CovenantAI - New Insights into Covenant Violations

Sascha Steffen, Anthony Saunders and Paulina Verhoff

No 20117, CEPR Discussion Papers from Centre for Economic Policy Research

Abstract: We introduce CovenantAI, an advanced AI-based approach to accurately identify loan covenant violations from SEC filings. CovenantAI outperforms traditional keyword-based and Dealscan approaches by precisely classifying complex renegotiation outcomes such as amendments, waivers, and technical defaults. Our analyses validate CovenantAI's higher accuracy and consistency against existing methods. By capturing nuanced creditor-borrower interactions, CovenantAI enables new research into the economic implications of covenant resolution outcomes and investor behaviors surrounding violations. This novel dataset thus significantly enhances empirical research capabilities in corporate finance by providing comprehensive, granular, and reliable data on covenant violations and resolutions.

Keywords: Renegotiations (search for similar items in EconPapers)
JEL-codes: G21 G32 G34 (search for similar items in EconPapers)
Date: 2025-04
References: Add references at CitEc
Citations:

Downloads: (external link)
https://cepr.org/publications/DP20117 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:cpr:ceprdp:20117

Ordering information: This working paper can be ordered from
https://cepr.org/publications/DP20117

Access Statistics for this paper

More papers in CEPR Discussion Papers from Centre for Economic Policy Research 33 Great Sutton Street, London EC1V 0DX, UK.
Bibliographic data for series maintained by CEPR ().