Explainable artificial intelligence for credit scoring in banking

Borger Melsom, Christian Bakke Vennerød, Petter Eilif de Lange, Lars Ole Hjelkrem and Sjur Westgaard

Journal of Risk

Abstract: This paper proposes an explainable machine learning model for predicting credit default using a real-world data set provided by a Norwegian bank. We combine a Light Gradient Boosting Machine (LightGBM) model with Shapley additive explanations (SHAP), an explainable artificial intelligence (XAI) framework that enables the interpretation of explanatory variables affecting the predictions. Using the Light- GBM model, we achieve a 1% increase in the area under the receiver operating characteristic curve and a 19% increase in the area under the precision recall curve compared with an industry-standard logistic regression model. An empirical analysis using SHAP on the explanatory variables is also conducted. Our main contribution is the exploration of how the implementation of XAI methods can be applied in banking to improve the interpretability and reliability of state-of-the-art machine learning models. We specifically find that LightGBM models may outperform logistic regression models for credit scoring in terms of both predictive performance and explainability.

References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.risk.net/journal-of-risk/7955208/expla ... t-scoring-in-banking (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:journ4:7955208

Access Statistics for this article

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