A Reflective LLM-based Agent to Guide Zero-shot Cryptocurrency Trading

TL;DR

This paper introduces CryptoTrade, an LLM-based cryptocurrency trading agent that combines on-chain and off-chain data analysis with a reflective mechanism to improve decision-making, demonstrating superior performance over traditional strategies.

Contribution

It extends LLM applications to cryptocurrency trading and establishes a new benchmark for evaluating trading strategies in this domain.

Findings

CryptoTrade outperforms traditional trading strategies.

The reflective mechanism improves daily trading decisions.

CryptoTrade is effective across various cryptocurrencies and market conditions.

Abstract

The utilization of Large Language Models (LLMs) in financial trading has primarily been concentrated within the stock market, aiding in economic and financial decisions. Yet, the unique opportunities presented by the cryptocurrency market, noted for its on-chain data's transparency and the critical influence of off-chain signals like news, remain largely untapped by LLMs. This work aims to bridge the gap by developing an LLM-based trading agent, CryptoTrade, which uniquely combines the analysis of on-chain and off-chain data. This approach leverages the transparency and immutability of on-chain data, as well as the timeliness and influence of off-chain signals, providing a comprehensive overview of the cryptocurrency market. CryptoTrade incorporates a reflective mechanism specifically engineered to refine its daily trading decisions by analyzing the outcomes of prior trading decisions. This research makes two significant contributions. Firstly, it broadens the applicability of LLMs to the domain of cryptocurrency trading. Secondly, it establishes a benchmark for cryptocurrency trading strategies. Through extensive experiments, CryptoTrade has demonstrated superior performance in maximizing returns compared to traditional trading strategies and time-series baselines across various cryptocurrencies and market conditions. Our code and data are available at \url{https://anonymous.4open.science/r/CryptoTrade-Public-92FC/}.