Beyond the Lines: Deciphering Private Information from Fund Managers' Narratives

Abstract

We identify private information from mutual fund managers' narratives in their letters to shareholders with the help of large language models (LLM). Informed funds deliver superior abnormal returns and are more likely to receive an upgrade in Morningstar ratings. Informative textual disclosure contains more forward-looking discussions and is associated with more modest and cautious managers. We find evidence that investors recognize such qualitative information and reward funds that disclose private information with greater flows. Furthermore, textual disclosure is particularly informative and valuable for hard-to-evaluate funds, suggesting the importance of qualitative disclosure in complementing quantitative information for mutual funds.

Keywords: Machine Learning, Large Language Models, Mutual Fund Performance, Disclosure, Textual Analysis, Shareholder Letters, Fund Flows

JEL Classification: C45, G11, G14, G23