A transformer-based model for default prediction in mid-cap corporate markets
European Journal of Operational Research · 2023-07 · 308 (1) · 306-320
DOI: 10.1016/j.ejor.2022.10.032 ↗Kurz gefasst
Fachartikel in der Zeitschrift European Journal of Operational Research, 2023-07. Verfasst von Kamesh Korangi und 2 weiteren Autor:innen. Die Arbeit wurde bisher 72-mal zitiert (Crossref) und nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Sciences and Engineering Research Council of Canada, Canada Research Chairs, ESRC.
Abstract (Originalsprache)
In this paper, we study mid-cap companies, i.e. publicly traded companies with less than US $10 billion in market capitalisation. Using a large dataset of US mid-cap companies observed over 30 years, we look to predict the default probability term structure over the medium term and understand which data sources (i.e. fundamental, market or pricing data) contribute most to the default risk. Whereas existing methods typically require that data from different time periods are first aggregated and turned into cross-sectional features, we frame the problem as a multi-label time-series classification problem. We adapt transformer models, a state-of-the-art deep learning model emanating from the natural language processing domain, to the credit risk modelling setting. We also interpret the predictions of these models using attention heat maps. To optimise the model further, we present a custom loss function for multi-label classification and a novel multi-channel architecture with differential training that gives the model the ability to use all input data efficiently. Our results show the proposed deep learning architecture's superior performance, resulting in a 13% improvement in AUC (Area Under the receiver operating characteristic Curve) over traditional models. We also demonstrate how to produce an importance ranking for the different data sources and the temporal relationships using a Shapley approach specific to these models.
Förderung
- Natural Sciences and Engineering Research Council of Canada
- Canada Research Chairs
- ESRC
Zitieren
APA
Korangi, K., Mues, C., & Bravo, C. (2023). A transformer-based model for default prediction in mid-cap corporate markets. European Journal of Operational Research, 308(1), 306-320. https://doi.org/10.1016/j.ejor.2022.10.032
Vancouver
Korangi K, Mues C, Bravo C. A transformer-based model for default prediction in mid-cap corporate markets. European Journal of Operational Research. 2023;308(1):306-320. doi:10.1016/j.ejor.2022.10.032
BibTeX
@article{Korangi2023,
author = {Korangi, Kamesh and Mues, Christophe and Bravo, Cristián},
title = {A transformer-based model for default prediction in mid-cap corporate markets},
journal = {European Journal of Operational Research},
year = {2023},
volume = {308},
number = {1},
pages = {306--320},
doi = {10.1016/j.ejor.2022.10.032}
}
EUVIMED