Financial Services Advisory

Machine learning in IRB

By:
Brian O'Dwyer,
Dwayne Price,
Frankie Cronin,
Nuala Crimmins,
Amanda Ward,
Mark Perry,
Lukas Majer
28 Jun 20222 min read
insight featured image
How Grant Thornton can help you understand the challenges surrounding the implementation and validation of machine learning techniques in IRB models.
Contents

Subscribe to our mailing list

Update your subscriptions for Grant Thornton publications and events.

This paper will provide an overview of the current and future uses of Machine Learning in the world of Internal Rating Based (IRB) Models which allow banks to model their own inputs for calculating Risk Weighted Assets.

What are Internal Rating Based (IRB) Models?

Risk Weighted Assets (and as a result capital requirements) for credit risk can be calculated either using the IRB or Standardised Approach.  IRB models represent a more advanced and risk sensitive approach, breaking down into three component parts (PD, LGD, EAD):

  1. Probability of Default (PD): What is the chance that the borrower will default on a 1 year time horizon?
  2. Loss Given Default (LGD): How much will I get back (and therefore how much will I lose) in the event of default?
  3. Exposure at Default (EAD): If the borrower defaults, what will be the size of my exposure?

A Bank’s IRB approach can be classified either as Foundation or Advanced:

(1) Foundation IRB (FIRB) Approach:  Banks estimate PD and use regulatory prescribed estimates of LGD and EAD.

(2) Advanced IRB (AIRB) Approach:  Banks use their own estimates of PD, LGD, and EAD.

TAGS
Authors
  • Brian O'Dwyer
    Brian O'Dwyer Brian joined the firm in 2015 and is the current lead of the Consulting team specialising in designing and leading major business transformation programmes. View Profile
  • Dwayne Price
    Dwayne Price Dwayne joined Grant Thornton in 2016 as partner to head our Regulatory Advisory Services offering. Dwayne leads the firm’s risk and regulatory offering focusing on Quantitative Risk Advisory, Regulatory Risk and Strategy, and Regulatory Support services. View Profile
  • Frankie Cronin
    Frankie Cronin Frankie is a Partner in Grant Thornton’s Advisory practice and leads the dedicated Business Risk Services team. View Profile
  • Nuala Crimmins
    Nuala Crimmins Nuala joined the firm as a Partner in 2021 and is Head of Insurance Risk and Actuarial Services for Grant Thornton Ireland. View Profile
  • Amanda Ward
    Amanda Ward Amanda joined Grant Thornton in August 2020 as a Partner in our Consulting team. Prior to joining Grant Thornton Amanda spent 8 years with the Irish branch of an International Nordic Bank finishing in the role of Chief Operating Officer. Prior to this she spent 8 years with a Big Four firm where she worked with the Financial Effectiveness Consulting and Audit divisions. View Profile
  • Mark Perry
    Mark Perry Mark joined Grant Thornton in 2018 having previously held a Senior Management role in Risk Strategy at Bank of Ireland Group where he worked in Credit Risk Measurement. Mark is a Director in the Quantitative Risk service line. View Profile
  • Lukas Majer
    Lukas Majer Lukas is a Director in our Quantitative Risk team. He has extensive experience in Scorecard/Calibration build and validation, including low default portfolios (LDPs), long run average and lifetime probability of default estimation. View Profile