The European Banking Authority (EBA) published a discussion paper on machine learning used in the context of internal ratings-based (IRB) models to calculate regulatory capital for credit risk. The aim of the discussion paper is to set supervisory expectations on how new sophisticated machine learning models can coexist with and adhere to the Capital Requirements Regulation (CRR) when used in the context of IRB models. The discussion paper seeks stakeholder feedback on many practical aspects on the use of machine learning in the context of IRB models, with the consultation period ending on February 11, 2022.
This discussion paper is a first step to engage the industry and the supervisory community to investigate the possible use of machine learning in IRB models and to build a common understanding of the general aspects of machine learning and the related challenges in complying with the regulatory requirements. The discussion paper provides a general definition of machine learning models, discusses the main learning paradigms used to train machine learning models, and discusses the current limited use of machine learning models in the context of IRB models. It also analyzes the challenges and the benefits institutions may face in using machine learning to develop compliant IRB models. The paper provides a set of principle-based recommendations that aim to ensure that machine learning models adhere to the regulatory requirements set out in the CRR, should they be used in the context of the IRB framework.
EBA recommends for institutions to ensure that the staff working in the model development unit, credit risk control unit, and the validation unit is sufficiently skilled to develop and validate machine learning models. EBA recommends that institutions should ensure that the management body and senior management are in a position to have good understanding of the model, by providing them with appropriate high-level documentation. It is also recommended for institutions to avoid any unnecessary complexity in the modeling approach, unless it is justified by a significant improvement in the predictive capacities. Institutions should avoid including an excessive number of explanatory drivers or drivers with no significant predictive information and using unstructured data if more conventional data is available that provides similar predictive capacities. Institutions should also avoid overly complex modeling choices if simpler approaches yielding similar results are available. In addition, to ensuring that the model is correctly interpreted and understood, institutions are recommended to:
- analyze, in a statistical manner, the relationship of each single risk driver with the output variable and the overall weight of each risk driver in determining the output variable.
- assess the economic relationship of each risk driver with the output variable to ensure that the model estimates are plausible and intuitive.
- provide a summary document in which the model is explained in an easy manner based on the outcomes of the analysis.
- ensure that potential biases in the model (for example, overfitting to the training sample) are detected.
Comment Due Date: February 11, 2022
Keywords: Europe, EU, Banking, CRR, Basel, Machine Learning, Regulatory Capital, Credit Risk, Regtech, IRB Approach, EBA
Previous ArticleBOM Issues Multiple Regulatory Updates in November 2021
The Australian Prudential Regulation Authority (APRA) found that Heritage Bank Limited had incorrectly reported capital because of weaknesses in operational risk and compliance frameworks, although the bank did not breach minimum prudential capital ratios at any point and remains well-capitalized.
The Office of the Superintendent of Financial Institutions (OSFI) released the annual report for 2020-2021.
The Australian Prudential Regulation Authority (APRA) released the final Prudential Practice Guide on management of climate change financial risks (CPG 229) for banks, insurers, and superannuation trustees.
The European Banking Authority (EBA) Single Rulebook Question and Answer (Q&A) tool updates for this month include answers to 10 questions.
The European Commission (EC) has adopted a package of measures related to the Capital Markets Union.
The European Council adopted its position on two proposals that are part of the digital finance package adopted by the European Commission in September 2020, with one of the proposals involving the regulation on markets in crypto-assets (MiCA) and the other involving the Digital Operational Resilience Act (DORA).
The Prudential Regulation Authority (PRA) is proposing, via the consultation paper CP21/21, to apply group provisions in the Operational Resilience Part of the PRA Rulebook (relevant for the Capital Requirements Regulation or CRR firms) to holding companies.
The Board of Governors of the Federal Reserve System (FED) published a report that summarizes banking conditions in the United States, along with the supervisory and regulatory activities of FED.
The European Banking Authority (EBA) published the final report on draft regulatory technical standards for the calculation of risk-weighted exposure amounts of collective investment undertakings or CIUs, in line with the Capital Requirements Regulation (CRR).
The Australian Prudential Regulation Authority (APRA) recently completed two pilot initiatives in its 2020-2024 Cyber Security Strategy, which was published in November 2020.