On 11 November 2021, the European Banking Authority (EBA) published a discussion paper on machine learning for internal ratings-based (IRB) models. The discussion paper is a first step to engage the industry and the supervisory community to investigate the possible use of machine learning as IRB models and to build up a common understanding of the general aspects of machine learning and the related challenges in complying with the regulatory requirements. In particular, the discussion paper discusses the relevance of possible obstacles to the implementation of machine learning models in the IRB model space based on certain practical issues including the use of data.
The discussion paper is organised as follows:
- Section 2 provides a general definition of machine learning models for the purpose of the discussion paper, discusses the main learning paradigms used to train machine learning models and, finally, discusses the current limited use of machine learning models in the context of IRB models.
- Section 3 analyses the challenges and the benefits related institutions may face in using machine learning to develop compliant IRB models.
- Section 4 provides a set of principle-based recommendations that aim at ensuring machine learning models adhere to the regulatory requirements set out in the Capital Requirements Regulation, should they be used in the context of the IRB framework.
The deadline for comments on the discussion paper is 11 February 2022.
