Enhancing Cryptocurrency Trading Strategies: A Deep Reinforcement Learning Approach Integrating Multi-Source LLM Sentiment Analysis

Nanjiang Du, Yida Zhao, Jintao Wang, Yicheng Zhu, Siyu Xie, Luyao Yang, Yiru Tong, Shengzhe Xu, Wangying Zhang, Zecheng Tang, Kai Xu, Jianfeng Ren, Tianxiang Cui

Research output: Chapter in Book/Conference proceedingConference contributionpeer-review

Abstract

Recent advancements in large language models (LLMs) have demonstrated their potential to significantly impact finance trading, particularly through sentiment analysis. The cryptocurrency market, known for its volatility and unpredictability, often renders price-based trading approaches inadequate. This necessitates the adoption of more sophisticated techniques such as market sentiment analysis, which can benefit from the insights provided by LLMs. This study introduces an innovative method that integrates sentiment analysis derived from five distinct LLMs with deep reinforcement learning to devise a cryptocurrency trading strategy. Recognizing that LLM outputs cannot be guaranteed to be infallibly accurate, which contributing to the LLM hallucinations, this paper details the implementation of a stringent outlier detection and removal process. By adopting a 'Trust-The-Majority' strategy, the research aims to ensure that trading decisions are informed by reliable sentiment data. In addition, sentiment scores are traditionally timestamped to the publication of news or social media posts. To more accurately reflect the actual impact of such information on market sentiment, this study applies the Ebbinghaus Forgetting Curve to model the waning influence of information over time. This allows for a more nuanced understanding of how news affects market dynamics. The enhanced sentiment scores, in conjunction with traditional market data such as OHLCV (Open, High, Low, Close, Volume), are utilized by a deep reinforcement learning model to make trading decisions. Experimental results demonstrate that the proposed multi-LLM sentiment-driven framework improves trading performance in the fast-paced cryptocurrency market. The methodology outlined in this paper offers a solid foundation for incorporating real-time market sentiment analysis into financial applications.

Original languageEnglish
Title of host publication2025 IEEE Symposium on Computational Intelligence for Financial Engineering and Economics, CiFer 2025
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798331508319
DOIs
Publication statusPublished - 2025
Event2025 IEEE Symposium on Computational Intelligence for Financial Engineering and Economics, CiFer 2025 - Trondheim, Norway
Duration: 17 Mar 202520 Mar 2025

Publication series

Name2025 IEEE Symposium on Computational Intelligence for Financial Engineering and Economics, CiFer 2025

Conference

Conference2025 IEEE Symposium on Computational Intelligence for Financial Engineering and Economics, CiFer 2025
Country/TerritoryNorway
CityTrondheim
Period17/03/2520/03/25

ASJC Scopus subject areas

  • Artificial Intelligence
  • Economics and Econometrics
  • Finance
  • Modelling and Simulation

Fingerprint

Dive into the research topics of 'Enhancing Cryptocurrency Trading Strategies: A Deep Reinforcement Learning Approach Integrating Multi-Source LLM Sentiment Analysis'. Together they form a unique fingerprint.

Cite this