🤖 AI Summary
Traditional asset pricing models rely excessively on quantitative factors and struggle to capture qualitative investment logic. Method: This paper pioneers the integration of large language model (LLM) agents into empirical asset pricing, proposing a synergistic modeling framework that fuses LLM-generated qualitative investment judgments—derived from semantic parsing and investment logic inference on unstructured texts (e.g., financial reports, news)—with hand-crafted quantitative economic factors. The framework employs joint modeling, portfolio optimization, and abnormal return analysis for empirical validation. Contribution/Results: The proposed model significantly enhances explanatory power and investment performance: portfolio Sharpe ratios increase by 10.6%, and the absolute mean α of anomaly portfolios declines by 10.0%, outperforming leading machine learning baselines across all metrics. This work establishes the first LLM-driven, qualitative–quantitative dual-track paradigm in asset pricing.
📝 Abstract
In this study, we introduce a novel asset pricing model leveraging the Large Language Model (LLM) agents, which integrates qualitative discretionary investment evaluations from LLM agents with quantitative financial economic factors manually curated, aiming to explain the excess asset returns. The experimental results demonstrate that our methodology surpasses traditional machine learning-based baselines in both portfolio optimization and asset pricing errors. Notably, the Sharpe ratio for portfolio optimization and the mean magnitude of $|alpha|$ for anomaly portfolios experienced substantial enhancements of 10.6% and 10.0% respectively. Moreover, we performed comprehensive ablation studies on our model and conducted a thorough analysis of the method to extract further insights into the proposed approach. Our results show effective evidence of the feasibility of applying LLMs in empirical asset pricing.