Cutting Through the Fog: Generative AI and the Future of Financial Readability Metrics

The readability of financial disclosures plays a major role in effective communication between firms and investors, with implications for firm performance and earnings persistence. Building upon previous studies by Li (2008), Loughran and McDonald (2014), and Bonsall et al. (2017), this research aims to improve traditional readability metrics such as file size, the Fog index, and the Bog index through the application of generative AI. By leveraging AI models, I seek to develop a more predictive readability metric that captures deeper semantic characteristics of financial documents. This research evaluates whether AI-driven metrics can better capture the relationship between readability and financial performance, advancing the field of textual analysis. My analysis validates the potential for LLMs to measure readability based on detailed prompting and criteria, showing several correlations with firm fundamentals and traits. However, my findings do not demonstrate superior predictive power for earnings persistence when compared to established metrics in empirical tests.

Name thesis:degree_name

Master

Department dc:contributor.department

Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science

Grantor dc:publisher

Massachusetts Institute of Technology

Year dc:date.issued

2025

Author dc:creator

• Berger, Jonathan

Advisor dc:contributor.advisor

• So, Eric

Statement dc:rights

• In Copyright - Educational Use Permitted
• Copyright retained by author(s)

Licence dc:rights.uri

• https://rightsstatements.org/page/InC-EDU/1.0/

Handle dc:identifier.uri

https://hdl.handle.net/1721.1/162545

OAI identifier oai:identifier

oai:dspace.mit.edu:1721.1/162545