Are LLMs Good Financial User Simulators? A Preliminary Study

2026-09-14

AI Summary

研究使用大型语言模型作为金融用户模拟器，通过120名志愿者在虚拟交易环境中的行为预测其决策，发现市场信息能提高部分预测准确性但模型存在行为压缩问题。

Abstract

Large language models (LLMs) are increasingly used as user simulators, but their ability to reproduce evolving individual financial decisions remains unclear. We present a preliminary study in a controlled paper-trading environment with 120 volunteers. Participants used non-redeemable virtual funds under real-time market conditions; no real brokerage accounts, real-money positions, or real transaction records were accessed. Given only information available before a prediction cutoff, a simulator predicts the participant's next-trading-day action, traded security, and transaction quantity. We evaluate temporally aligned rolling predictions and compare settings with and without point-in-time market information. Market context improves action and ticker prediction in the controlled ablation, while transaction sizing remains difficult. We also observe systematic behavioral compression: models overproduce hold actions, underpredict sell decisions, and simplify multi-security transactions. These results provide an initial empirical characterization and motivate larger-scale evaluation of individual, temporal, and portfolio-level behavioral fidelity.

Problem

• Large language models
• Financial user simulators
• Individual financial decisions
• Behavioral fidelity

Innovation

• Large language models
• Financial user simulators
• Temporal predictions
• Behavioral compression
• Market context