Supporting the Age-Period-Cohort model of default rate prediction with interpretable machine learning

Maciej Paweł Kwiatkowski

doi:https://doi.org/10.59139/ps.2023.01.3

Maciej Paweł Kwiatkowski Freelance researcher, Poland ORCID:https://orcid.org/0000-0001-6564-7786 Przegląd Statystyczny. Statistical Review, vol. 70, 2023, 1, pages: 54-78 Published online: 30 August 2023 DOI https://doi.org/10.59139/ps.2023.01.3 Citation: Kwiatkowski, M. P. (2023). Supporting the Age-Period-Cohort model of default rate prediction with interpretable machine learning. Przegląd Statystyczny. Statistical Review, 70(1), 54–78. https://doi.org/10.59139/ps.2023.01.3.

256 Views 35 Downloads

ARTICLE

(English) PDF

ABSTRACT

Regular short-term forecasting of defaults is a basic activity of a retail portfolio risk manager. From a business perspective, not only the quality of the forecast is significant, but also the understanding of the trends and their driving factors. The vintage analysis and a more advanced Age-Period-Cohort approach are popular tools used for the purpose. The aim of this article is to demonstrate that interpretable machine learning can support the Age-Period- Cohort approach, facilitating forecasting beyond the time range of training data, eliminating the model identification problem and attributing cohort quality to the specific characteristics of loans approved in a given month. The study is based on real consumer finance portfolios from the Polish market.

KEYWORDS

credit risk, macroeconomic impact, age-period-cohort, machine learning, XGBoost, SHAP

JEL

C41, C53, C55, C58, G20, G21

REFERENCES

Babikov, V. G. (2013). Credit Portfolio Behavior Modeling and Stress-test. The Analytical banking Magazine, (10). https://bsc-consult.com/doc/DtD.pdf.

Borges, M. R., & Machado, R. (2020). Modelling credit risk: evidence for EMV methodology on Portuguese mortgage data (Working Paper No. WP03/2020/DE/UECE).

Bracke, P., Datta, A., Jung, C., & Sen, S. (2019). Machine learning explainability in finance: an application to default risk analysis (Staff Working Paper No. 816). https://www.bankofengland.co.uk/-/media/boe/files/working-paper/2019/machine-learning-explainability-in-finance-an-application-to-default-risk-analysis.pdf.

Breeden, J. L. (2007). Modelling data with multiple time dimensions. Computational Statistics and Data Analysis, 51(9), 4761–4785. https://doi.org/10.1016/j.csda.2007.01.023.

Breeden, J. L. (2010). Reinventing Retail Lending Analytics. Incisive Media.

Breeden, J. L., Thomas, L., & McDonald III, J. W. (2008). Stress-testing retail loan portfolios with dual-time dynamics. The Journal of Risk Model Validation, 2(2), 43–62. https://doi.org/10.21314/JRMV.2008.033.

Chen, T., & Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco. https://doi.org/10.1145/2939672.2939785.

Forster, J. J., & Sudjianto, A. (2013, May 13). Modelling time and vintage variability in retail credit portfolios: the decomposition approach. https://doi.org/10.48550/arXiv.1305.2815.

Gamba-Santamaria, S., Melo-Velandia, L. F., & Orozco-Vanegas, C. (2021). What can credit vintages tell us about non-performing loans?. Borradores de Economia, (1154), 1–27. https://repositorio.banrep.gov.co/handle/20.500.12134/9973.

International Accounting Standards Board. (2014). IFRS 9 Financial Instruments. IFRS Foundation. http://www.kasb.or.kr/upload/constancy/20140730/IFRS9_July%202014_Basis%20for%20Conclusions_WEBSITE_144.pdf.

Kaszyński, D., Kamiński, B., & Szapiro, T. (red.). (2020). Credit Scoring in Context of Interpretable Machine Learning: Theory and Practice. SGH Publishing House.

Lawrence, D., & Solomon, A. (2002). Managing a Consumer Lending Business. Solomon Lawrence Partners.

Lundberg, S. M., & Lee, S.-I. (2017). A Unified Approach to Interpreting Model Predictions. In I. U. von Luxburg, Guyon, S., Bengio, H. Wallach, R., Fergus, S. Vishwanathan, & R. Garnett (Eds.), Advances in Neural Information Processing Systems 30: 31st Annual Conference on Neural Information Processing Systems (pp. 4765–4774). Curran Associates.

Siarka, P. (2011). Vintage Analysis as a Basic Tool for Monitoring Credit Risk. Mathematical Economics, (14), 213–228. https://dbc.wroc.pl/Content/18921/Siarka_Vintage_Analysis_As_A_Basic_Tool_2011.pdf.

Siddiqi, N. (2017). Intelligent Credit Scoring: Building and Implementing Better Credit Risk Scorecards (2nd edition). SAS Institute. John Willey & Sons. https://doi.org/10.1002/9781119282396.

Strydom, P. (2017). Macroeconomic cycle effect on mortgage and personal loan default rates. Journal of Applied Finance and Banking, 7(6), 1–27. http://www.scienpress.com/Upload/JAFB/Vol%207_6_1.pdf.