Towards Realistic and Interpretable Market Simulations: Factorizing Financial Power Law using Optimal Transport

2025-07-13

AI Summary

This study investigates the generative mechanisms underlying the power-law tails observed in stock return distributions. Addressing the persistent mismatch between conventional Gaussian assumptions and empirical heavy-tailed evidence—and the inability of existing models to disentangle individual versus interactive effects of behavioral factors—we develop an interpretable, incremental agent-based model (ABM) incorporating key behavioral drivers such as price informativeness and investor heterogeneity. Innovatively, we employ optimal transport distance to quantify distributional similarity between simulated and empirical return distributions, and conduct controlled experiments to assess both marginal and joint contributions of each factor. Results demonstrate that price informativeness is the primary driver of power-law tail formation; moreover, multiple behavioral factors exhibit significant synergistic enhancement, substantially improving the fidelity of simulated distributions to real-world data. This framework advances behavioral finance by providing a novel, causally grounded methodology for attributing distributional shape to specific microfoundational mechanisms.

Technology Category

• Game Theory and Economic Paradigms: Behavioral Game Theory
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success

Abstract

We investigate the mechanisms behind the power-law distribution of stock returns using artificial market simulations. While traditional financial theory assumes Gaussian price fluctuations, empirical studies consistently show that the tails of return distributions follow a power law. Previous research has proposed hypotheses for this phenomenon -- some attributing it to investor behavior, others to institutional demand imbalances. However, these factors have rarely been modeled together to assess their individual and joint contributions. The complexity of real financial markets complicates the isolation of the contribution of a single component using existing data. To address this, we construct artificial markets and conduct controlled experiments using optimal transport (OT) as a quantitative similarity measure. Our proposed framework incrementally introduces behavioral components into the agent models, allowing us to compare each simulation output with empirical data via OT distances. The results highlight that informational effect of prices plays a dominant role in reproducing power-law behavior and that multiple components interact synergistically to amplify this effect.

Problem

• Investigates power-law distribution in stock returns
• Models investor behavior and demand imbalances jointly
• Uses optimal transport to isolate contributing factors

Innovation

• Uses optimal transport for market similarity measurement
• Incrementally adds behavioral components to agent models
• Isolates price informational effects via controlled experiments