FinHEAR: Human Expertise and Adaptive Risk-Aware Temporal Reasoning for Financial Decision-Making

2025-06-10

AI Summary

Large language models (LLMs) struggle to model human behavioral patterns—such as expert reliance under information asymmetry, loss aversion, and feedback-driven temporal adaptation—in financial decision-making. Method: This paper proposes a behavioral economics–driven multi-agent framework integrating (i) expert-guided retrieval, (ii) confidence-adaptive position sizing, and (iii) outcome-feedback–based iterative optimization, alongside an event-centric pipeline and behavior-inspired risk modeling. Contribution/Results: Compared to conventional RAG and static strategies, the framework significantly enhances interpretability and robustness. Empirical evaluation across multiple financial datasets—spanning trend prediction and live trading tasks—demonstrates an average 23.6% improvement in Sharpe ratio, consistently outperforming strong baselines.

Technology Category

• Multiagent Systems: Mechanism Design
• Machine Learning: Large Multimodal Models (LMMs)
• Game Theory and Economic Paradigms: Behavioral Game Theory

Application Category

• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Financial decision-making presents unique challenges for language models, demanding temporal reasoning, adaptive risk assessment, and responsiveness to dynamic events. While large language models (LLMs) show strong general reasoning capabilities, they often fail to capture behavioral patterns central to human financial decisions-such as expert reliance under information asymmetry, loss-averse sensitivity, and feedback-driven temporal adjustment. We propose FinHEAR, a multi-agent framework for Human Expertise and Adaptive Risk-aware reasoning. FinHEAR orchestrates specialized LLM-based agents to analyze historical trends, interpret current events, and retrieve expert-informed precedents within an event-centric pipeline. Grounded in behavioral economics, it incorporates expert-guided retrieval, confidence-adjusted position sizing, and outcome-based refinement to enhance interpretability and robustness. Empirical results on curated financial datasets show that FinHEAR consistently outperforms strong baselines across trend prediction and trading tasks, achieving higher accuracy and better risk-adjusted returns.

Problem

• Enhancing financial decision-making with temporal reasoning and risk assessment
• Addressing human behavioral patterns in financial decisions using LLMs
• Improving accuracy and risk-adjusted returns in financial predictions

Innovation

• Multi-agent framework for financial decision-making
• Expert-guided retrieval and confidence-adjusted positioning
• Event-centric pipeline with behavioral economics grounding