IDEAS home Printed from https://ideas.repec.org/a/eee/finana/v84y2022ics1057521922003222.html
   My bibliography  Save this article

Can machine learning models save capital for banks? Evidence from a Spanish credit portfolio

Author

Listed:
  • Alonso-Robisco, Andrés
  • Carbó, José Manuel

Abstract

We study the impact of machine learning (ML) models for credit default prediction in the calculation of regulatory capital by financial institutions. We do so by using a unique and anonymized database from a major Spanish bank. We first compare the statistical performance of five models based on supervised learning like Logistic Lasso, Trees (CART), Random Forest, XGBoost and Deep Learning, with a well-known model like Logit. We measure the statistical performance through different metrics, and for different sample sizes and features available. We find that ML models outperform, even when relatively low amount of data is used. We then translate this statistical performance into economic impact by estimating the savings in capital when using an advanced ML model instead of a simpler one to compute the risk-weighted assets following the Internal Ratings Based (IRB) approach. Our benchmark results show that implementing XGBoost instead of Logistic Lasso could yield savings from 12.4% to 17% in terms of regulatory capital requirements.

Suggested Citation

  • Alonso-Robisco, Andrés & Carbó, José Manuel, 2022. "Can machine learning models save capital for banks? Evidence from a Spanish credit portfolio," International Review of Financial Analysis, Elsevier, vol. 84(C).
    • Handle: RePEc:eee:finana:v:84:y:2022:i:c:s1057521922003222
    DOI: 10.1016/j.irfa.2022.102372
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S1057521922003222
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.irfa.2022.102372?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Dominique Guegan & Bertrand Hassani, 2018. "Regulatory learning: How to supervise machine learning models? An application to credit scoring," Université Paris1 Panthéon-Sorbonne (Post-Print and Working Papers) halshs-01835213, HAL.
    2. Yiping Huang & Ms. Longmei Zhang & Zhenhua Li & Han Qiu & Tao Sun & Xue Wang, 2020. "Fintech Credit Risk Assessment for SMEs: Evidence from China," IMF Working Papers 2020/193, International Monetary Fund.
    3. Edson Bastos e Santos & Neil Esho & Marc Farag & Christopher Zuin, 2020. "Variability in risk-weighted assets: what does the market think?," BIS Working Papers 844, Bank for International Settlements.
    4. Christophe Schalck & Meryem Yankol-Schalck, 2021. "Predicting French SME failures: new evidence from machine learning techniques," Applied Economics, Taylor & Francis Journals, vol. 53(51), pages 5948-5963, November.
    5. Stefania Albanesi & Domonkos F. Vamossy, 2019. "Predicting Consumer Default: A Deep Learning Approach," NBER Working Papers 26165, National Bureau of Economic Research, Inc.
    6. 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.
    7. Dominique Guegan & Bertrand Hassani, 2018. "Regulatory learning: How to supervise machine learning models? An application to credit scoring," Post-Print halshs-01835213, HAL.
    8. Butaru, Florentin & Chen, Qingqing & Clark, Brian & Das, Sanmay & Lo, Andrew W. & Siddique, Akhtar, 2016. "Risk and risk management in the credit card industry," Journal of Banking & Finance, Elsevier, vol. 72(C), pages 218-239.
    9. Bartlett, Robert & Morse, Adair & Stanton, Richard & Wallace, Nancy, 2022. "Consumer-lending discrimination in the FinTech Era," Journal of Financial Economics, Elsevier, vol. 143(1), pages 30-56.
    10. Anastasios Petropoulos & Vasilis Siakoulis & Evaggelos Stavroulakis & Aristotelis Klamargias, 2019. "A robust machine learning approach for credit risk analysis of large loan level datasets using deep learning and extreme gradient boosting," IFC Bulletins chapters, in: Bank for International Settlements (ed.), Are post-crisis statistical initiatives completed?, volume 49, Bank for International Settlements.
