Validating SAFE metrics by traditional machine learning in credit rating classification

Previous studies often binarized credit ratings, but their impact on machine learning model performance has not been thoroughly examined. Wu and Giudici (2025) address this by evaluating different binarization methods with SAFE metrics (Sustainability, Accuracy, Fairness, and Explainability metrics) Babaei et al. (2025a), which are based on Random Forest (RF), Gradient Boosting Tree (GBT), Stacked Ensemble Model (SEM) and Voting Ensemble Model (VEM).In this paper, we need to analyze various classifications and identify BB=1 and BBB=1 as the best two classifications using the method of entropy, balance scores and transition matrix. Confusion matrix, ROC curve, and prediction probability distributions help determine the best-performing classification scheme. This study validates the innovativeness and applicability of SAFE metrics, emphasizing their effectiveness in distinguishing between high-risk and low-risk categories.