Machine Learning and IRB Capital Requirements

Christophe Hurlin and Christophe Pérignon
Additional contact information
Christophe Pérignon: HEC Paris - Ecole des Hautes Etudes Commerciales

Working Papers from HAL

Abstract: This survey proposes a theoretical and practical reflection on the use of machine learning methods in the context of the Internal Ratings Based (IRB) approach to banks' capital requirements. While machine learning is still rarely used in the regulatory domain (IRB, IFRS 9, stress tests), recent discussions initiated by the European Banking Authority suggest that this may change in the near future. While technically complex, this subject is crucial given growing concerns about the potential financial instability caused by the banks' use of opaque internal models. Conversely, for their proponents, machine learning models offer the prospect of better measurement of credit risk and enhancing financial inclusion. This survey yields several conclusions and recommendations regarding (i) the accuracy of risk parameter estimations, (ii) the level of regulatory capital, (iii) the trade-off between performance and interpretability, (iv) international banking competition, and (v) the governance and operational risks of machine learning models.

Keywords: Banking; Machine Learning; Artificial Intelligence; Internal models; Prudential regulation; Regulatory capital (search for similar items in EconPapers)
Date: 2023-12-05
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
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:hal:wpaper:hal-04414108

DOI: 10.2139/ssrn.4483793

Access Statistics for this paper

More papers in Working Papers from HAL
Bibliographic data for series maintained by CCSD ().