Featured Product

    EBA Consults on Use of Machine Learning for IRB Credit Risk Models

    November 11, 2021

    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.

     

    Related Links

    Comment Due Date: February 11, 2022

    Keywords: Europe, EU, Banking, CRR, Basel, Machine Learning, Regulatory Capital, Credit Risk, Regtech, IRB Approach, EBA

    Featured Experts
    Related Articles
    News

    BSP Tackles Aspects of Lending and Islamic, Open & Sustainable Finance

    The Central Bank of the Philippines (BSP) issued communications covering developments related to online lending platforms, open finance framework and roadmap, and on the expected regulations in the area sustainable finance.

    January 16, 2022 WebPage Regulatory News
    News

    US Agencies Issue Regulatory Updates, FDIC Launches Tech Sprint

    The Board of Governors of the Federal Reserve System (FED) published the final rule that amends Regulation I to reduce the quarterly reporting burden for member banks by automating the application process for adjusting their subscriptions to the Federal Reserve Bank capital stock, except in the context of mergers.

    January 13, 2022 WebPage Regulatory News
    News

    EBA Issues Guide on Bank Resolvability, Consults on Transferability

    The European Banking Authority (EBA) published its assessment of risks through the quarterly Risk Dashboard and the results of the Autumn edition of the Risk Assessment Questionnaire (RAQ).

    January 13, 2022 WebPage Regulatory News
    News

    MFSA Publishes CRD5 Updates and Supervisory Priorities for 2022

    The Malta Financial Services Authority (MFSA) updated the guidelines on supervisory reporting requirements under the reporting framework 3.0.

    January 13, 2022 WebPage Regulatory News
    News

    HKMA Extends Repayment for Trade Facilities, Consults on Crypto-Assets

    The Hong Kong Monetary Authority (HKMA) published a circular, along with the reporting form and instructions, for self-assessment, by authorized institutions, of compliance with the Code of Banking Practice 2021.

    January 12, 2022 WebPage Regulatory News
    News

    FCA Registers Securitization Repositories; PRA Issues 2022 Priorities

    The Financial Conduct Authority (FCA) decided to register European DataWarehouse Ltd and SecRep Limited as securitization repositories under the UK Securitization Regulation, with effect from January 17, 2022.

    January 12, 2022 WebPage Regulatory News
    News

    EC Regulation Sets Out Methods for Measuring K-Factors Under IFR

    The European Commission (EC) published the Delegated Regulation 2022/25, which supplements the Investment Firms Regulation (IFR or Regulation 2019/2033) with respect to the regulatory technical standards specifying the methods for measuring the K-factors referred to in Article 15 of the IFR.

    January 11, 2022 WebPage Regulatory News
    News

    BIS Studies How Platform Models Impact Financial Stability & Inclusion

    The Bank of International Settlements (BIS) published a paper that assesses the ways in which platform-based business models can affect financial inclusion, competition, financial stability and consumer protection.

    January 10, 2022 WebPage Regulatory News
    News

    CBE Issues Additional Measures to Ease Disruptions from Pandemic

    The Central Bank of Egypt (CBE) published a circular with instructions on emergency liquidity assistance to banks that are unable to meet their liquidity requirements.

    January 10, 2022 WebPage Regulatory News
    News

    ESAs Publish List of Financial Conglomerates for 2021

    The European Supervisory Authorities (ESAs) published the list of identified financial conglomerates for 2021.

    January 07, 2022 WebPage Regulatory News
    RESULTS 1 - 10 OF 7868