Stock Price Prediction via Feature Optimization and SVM-Random Forest Multi-Model Fusion

This article proposes a stock price prediction method based on feature optimization and multi model fusion, aiming to improve the accuracy and robustness of stock price prediction by combining the advantages of support vector machine (SVM) and random forest. Specifically, this article first uses Spearman correlation to analyze the correlation of features in the stock dataset, selects features that have a significant impact on the target variable (closing price), and constructs a new dataset. Subsequently, support vector machines and random forests were used to train and predict the original dataset and the feature selected dataset, respectively. The prediction results of the two models were fused using a multi model fusion strategy (such as weighted average or voting method) to obtain the final prediction result. The experimental results show that the performance of the prediction model is significantly improved after feature optimization and multi model fusion, especially when dealing with nonlinear problems, the performance of the fusion model is better than that of the single model.