IDEAS home Printed from https://ideas.repec.org/p/boe/boeewp/0816.html
   My bibliography  Save this paper

Machine learning explainability in finance: an application to default risk analysis

Author

Listed:
  • Bracke, Philippe

    (UK Financial Conduct Authority)

  • Datta, Anupam

    (Carnegie Mellon University)

  • Jung, Carsten

    (Bank of England)

  • Sen, Shayak

    (Carnegie Mellon University)

Abstract

We propose a framework for addressing the ‘black box’ problem present in some Machine Learning (ML) applications. We implement our approach by using the Quantitative Input Influence (QII) method of Datta et al (2016) in a real‑world example: a ML model to predict mortgage defaults. This method investigates the inputs and outputs of the model, but not its inner workings. It measures feature influences by intervening on inputs and estimating their Shapley values, representing the features’ average marginal contributions over all possible feature combinations. This method estimates key drivers of mortgage defaults such as the loan‑to‑value ratio and current interest rate, which are in line with the findings of the economics and finance literature. However, given the non‑linearity of ML model, explanations vary significantly for different groups of loans. We use clustering methods to arrive at groups of explanations for different areas of the input space. Finally, we conduct simulations on data that the model has not been trained or tested on. Our main contribution is to develop a systematic analytical framework that could be used for approaching explainability questions in real world financial applications. We conclude though that notable model uncertainties do remain which stakeholders ought to be aware of.

Suggested Citation

  • Bracke, Philippe & Datta, Anupam & Jung, Carsten & Sen, Shayak, 2019. "Machine learning explainability in finance: an application to default risk analysis," Bank of England working papers 816, Bank of England.
  • Handle: RePEc:boe:boeewp:0816
    as

