@article {Ramtekejfds.2022.1.089, author = {Anand K. Ramteke and Pavan Wadhwa and Monica Yan}, title = {Interpretability of Machine Learning versus Statistical Credit Risk Models}, elocation-id = {jfds.2022.1.089}, year = {2022}, doi = {10.3905/jfds.2022.1.089}, publisher = {Institutional Investor Journals Umbrella}, abstract = {Model interpretability is important in the banking industry for three reasons: certain US regulations require creditors to provide consumers with the reasons for taking adverse action (reason codes) on their credit applications; model users want to understand the reasoning behind model predictions; and identification of bias and reinforcement of stakeholders{\textquoteright} trust in the model. In this article, the authors compare the interpretability of an XGBoost versus a logistic model in predicting the probability of default for a credit card customer. They conclude that (1) the reason codes of an XGBoost model and a comparable logistic model are similar, (2) reason codes generated by XGBoost are more trustworthy from the customer{\textquoteright}s perspective, and (3) nonlinearity of XGBoost is unlikely to have a significant impact on reason code(s).}, issn = {2640-3943}, URL = {https://jfds.pm-research.com/content/early/2022/03/26/jfds.2022.1.089}, eprint = {https://jfds.pm-research.com/content/early/2022/03/26/jfds.2022.1.089.full.pdf}, journal = {The Journal of Financial Data Science} }