Financial Vision Based Reinforcement Learning Trading Strategy
Research on financial vision-based reinforcement learning for trading strategies using candlestick patterns and GAF encoding.
What it examines
This paper explores financial vision-based reinforcement learning for trading, focusing on candlestick pattern detection, trading signals, and transfer learning from Ethereum to US stock trading. It aims to provide an explainable AI approach to enhance trust and performance in trading systems.
What it concludes
The research offers a novel approach to trading by focusing on current candlestick patterns and using explainable AI. Potential applications include enhanced trading strategies and risk management. Future research could explore optimizing trading frequency and expanding to other financial assets.
Evidence objects
The research offers a novel approach to trading by focusing on current candlestick patterns and using explainable AI. Potential applications include enhanced trading strategies and risk management. Future research could explore optimizing trading frequency and expanding to other financial assets.
key_findings bullet 1 · key_findings · validation V0
Raw abstract and provenance
Recent advances in artificial intelligence (AI) for quantitative trading have led to its general superhuman performance among notable trading performance results. However, if we use AI without proper supervision, it can lead to wrong choices and huge losses. Therefore, we need to ask why AI makes decisions and how AI makes decisions so that people can trust AI. By understanding the decision process, people can make error corrections, so the need for explainability highlights the artificial intelligence challenges that intelligent technology can explain in trading. This research focuses on financial vision, an explainable approach, and the link to its programmatic implementation. We hope our paper can refer to superhuman performance and the reasons for decisions in trading systems.
Source row: 829 · abstract type: unknown