Explainable Artificial Intelligence in Credit Risk: Evaluating Machine Learning and Traditional Models in Buy Now Pay Later under EU Regulation

Sammanfattning

This paper examines the trade-off between predictive performance and interpretabilityin credit risk modeling within a buy-now-pay-later (BNPL) setting. Using a proprietarydataset from Walley, the study compares logistic regression with random forest and XGBoost. To assess interpretability, SHAP and LIME are applied as post-hoc explainabilitymethods.The study is motivated by the growing use of machine learning in credit scoring, whereimproved predictive performance must be balanced against transparency, validation, andsupervisory requirements. The results show that XGBoost provides the strongest predictive performance across all evaluations and the XAI methods used provided insights intothe black-box models. LIME delivers case-specific, local explanations for individual predictions while SHAP provided an overview of the global characteristics and how differentfeatures interacted in the framework.Overall, the findings suggest that machine learning models can improve predictive performance in credit risk modeling, but that their practical usefulness depends on whethertheir outputs can be explained in a meaningful and transparent way.