Dissecting AI Trading: Behavioral Finance and Market Bubbles
TLDR
AI agents in simulated markets exhibit behavioral biases like disposition effect and extrapolative beliefs, replicating market bubbles.
Key contributions
- AI agents show classic behavioral patterns: disposition effect and recency-weighted beliefs.
- Individual AI behaviors aggregate into market dynamics, replicating classic experimental findings.
- Targeted prompt interventions can causally alter behavioral mechanisms and significantly impact market bubbles.
Why it matters
This paper reveals that AI agents, specifically LLMs, can replicate human-like behavioral biases and market dynamics in trading simulations. Understanding these patterns is crucial for designing more robust AI trading systems and for predicting market behavior. It also shows how targeted interventions can mitigate or amplify market bubbles.
Original Abstract
We study how AI agents form expectations and trade in experimental asset markets. Using a simulated open-call auction populated by autonomous Large Language Model (LLM) agents, we document three main findings. First, AI agents exhibit classic behavioral patterns: a pronounced disposition effect and recency-weighted extrapolative beliefs. Second, these individual-level patterns aggregate into equilibrium dynamics that replicate classic experimental findings (Smith et al., 1988), including the predictive power of excess demand for future prices and the positive relationship between disagreement and trading volume. Third, by analyzing the agents' reasoning text through a twenty-mechanism scoring framework, we show that targeted prompt interventions causally amplify or suppress specific behavioral mechanisms, significantly altering the magnitude of market bubbles.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.