    Download full text from publisher

    File URL: https://www.bankofengland.co.uk/-/media/boe/files/working-paper/2019/machine-learning-explainability-in-finance-an-application-to-default-risk-analysis.pdf
    File Function: Full text
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Andreas Fuster & Matthew Plosser & Philipp Schnabl & James Vickery, 2019. "The Role of Technology in Mortgage Lending," The Review of Financial Studies, Society for Financial Studies, vol. 32(5), pages 1854-1899.
    2. Aron, Janine & Muellbauer, John, 2016. "“Modelling and forecasting mortgage delinquency and foreclosure in the UK.”," Journal of Urban Economics, Elsevier, vol. 94(C), pages 32-53.
    3. John Y. Campbell & João F. Cocco, 2015. "A Model of Mortgage Default," Journal of Finance, American Finance Association, vol. 70(4), pages 1495-1554, August.
    4. Christopher L. Foote & Paul S. Willen, 2018. "Mortgage-Default Research and the Recent Foreclosure Crisis," Annual Review of Financial Economics, Annual Reviews, vol. 10(1), pages 59-100, November.
    5. Andreas Fuster & Paul Goldsmith‐Pinkham & Tarun Ramadorai & Ansgar Walther, 2022. "Predictably Unequal? The Effects of Machine Learning on Credit Markets," Journal of Finance, American Finance Association, vol. 77(1), pages 5-47, February.
    6. Lazarov, Vladimir & Hinterschweiger, Marc, 2018. "Determinants of distress in the UK owner-occupier and buy-to-let mortgage markets," Bank of England working papers 760, Bank of England.
    7. Andreas Fuster & Paul S. Willen, 2017. "Payment Size, Negative Equity, and Mortgage Default," American Economic Journal: Economic Policy, American Economic Association, vol. 9(4), pages 167-191, November.
    8. Chakraborty, Chiranjit & Gimpelewicz, Mariana & Uluc, Arzu, 2017. "A tiger by the tail: estimating the UK mortgage market vulnerabilities from loan-level data," Bank of England working papers 703, Bank of England.
    9. Dent, Kieran & Westwood, Ben & Segoviano, Miguel, 2016. "Stress testing of banks: an introduction," Bank of England Quarterly Bulletin, Bank of England, vol. 56(3), pages 130-143.
    10. Dynan Karen & Elmendorf Douglas & Sichel Daniel, 2012. "The Evolution of Household Income Volatility," The B.E. Journal of Economic Analysis & Policy, De Gruyter, vol. 12(2), pages 1-42, December.
    11. Gogas, Periklis & Papadimitriou, Theophilos & Agrapetidou, Anna, 2018. "Forecasting bank failures and stress testing: A machine learning approach," International Journal of Forecasting, Elsevier, vol. 34(3), pages 440-455.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. O’Toole, Conor & Slaymaker, Rachel, 2021. "Repayment capacity, debt service ratios and mortgage default: An exploration in crisis and non-crisis periods," Journal of Banking & Finance, Elsevier, vol. 133(C).
    2. Cumming, Fergus, 2018. "Mortgages, cash-flow shocks and local employment," Bank of England working papers 773, Bank of England.
    3. Cumming, Fergus, 2022. "Mortgage cash-flows and employment," European Economic Review, Elsevier, vol. 144(C).
    4. Piskorski, Tomasz & Seru, Amit, 2021. "Debt relief and slow recovery: A decade after Lehman," Journal of Financial Economics, Elsevier, vol. 141(3), pages 1036-1059.
    5. Andrieș, Alin Marius & Copaciu, Anca & Popa, Radu & Vlahu, Razvan, 2025. "Recourse and (strategic) mortgage defaults: Evidence from changes in housing market laws," European Economic Review, Elsevier, vol. 173(C).
    6. Terry O'Malley, 2021. "The Impact of Repossession Risk on Mortgage Default," Journal of Finance, American Finance Association, vol. 76(2), pages 623-650, April.
    7. Liu, Lu, 2023. "The demand for long-term mortgage contracts and the role of collateral," Bank of England working papers 1009, Bank of England.
    8. Nadav Ben Zeev, 2019. "Adjustable-Rate Mortgages, Systematic Monetary Policy, And The Root Cause Of The Financial Crisis," Working Papers 1908, Ben-Gurion University of the Negev, Department of Economics.
    9. Erik Hembre & Stephanie Moulton & Matthew Record, 2021. "Low‐Income Homeownership and the Role of State Subsidies: A Comparative Analysis of Mortgage Outcomes," Journal of Policy Analysis and Management, John Wiley & Sons, Ltd., vol. 40(1), pages 78-106, January.
    10. Liu, Lu, 2023. "The demand for long-term mortgage contracts and the role of collateral," ESRB Working Paper Series 142, European Systemic Risk Board.
    11. Luca Barbaglia & Sebastiano Manzan & Elisa Tosetti, 2023. "Forecasting Loan Default in Europe with Machine Learning," Journal of Financial Econometrics, Oxford University Press, vol. 21(2), pages 569-596.
    12. Jorge E. Galán & Matías Lamas, 2019. "Beyond the LTV ratio: new macroprudential lessons from Spain," Working Papers 1931, Banco de España.
    13. Stefano Colonnello & Mariela Dal Borgo, 2024. "Raising Household Leverage: Evidence from Co-Financed Mortgages," Working Papers 2024: 01, Department of Economics, University of Venice "Ca' Foscari".
    14. Matteo Benetton, 2021. "Leverage Regulation and Market Structure: A Structural Model of the U.K. Mortgage Market," Journal of Finance, American Finance Association, vol. 76(6), pages 2997-3053, December.
    15. Xie, Xueyan & Zhu, Xiaoyang, 2022. "FinTech and capital allocation efficiency: Another equity-efficiency dilemma?," Global Finance Journal, Elsevier, vol. 53(C).
    16. Andreas Fuster & Aurel Hizmo & Lauren Lambie-Hanson & James Vickery & Paul S. Willen, 2021. "How Resilient Is Mortgage Credit Supply? Evidence from the COVID-19 Pandemic," Working Papers 21-4, Federal Reserve Bank of Boston.
    17. David Gaddis Ross & Dong Hyun Shin, 2024. "Do financial market frictions hurt the performance of women‐led ventures? A meta‐analytic investigation," Strategic Management Journal, Wiley Blackwell, vol. 45(3), pages 507-534, March.
    18. Congjin Zhou & Guojing Wang & Yinghui Dong & Pin Wang, 2024. "The Valuation at Origination of Mortgages with Full Prepayment and Default Risks," Methodology and Computing in Applied Probability, Springer, vol. 26(2), pages 1-26, June.
    19. Sabrina T. Howell & Theresa Kuchler & David Snitkof & Johannes Stroebel & Jun Wong, 2024. "Lender Automation and Racial Disparities in Credit Access," Journal of Finance, American Finance Association, vol. 79(2), pages 1457-1512, April.
    20. Ángel Estrada & Christian Castro, 2021. "Function and application of the new macroprudential tools available to the Banco de España," Financial Stability Review, Banco de España, issue Spring.

    More about this item

    Keywords

    Machine learning; explainability; mortgage defaults;
    All these keywords.

    JEL classification:

    • C55 - Mathematical and Quantitative Methods - - Econometric Modeling - - - Large Data Sets: Modeling and Analysis
    • G21 - Financial Economics - - Financial Institutions and Services - - - Banks; Other Depository Institutions; Micro Finance Institutions; Mortgages

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:boe:boeewp:0816. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Digital Media Team (email available below). General contact details of provider: https://edirc.repec.org/data/boegvuk.html .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.