Financial Vision Based Reinforcement Learning Trading Strategy
This work tackles the challenge of explainability in AI for financial trading, which is crucial for risk management and trust, though it appears incremental as it focuses on well-known issues in the field.
The paper addresses the 'black box' problem in AI-driven quantitative trading, where complex AI mechanisms make decisions difficult to understand and trust, potentially leading to significant financial losses. It highlights the need for explainable AI in trading to answer questions about why AI makes specific decisions, how to trust it, and how to correct errors.
Recent advances in artificial intelligence (AI) for quantitative trading have led to its general superhuman performance in significant trading performance. However, the potential risk of AI trading is a "black box" decision. Some AI computing mechanisms are complex and challenging to understand. If we use AI without proper supervision, AI may lead to wrong choices and make huge losses. Hence, we need to ask about the AI "black box", including why did AI decide to do this or not? Why can people trust AI or not? How can people fix their mistakes? These problems also highlight the challenges that AI technology can explain in the trading field.