Boosting credit risk models

Baesens, Bart and Smedts, Kristien (2023) Boosting credit risk models. British Accounting Review, [101241]. (doi:10.1016/j.bar.2023.101241).

Record type: Article

Abstract

In this article, we give various recommendations to boost the performance of credit risk models. It is based upon more than two decades of research and consulting on the topic. Building credit risk models typically entails four steps: gathering and preprocessing data, modelling of probability of default (PD), Loss Given Default (LGD) and Exposure at Default (EAD), evaluating the credit risk models built and then the deployment step to put them into production. We give recommendations to boost credit risk models during each of these steps. Furthermore, we also define and review model risk as an all-encompassing challenge one needs to be properly aware of during each step of the process. We conclude by presenting a research agenda of topics we believe are in high need for further investigation and study.

Text

final paper - Accepted Manuscript

Restricted to Repository staff only until 27 July 2025.

Available under License Creative Commons Attribution Non-commercial No Derivatives.

Request a copy

More information

Accepted/In Press date: 27 July 2023

e-pub ahead of print date: 29 July 2023

Additional Information: Funding Information: Besides provisioning and regulatory capital calculation, modern day credit risk models can also contribute to the credit approval decision by setting the decision threshold in a profit-driven way. In Verbraken et al. (2014), we calculate the optimal cutoff value by taking into account the expected profits and losses of credit granting as quantified by the PD, LGD, and EAD. Taking this one step further, one can use the three credit risk parameters to do risk-based pricing or set the price or conditions (e.g., duration and collateral) of the loan based on the quantified risk. Publisher Copyright: © 2023 British Accounting Association

Keywords: Basel, Credit risk, Exposure at default (EAD), IFRS 9, Loss given default (LGD), Probability of default (PD)