrated learning
摘要
With the rapid development of the stock market, fields related to stock prediction have attracted the attention of more and more researchers. Stock forecasts can help the healthy development of the stock market and are of great significance to society, companies and individual investors. Through experiments, we found that the support vector regression model (SVR) is not stable due to the distribution characteristics of the training data. The specific manifestation is that the stock price forecasts of certain stocks have large deviations. In response to this problem, this paper improves the SVR model from the perspective of integrated learning. Based on the SVR model, we integrated two simple and effective learners, linear regression model (LR) and K nearest neighbor model (KNN) to enhance the generalization ability of the SVR model. Experiments show that the ensemble model proposed in this paper has a significant improvement in stock price prediction accuracy compared to the pure SVR model.