When AI Meets Finance (StockAgent): Large Language Model-based Stock Trading in Simulated Real-world Environments

TL;DR

This paper introduces StockAgent, a multi-agent system driven by large language models that simulates real-world stock trading environments to analyze the influence of external factors on trading behaviors and market dynamics.

Contribution

It presents a novel LLM-based multi-agent simulation framework that avoids test set leakage and enables detailed analysis of external factors on stock trading and market fluctuations.

Findings

External factors significantly influence trading behavior.

StockAgent accurately models stock price fluctuations.

LLMs can provide valuable insights for investment strategies.

Abstract

Can AI Agents simulate real-world trading environments to investigate the impact of external factors on stock trading activities (e.g., macroeconomics, policy changes, company fundamentals, and global events)? These factors, which frequently influence trading behaviors, are critical elements in the quest for maximizing investors' profits. Our work attempts to solve this problem through large language model based agents. We have developed a multi-agent AI system called StockAgent, driven by LLMs, designed to simulate investors' trading behaviors in response to the real stock market. The StockAgent allows users to evaluate the impact of different external factors on investor trading and to analyze trading behavior and profitability effects. Additionally, StockAgent avoids the test set leakage issue present in existing trading simulation systems based on AI Agents. Specifically, it prevents the model from leveraging prior knowledge it may have acquired related to the test data. We evaluate different LLMs under the framework of StockAgent in a stock trading environment that closely resembles real-world conditions. The experimental results demonstrate the impact of key external factors on stock market trading, including trading behavior and stock price fluctuation rules. This research explores the study of agents' free trading gaps in the context of no prior knowledge related to market data. The patterns identified through StockAgent simulations provide valuable insights for LLM-based investment advice and stock recommendation. The code is available at https://github.com/MingyuJ666/Stockagent.