Company rating with support vector machines
Statistics & Risk Modeling · 2017
DOI: 10.1515/strm-2012-1141 ↗Kurz gefasst
Fachartikel in der Zeitschrift Statistics & Risk Modeling, 2017. Verfasst von Russ A. Moro und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 39 Literaturangaben. Gefördert von: Deutsche Forschungsgemeinschaft.
Abstract (Originalsprache)
This paper proposes a rating methodology that is based on a non-linear classification method, a support vector machine, and a non-parametric isotonic regression for mapping rating scores into probabilities of default. We also propose a four data set model validation and training procedure that is more appropriate for credit rating data commonly characterised with cyclicality and panel features. Tests on representative data covering fifteen years of quarterly accounts and default events for 10,000 US listed companies confirm superiority of non-linear PD estimation. Our methodology demonstrates the ability to identify companies of diverse credit quality from Aaa to Caa–C.
Förderung
- Deutsche Forschungsgemeinschaft
Zitieren
APA
Moro, R. A., Härdle, W. K., & Schäfer, D. (2017). Company rating with support vector machines. Statistics & Risk Modeling. https://doi.org/10.1515/strm-2012-1141
Vancouver
Moro RA, Härdle WK, Schäfer D. Company rating with support vector machines. Statistics & Risk Modeling. 2017. doi:10.1515/strm-2012-1141
BibTeX
@article{Moro2017,
author = {Moro, Russ A. and Härdle, Wolfgang K. and Schäfer, Dorothea},
title = {Company rating with support vector machines},
journal = {Statistics & Risk Modeling},
year = {2017},
doi = {10.1515/strm-2012-1141}
}
EUVIMED