Cutting Through the Fog: Generative AI and the Future of Financial Readability Metrics
Name
berger-bergerj-meng-eecs-2025-thesis.pdf
Description
Thesis PDF
Size
538.04 KB
Format
Adobe PDF
Checksum (MD5)
be50c1fdbbf43abebd874fc5ae674c52
Author(s)
Berger, Jonathan
Advisor(s)
So, Eric
Date Issued
May 2025
Publisher
Massachusetts Institute of Technology
Abstract
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.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright retained by author(s)
Persistent DSpace Link
