Explainable models of credit losses
João Bastos and
Sara M. Matos
European Journal of Operational Research, 2022, vol. 301, issue 1, 386-394
Abstract:
Credit risk management is an area where regulators expect banks to have transparent and auditable risk models, which would preclude the use of more accurate black-box models. Furthermore, the opaqueness of these models may hide unknown biases that may lead to unfair lending decisions. In this study, we show that banks do not have to sacrifice prediction accuracy at the cost of model transparency to be compliant with regulatory requirements. We illustrate this by showing that the predictions of credit losses given by a black-box model can be easily explained in terms of their inputs. Because black-box models are better at uncovering complex patterns in the data, banks should consider the determinants of credit losses suggested by these models in lending decisions and pricing of credit exposures.
Keywords: Risk management; Loss given default; Recovery rates; Explainable machine learning; Forecasting (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (15)
Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0377221721009553
Full text for ScienceDirect subscribers only
Related works:
Working Paper: Explainable models of credit losses (2021) 
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:eee:ejores:v:301:y:2022:i:1:p:386-394
DOI: 10.1016/j.ejor.2021.11.009
Access Statistics for this article
European Journal of Operational Research is currently edited by Roman Slowinski, Jesus Artalejo, Jean-Charles. Billaut, Robert Dyson and Lorenzo Peccati
More articles in European Journal of Operational Research from Elsevier
Bibliographic data for series maintained by Catherine Liu ().