Speaker:Jiajie Li

Combine Double DQN and “Chan Theory” to Build an Applicable Trading Framework

We explored the potential of Double DQN (Deep Q-learning) framework to trade on stock market based on SP500 and Chinese Future market. In our work, human crafted features were used to capture the trend of the complex unstable and dynamic financial time series. The feature engineering is based on `Chan' theory, which is very popular trading system in Chinese financial market. Combined with the Double DQN's capability for searching policies, our experiments results show the Double DQN model has competitive performance, which also prove the 'Chan theory' is a successful technology analysis methodology. In this research, we solved three problems: 1. Firstly introduce 'Chan Theory', a method analysis financial time series based on its configuration. 2. Successfully combine the 'Chan theory' with machine learning models 3. Establish a novel trading system

Committee: Chris Quinn (major professor), Andrew Miner, and Daniel Nordman

Join on Zoom: https://iastate.zoom.us/j/96382864976 Or, go to https://iastate.zoom.us/join and enter meeting ID: 963 8286 4976