    11. Gabriel Jiménez & Jesús Saurina, 2006. "Credit Cycles, Credit Risk, and Prudential Regulation," International Journal of Central Banking, International Journal of Central Banking, vol. 2(2), May.
    12. Mirko Moscatelli & Simone Narizzano & Fabio Parlapiano & Gianluca Viggiano, 2019. "Corporate default forecasting with machine learning," Temi di discussione (Economic working papers) 1256, Bank of Italy, Economic Research and International Relations Area.
    13. Khandani, Amir E. & Kim, Adlar J. & Lo, Andrew W., 2010. "Consumer credit-risk models via machine-learning algorithms," Journal of Banking & Finance, Elsevier, vol. 34(11), pages 2767-2787, November.
    14. Justin Sirignano & Rama Cont, 2019. "Universal features of price formation in financial markets: perspectives from deep learning," Quantitative Finance, Taylor & Francis Journals, vol. 19(9), pages 1449-1459, September.
    15. Maria Ludovica Drudi & Stefano Nobili, 2021. "A liquidity risk early warning indicator for Italian banks: a machine learning approach," Temi di discussione (Economic working papers) 1337, Bank of Italy, Economic Research and International Relations Area.
    16. Yan Zhang & Peter Trubey, 2019. "Machine Learning and Sampling Scheme: An Empirical Study of Money Laundering Detection," Computational Economics, Springer;Society for Computational Economics, vol. 54(3), pages 1043-1063, October.
    17. Jones, Stewart & Johnstone, David & Wilson, Roy, 2015. "An empirical evaluation of the performance of binary classifiers in the prediction of credit ratings changes," Journal of Banking & Finance, Elsevier, vol. 56(C), pages 72-85.
    18. Christophe Schalck & Meryem Yankol-Schalck, 2021. "Predicting French SME failures: new evidence from machine learning techniques," Post-Print hal-03573319, HAL.
    19. Andrés Alonso Robisco & José Manuel Carbó Martínez, 2022. "Measuring the model risk-adjusted performance of machine learning algorithms in credit default prediction," Financial Innovation, Springer;Southwestern University of Finance and Economics, vol. 8(1), pages 1-35, December.
    20. Anastasios Petropoulos & Vasilis Siakoulis & Evaggelos Stavroulakis & Aristotelis Klamargias, 2019. "A robust machine learning approach for credit risk analysis of large loan-level datasets using deep learning and extreme gradient boosting," IFC Bulletins chapters, in: Bank for International Settlements (ed.), The use of big data analytics and artificial intelligence in central banking, volume 50, Bank for International Settlements.
    21. Laura Blattner & Scott Nelson & Jann Spiess, 2021. "Unpacking the Black Box: Regulating Algorithmic Decisions," Papers 2110.03443, arXiv.org, revised Jul 2023.
    22. Jeremy D. Turiel & Tomaso Aste, 2019. "P2P Loan acceptance and default prediction with Artificial Intelligence," Papers 1907.01800, arXiv.org.
    23. Sigrist, Fabio & Hirnschall, Christoph, 2019. "Grabit: Gradient tree-boosted Tobit models for default prediction," Journal of Banking & Finance, Elsevier, vol. 102(C), pages 177-192.
    24. Fraisse, Henri & Laporte, Matthias, 2022. "Return on investment on artificial intelligence: The case of bank capital requirement," Journal of Banking & Finance, Elsevier, vol. 138(C).
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Cosma, Simona & Rimo, Giuseppe & Torluccio, Giuseppe, 2023. "Knowledge mapping of model risk in banking," International Review of Financial Analysis, Elsevier, vol. 89(C).
    2. Bolívar, Fernando & Duran, Miguel A. & Lozano-Vivas, Ana, 2023. "Business model contributions to bank profit performance: A machine learning approach," Research in International Business and Finance, Elsevier, vol. 64(C).
    3. Zhou, Ying & Shen, Long & Ballester, Laura, 2023. "A two-stage credit scoring model based on random forest: Evidence from Chinese small firms," International Review of Financial Analysis, Elsevier, vol. 89(C).

