About Me
I am a PhD candidate in my 3rd year at Frankfurt School of Finance & Management. I have a Master’s degree in Finance from Frankfurt School and a Bachelor of Science in Economics from Justus-Liebig-University in Giessen. My interests are in the field of financial intermediation and the use of AI to generate new data.
Research Interests
CovenantAI – New Insights into Covenant Violations (with Anthony Saunders and Sascha Steffen) [Paper]
Best PhD Presentation Award, Generative AI Conference Concordia University
Conferences: 1st Lapland Financial Institutions Summit, Finance Research Seminar Krakow University of Economics, 3rd Bonn/Mannheim Workshop on Digital Finance, Generative AI in Finance Conference in Montreal, Harvard-Wharton Insolvency and Restructuring Conference, 8th Household Finance Workshop, 6th Future of Financial Information Conference, UCLA Conference on Financial Markets, Harvard Corporate Restructuring & Insolvency Seminar, 2023 NBER Big Data and Securities Markets Conference, Bonn-Frankfurt-Mannheim PhD Conference 2023, 11th Workshop Banks and Financial Markets in Halle, 4th Vaasa Banking Research Workshop and New (and Old) challenges to Financial Intermediaries Conference in Bayes Business School
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.
Do Institutional Investors Trade on Covenant Violations? (with Sascha Steffen)
Conferences: Bonn-Frankfurt-Mannheim PhD Conference 2024
Abstract
We use CovenantAI, the Artificial Intelligence (AI) – powered covenant monitoring tool developed in Krockenberger, Saunders, Steffen and Verhoff (2024), to study whether institutional investors such as Collateralized Loan Obligations (CLOs) trade around covenant violations. We find that they do. We document a persistent decline in loan prices in the 100 days before a covenant violation with a noticeable drop in the 20 days before the violation. Consistently, we find the largest Cumulative Abnormal Return (CAR) of 0.84% during the [-20,-1] event window. The effect are largest for loans that are amended after (but not before) a covenant violation or that remain in technical default. We document a significant increase in both downgrade and bankruptcy likelihood after loan amendments, particularly among leveraged loans purchased by CLOs. We document substantial cross-sectional variation in CLO constraints (both from ownership of CCC-rated loans as well as overcollateralization tests from junior tranches). Loan prices and CARs before covenant violations are affected by CLO constraints. Loan price declines pre-violation are more pronounced for loans mainly owned by constrained CLOs. The CARs in the [-20,-1] event window are also significantly more negative among constrained CLOs. Overall, our results are consistent with constrained institutional investors trading out of loan positions for which they anticipate future covenant violations.