AI massively reduces the cost of prediction, while cheap prediction is directly applicable to finance and envisioned to have a huge impact.
We apply algorithms and softwares developped in AI, including OpenAI, TensorFlow, PyTorch, Keras; LSTM, DQN, DDPG, PPO, A2C, SAC, etc., to quantitative trading.
We also design deep learning and deep reinforcement learning (DRL) algorithms, e.g., quantum tensor networks, quantum reinforcement learning, etc. Exploiting the notion of differential privacy, we build more robust models or ensemble strategies; We develop a deep reinforcement learning library FinRL for finance.
Scholar data and ESG data as alternative data, we propose a practical machine learning approach and develop trading strategy to capture the scholar data or ESG data driven alpha.