    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. Andrés Alonso & José Manuel Carbó, 2021. "Understanding the performance of machine learning models to predict credit default: a novel approach for supervisory evaluation," Working Papers 2105, Banco de España.
    2. Andrés Alonso Robisco & José Manuel Carbó Martínez, 2022. "Measuring the model risk-adjusted performance of machine learning algorithms in credit default prediction," Financial Innovation, Springer;Southwestern University of Finance and Economics, vol. 8(1), pages 1-35, December.
    3. García-Céspedes, Rubén & Moreno, Manuel, 2022. "The generalized Vasicek credit risk model: A Machine Learning approach," Finance Research Letters, Elsevier, vol. 47(PA).
    4. Lisa Crosato & Caterina Liberati & Marco Repetto, 2021. "Look Who's Talking: Interpretable Machine Learning for Assessing Italian SMEs Credit Default," Papers 2108.13914, arXiv.org, revised Sep 2021.
    5. Hoang, Daniel & Wiegratz, Kevin, 2022. "Machine learning methods in finance: Recent applications and prospects," Working Paper Series in Economics 158, Karlsruhe Institute of Technology (KIT), Department of Economics and Management.
    6. Nicola Branzoli & Ilaria Supino, 2020. "FinTech credit: a critical review of empirical research," Questioni di Economia e Finanza (Occasional Papers) 549, Bank of Italy, Economic Research and International Relations Area.
    7. Paritosh Navinchandra Jha & Marco Cucculelli, 2021. "A New Model Averaging Approach in Predicting Credit Risk Default," Risks, MDPI, vol. 9(6), pages 1-15, June.
    8. Andrés Alonso & José Manuel Carbó, 2022. "Accuracy of explanations of machine learning models for credit decisions," Working Papers 2222, Banco de España.
    9. Königstorfer, Florian & Thalmann, Stefan, 2020. "Applications of Artificial Intelligence in commercial banks – A research agenda for behavioral finance," Journal of Behavioral and Experimental Finance, Elsevier, vol. 27(C).
    10. Apostolos Ampountolas & Titus Nyarko Nde & Paresh Date & Corina Constantinescu, 2021. "A Machine Learning Approach for Micro-Credit Scoring," Risks, MDPI, vol. 9(3), pages 1-20, March.
    11. Roy Cerqueti & Francesca Pampurini & Annagiulia Pezzola & Anna Grazia Quaranta, 2022. "Dangerous liasons and hot customers for banks," Review of Quantitative Finance and Accounting, Springer, vol. 59(1), pages 65-89, July.
    12. Dimitrios Nikolaidis & Michalis Doumpos, 2022. "Credit Scoring with Drift Adaptation Using Local Regions of Competence," SN Operations Research Forum, Springer, vol. 3(4), pages 1-28, December.
    13. Chen, Dangxing & Ye, Jiahui & Ye, Weicheng, 2023. "Interpretable selective learning in credit risk," Research in International Business and Finance, Elsevier, vol. 65(C).
    14. Jan Svanberg & Tohid Ardeshiri & Isak Samsten & Peter Öhman & Presha E. Neidermeyer & Tarek Rana & Natalia Semenova & Mats Danielson, 2022. "Corporate governance performance ratings with machine learning," Intelligent Systems in Accounting, Finance and Management, John Wiley & Sons, Ltd., vol. 29(1), pages 50-68, January.
    15. Agnese Carella & Federica Ciocchetta & Valentina Michelangeli & Federico Maria Signoretti, 2020. "What can we learn about mortgage supply from online data?," Questioni di Economia e Finanza (Occasional Papers) 583, Bank of Italy, Economic Research and International Relations Area.
    16. Wosnitza, Jan Henrik, 2022. "Calibration alternatives to logistic regression and their potential for transferring the dispersion of discriminatory power into uncertainties of probabilities of default," Discussion Papers 04/2022, Deutsche Bundesbank.
    17. Agarwal, Shivam & Muckley, Cal B. & Neelakantan, Parvati, 2023. "Countering racial discrimination in algorithmic lending: A case for model-agnostic interpretation methods," Economics Letters, Elsevier, vol. 226(C).
    18. Peter Martey Addo & Dominique Guegan & Bertrand Hassani, 2018. "Credit Risk Analysis Using Machine and Deep Learning Models," Risks, MDPI, vol. 6(2), pages 1-20, April.
    19. Fraisse, Henri & Laporte, Matthias, 2022. "Return on investment on artificial intelligence: The case of bank capital requirement," Journal of Banking & Finance, Elsevier, vol. 138(C).
    20. Dina Ait Lahcen, 2023. "Synthetic Reading Of The Different Approaches And Models For Assessing The Risk Of Business Failure [Lecture Synthétique Des Diverses Approches Et Modèles D'Évaluation Du Risque De La Défaillance D," Post-Print hal-04009420, HAL.

    More about this item

    Keywords

    Machine learning; Credit risk; Prediction; Probability of default; IRB system;
    All these keywords.

    JEL classification:

    • C45 - Mathematical and Quantitative Methods - - Econometric and Statistical Methods: Special Topics - - - Neural Networks and Related Topics
    • C38 - Mathematical and Quantitative Methods - - Multiple or Simultaneous Equation Models; Multiple Variables - - - Classification Methdos; Cluster Analysis; Principal Components; Factor Analysis
    • G21 - Financial Economics - - Financial Institutions and Services - - - Banks; Other Depository Institutions; Micro Finance Institutions; Mortgages

    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:eee:finana:v:84:y:2022:i:c:s1057521922003222. 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: Catherine Liu (email available below). General contact details of provider: http://www.elsevier.com/locate/inca/620166 .

    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.