Journal of Risk

Risk.net

Explainable artificial intelligence for credit scoring in banking

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

  • This study uses XAI methods in banking, exploring how these methods can be applied to improve the interpretability and reliability of state-of-the-art ML models.
  • A LightGBM model is combined with SHAP, which enables the interpretation of explanatory variables affecting the predictions.
  • it is proposed that LightGBM models may outperform logistic regression models for credit scoring both in terms of predictive performance and explainability.

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.

Sorry, our subscription options are not loading right now

Please try again later. Get in touch with our customer services team if this issue persists.

New to Risk.net? View our subscription options

You need to sign in to use this feature. If you don’t have a Risk.net account, please register for a trial.

Sign in
You are currently on corporate access.

To use this feature you will need an individual account. If you have one already please sign in.

Sign in.

Alternatively you can request an individual account here