TwinMarket: A Scalable Behavioral and SocialSimulation for Financial Markets

2025-02-03

AI Summary

This study investigates how individual irrational behaviors—mediated by interaction and feedback mechanisms—emerge as macroeconomic phenomena such as asset bubbles, herding, and recessions. To this end, we develop the first large language model (LLM)-based multi-agent behavioral finance simulation system, tightly integrating cognitive bias modeling from behavioral economics with formal analysis of social emergence. Our framework is behavior-driven and feedback-reinforced, enabling interpretable tracing from micro-level agent decisions to macro-level patterns. In stock market simulations, the system successfully reproduces canonical collective economic phenomena while preserving psychological realism at the individual level. The primary contribution is the pioneering systematic application of LLM-powered agents to large-scale behavioral finance simulation, thereby bridging micro-level psychological plausibility with macro-level emergent dynamics in a computationally tractable and theoretically grounded manner.

Technology Category

• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

The study of social emergence has long been a central focus in social science. Traditional modeling approaches, such as rule-based Agent-Based Models (ABMs), struggle to capture the diversity and complexity of human behavior, particularly the irrational factors emphasized in behavioral economics. Recently, large language model (LLM) agents have gained traction as simulation tools for modeling human behavior in social science and role-playing applications. Studies suggest that LLMs can account for cognitive biases, emotional fluctuations, and other non-rational influences, enabling more realistic simulations of socio-economic dynamics. In this work, we introduce TwinMarket, a novel multi-agent framework that leverages LLMs to simulate socio-economic systems. Specifically, we examine how individual behaviors, through interactions and feedback mechanisms, give rise to collective dynamics and emergent phenomena. Through experiments in a simulated stock market environment, we demonstrate how individual actions can trigger group behaviors, leading to emergent outcomes such as financial bubbles and recessions. Our approach provides valuable insights into the complex interplay between individual decision-making and collective socio-economic patterns.

Problem

• Financial Markets
• Behavioral Economics
• Social Economic Phenomena

Innovation

• TwinMarket
• Large Language Models
• Financial Market Simulation