Abstract
In this paper, we consider a sustainable quantitative stock selection strategy using some machine learning techniques. In particular, we use a random forest model to dynamically select factors for the training set in each period to ensure that the factors that can be selected in each period are the optimal factors in the current period. At the same time, the classification probability prediction (CPP) of stock returns is performed. Historical back-testing using Chinese stock market data shows that the proposed CPP quantitative stock selection strategy performs better than the traditional machine learning stock selection methods, and it can outperform the market index over the same period in most back-testing periods. Moreover, this strategy is sustainable in all market conditions, such as a bull market, a bear market, or a volatile market.
Highlights
In modern investing, algorithmic trading is getting more and more attention from individual and institutional traders
As we used the historical data for back-testing, we did not consider the impacts of the market liquidity, and the impacts of this strategy on the decisions of other market participants, etc
We used a random forest model to dynamically select factors for the training set in each period to ensure that the factors that could be selected in each period were the optimal factors in the current period
Summary
Algorithmic trading is getting more and more attention from individual and institutional traders. Li and Zhang (2018) [6] used the XGBoost model to establish a dynamic weighted multi-factor stock selection strategy. They used the XGBoost machine learning method to predict the information coefficients (ICs) of various factors. The empirical results showed that the XGBoost model is effective in predicting the ICs, and the dynamic weights based on the XGBoost model can improve the performance of multi-factor stock selection strategies. We propose a sustainable quantitative stock selection strategy using RF to dynamically adjust the factors to predict the importance of the training set for each period. The proposed strategy is a sustainable investment strategy in the sense that it works well over a long time period that consists of bear market, bull market, and volatile market periods
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have