Optimization of Multi-Factor Model in Quantitative Trading Based On Reinforcement Learning

Dylan Zhang, Xiaotong LIN

Keywords: Quantitative trading, Reinforcement learning, Multi-factor model

TL;DR: Use Reinforcement learning to construct alpha strategy in Chinese stock market

Abstract: Quantitative trading strategies play an important role in stock trading, and reinforcement learning (RL) has been increasingly applied to trading activities in recent years. In this paper, we mainly study the optimization of multi-factor model in quantitative trading by using the method of RL, that we train an agent with a series of historical trading data of the stock market. From the experiment results, we can see that RL is feasible in solving and optimizing similar investment decision-making problems in financial field, which can help us to obtain more stable returns.Eventually, we hope that our simple work can make more and more people notice the application of RL in investment.