The Information Content of Loan Contract Disclosures

working
accounting
NLP
We examine whether publicly disclosed loan contracts contain information that can be used by corporate stakeholders to predict borrower outcomes.
Authors

Isabella Brancaccio

Paul Demeré

Francesco Grossetti

Abstract

We examine whether publicly disclosed loan contracts contain information that can be used by corporate stakeholders to predict borrower outcomes. Loan contracts are the result of negotiations between informed parties after extensive due diligence, but strategic disclosure incentives and reliance on boilerplate language may limit their usefulness to stakeholders. Using natural language processing techniques applied to a large sample of SEC-filed loan contracts, we find that contract terms and language, particularly contract discussion topics, contain incremental predictive information about future borrower performance, investment, bankruptcy risk, and stock return volatility. However, we also find evidence that loan con- tract topics are associated with future stock returns and analyst forecast errors, suggesting that many corporate stakeholders struggle to effectively process and use this information in a timely manner. Our results indicate that loan contracts contain substantial information content of value to many corporate stakeholders and highlight the richness of the text in loan contracts.

Citation

Brancaccio, I., Demeré, P., & Grossetti, F. (work in progress). The Information Content of Loan Contract Disclosures.

BibTeX

@unpublished{brancaccio_loan_contract,
  title  = {The Information Content of Loan Contract Disclosures},
  author = {Brancaccio, Isabella and Demer{\'e}, Paul and Grossetti, Francesco},
  note   = {Working paper, under review},
  year   = {2025}
}