Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Simulating Financial Market via Large Language Model based Agents

Shen Gao, Yuntao Wen, Minghang Zhu, Jianing Wei, Yuhan Cheng, Qunzi Zhang, Shuo Shang

TL;DR

ASFM tackles the inadequacy of fully rational market models by introducing LLM-based agents into a simulated financial market. It combines a realistic order-matching market with agent-based traders possessing profiles, observations, and tool-driven actions. The paper shows that ASFM can reproduce market responses to policy shocks and that trader behavior bias and large-trader effects align with economic literature. This framework offers a new micro-level paradigm for economic research and policy analysis.

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.

Simulating Financial Market via Large Language Model based Agents

TL;DR

ASFM tackles the inadequacy of fully rational market models by introducing LLM-based agents into a simulated financial market. It combines a realistic order-matching market with agent-based traders possessing profiles, observations, and tool-driven actions. The paper shows that ASFM can reproduce market responses to policy shocks and that trader behavior bias and large-trader effects align with economic literature. This framework offers a new micro-level paradigm for economic research and policy analysis.

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.
Paper Structure (32 sections, 1 equation, 4 figures, 1 table)

This paper contains 32 sections, 1 equation, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. ASFM Framework
  3. Problem Formulation
  4. Overall Framework
  5. Simulated Stock Market
  6. Listed Company
  7. Order Matching System
  8. Stock Price Updating Strategy
  9. LLM-based Trading Agent
  10. Agent Profile
  11. Agent Observation
  12. Agent Action
  13. Experimental Setup
  14. Evaluation Metrics
  15. Ablation Models
  16. ...and 17 more sections

Figures (4)

  • Figure 1: Comparison between our proposed Agent-based Simulated Financial Market (ASFM) (shown in the right) and traditional economic research paradigm (shown in the left). ASFM does not require any human annotator involved and only uses the LLM-based agents to conduct micro-financial market simulation.
  • Figure 2: The impact of cutting interest rates policy shock.
  • Figure 3: Stock return under different inflation rate.
  • Figure 4: Average return for the agent with different initial capital.