Improving Credit Card Fraud Detection with an Optimized Explainable Boosting Machine

TL;DR

This paper enhances credit card fraud detection by optimizing an explainable machine learning model through hyperparameter tuning and data preprocessing, achieving high accuracy without sacrificing interpretability.

Contribution

It introduces a systematic optimization workflow for the Explainable Boosting Machine, improving fraud detection performance while maintaining transparency.

Findings

Achieved ROC-AUC of 0.983 on benchmark data

Outperformed traditional models like Logistic Regression and XGBoost

Demonstrated effective balance between accuracy and interpretability

Abstract

Addressing class imbalance is a central challenge in credit card fraud detection, as it directly impacts predictive reliability in real-world financial systems. To overcome this, the study proposes an enhanced workflow based on the Explainable Boosting Machine (EBM)-a transparent, state-of-the-art implementation of the GA2M algorithm-optimized through systematic hyperparameter tuning, feature selection, and preprocessing refinement. Rather than relying on conventional sampling techniques that may introduce bias or cause information loss, the optimized EBM achieves an effective balance between accuracy and interpretability, enabling precise detection of fraudulent transactions while providing actionable insights into feature importance and interaction effects. Furthermore, the Taguchi method is employed to optimize both the sequence of data scalers and model hyperparameters, ensuring robust, reproducible, and systematically validated performance improvements. Experimental evaluation on benchmark credit card data yields an ROC-AUC of 0.983, surpassing prior EBM baselines (0.975) and outperforming Logistic Regression, Random Forest, XGBoost, and Decision Tree models. These results highlight the potential of interpretable machine learning and data-driven optimization for advancing trustworthy fraud analytics in financial systems.