Research on Multi Factor Quantitative Investment Strategies Based on Machine Learning

Abstract

Training models using machine learning algorithms have shown strong capabilities in classification prediction, thus employing machine learning algorithms in quantitative research can significantly enhance the accuracy of investment decisions. Utilizing a combination of multifactor models and machine learning algorithms for quantifying investment strategies holds considerable theoretical and practical research value. The IC analysis method and the random forest algorithm are employed to select factors, which serve as input variables (explanatory variables) for linear regression models. Future 30-day returns are used as the input variable (dependent variable) for regression calculations, establishing linear regression models to identify the relationship between them. Subsequently, this linear relationship is utilized for predicting future stock returns, thereby constructing a stock investment portfolio. The research findings indicate that both sets of strategy combinations exhibit some similarities and have achieved favorable strategy returns. Additionally, they demonstrate strong performance in terms of volatility and risk control, albeit with a deficiency in success rate.