Maciej Paweł Kwiatkowski

© Maciej Paweł Kwiatkowski. Article available under the CC BY-SA 4.0 licence


(English) PDF


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.


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


C41, C53, C55, C58, G20, G21


Babikov, V. G. (2013). Credit Portfolio Behavior Modeling and Stress-test. The Analytical banking Magazine, (10).

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).

Breeden, J. L. (2007). Modelling data with multiple time dimensions. Computational Statistics and Data Analysis, 51(9), 4761–4785.

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.

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

Forster, J. J., & Sudjianto, A. (2013, May 13). Modelling time and vintage variability in retail credit portfolios: the decomposition approach.

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.

International Accounting Standards Board. (2014). IFRS 9 Financial Instruments. IFRS Foundation.

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.

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

Strydom, P. (2017). Macroeconomic cycle effect on mortgage and personal loan default rates. Journal of Applied Finance and Banking, 7(6), 1–27.

Back to top
© 2019–2022 Copyright by Statistics Poland, some rights reserved. Creative Commons Attribution-ShareAlike 4.0 International Public License (CC BY-SA 4.0) Creative Commons — Attribution-ShareAlike 4.0 International — CC BY-SA 4.0