Learning Financial Investment Strategies using Reinforcement Learning and 'Chan theory'
Is Version Of
We explored the potential of Double DQN (Deep Q-learning) framework to trade on stock market based on S&P500 and Chinese Future market. In our work, human crafted features were used to capture the trend of the complex unstable and dynamic nancial time series. The feature engineering is based on `Chan' theory, which is popular trading system in Chinese nancial market. Combined with the Double DQN's capability for searching policies, the results of our experiment show the Double DQN model has competitive performance, which also shows the 'Chan theory' is a successful technology analysis methodology. In this research, we solved two problems: 1. Firstly introduce 'Chan Theory', a nancial time series analysis method based on its con gurations, to formal paper. 2. The rst time to combine the 'Chan theory' with machine learning models