Simulating Financial Market via Large Language Model based Agents

TL;DR

This paper introduces ASFM, a novel agent-based simulated financial market using large language model agents that mimic human traders, providing a new paradigm for economic research by aligning with real market behaviors.

Contribution

The paper presents a new agent-based simulation framework with LLM-based traders that accurately reflect real market dynamics and support economic research.

Findings

ASFM's reactions match real stock market scenarios.

The model's conclusions align with existing economic research.

Demonstrates the potential of LLM agents in financial simulations.

Abstract

Most economic theories typically assume that financial market participants are fully rational individuals and use mathematical models to simulate human behavior in financial markets. However, human behavior is often not entirely rational and is challenging to predict accurately with mathematical models. In this paper, we propose \textbf{A}gent-based \textbf{S}imulated \textbf{F}inancial \textbf{M}arket (ASFM), which first constructs a simulated stock market with a real order matching system. Then, we propose a large language model based agent as the stock trader, which contains the profile, observation, and tool-learning based action module. The trading agent can comprehensively understand current market dynamics and financial policy information, and make decisions that align with their trading strategy. In the experiments, we first verify that the reactions of our ASFM are consistent with the real stock market in two controllable scenarios. In addition, we also conduct experiments in two popular economics research directions, and we find that conclusions drawn in our \model align with the preliminary findings in economics research. Based on these observations, we believe our proposed ASFM provides a new paradigm for economic research.