Analysis of multi-factor value investment strategy based on GA model

Abstract: This paper presents an analysis of a multi-factor value investment strategy based on a genetic algorithm (GA) model. The proposed approach leverages genetic algorithms for feature selection, aiming to enhance the model's capability in extracting features for stock prediction. By using GA for feature selection, the model significantly improves the accuracy of stock price predictions. Experiment results demonstrate its effectiveness, as the model outperforms mainstream stock prediction models in forecasting the performance of the CSI 300 Index and HSI index. The method's ability to extract valuable features for stock prediction is enhanced through the application of genetic algorithms. The research findings provide valuable insights into the application of multi-factor value investment strategies and highlight the potential for enhancing stock prediction accuracy using genetic algorithm-based models. This study contributes to the understanding of multi-factor value investment strategies and provides new perspectives on how genetic algorithms can be effectively utilized to improve stock prediction accuracy, thereby enriching the field of financial analysis and investment strategies.