Balancing Explainability and Privacy in Bank Failure Prediction: A Differentially Private Glass-Box Approach
TL;DR
This study uses differentially private glass-box models to predict bank failures, balancing explainability for stakeholders with data privacy protection.
Balancing Explainability and Privacy in Bank Failure Prediction: A Differentially Private Glass-Box Approach
Junyoung Byun; Jaewook Lee; Hyeongyeong Lee; Bumho Son
https://doi.org/10.1109/ACCESS.2024.3523967
Volume 13
Predicting bank failures is a critical task requiring balancing the need for model explainability with the necessity of preserving data privacy. Traditional machine learning models often lack transparency, which poses challenges for stakeholders who need to understand the factors leading to predictions. In this study, we employ differentially private glass-box models, namely Explainable Boosting M...