Addressing class imbalance in probability-of-default modeling: a comparative study of SMOTE, ensemble learning and explainable artificial intelligence

Konstantinos Papalamprou

Journal of Risk

Abstract: This study develops a governance-aligned framework for probability of default modeling under class imbalance, combining domain-informed feature engineering, resampling, ensemble learning and explainable artificial intelligence. Using real mortgage data, multiple configurations are evaluated under strict cross-validation to ensure unbiased performance estimation. The results show that economically grounded feature transformations substantially improve discrimination while maintaining transparency, whereas resampling provides only limited additional benefits once features are engineered. Ensemble architectures, in particular LightGBM and stacking, deliver strong discriminatory performance without synthetic data generation. Shapley additive explanations (SHAP) analysis confirms the economic plausibility of model drivers, while bootstrap diagnostics demonstrate robust generalization. Beyond predictive accuracy, the framework links methodological choices to supervisory priorities, showing that feature engineering can in some cases outweigh oversampling for boosting models and that explainability supports reliable model assessment.

References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.risk.net/node/7963508 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:rsk:journ4:7963508

Access Statistics for this article

More articles in Journal of Risk from Journal of Risk
Bibliographic data for series maintained by Thomas Paine ().