Financial Fraud Detection Using Explainable AI and Stacking Ensemble Methods

TL;DR

This paper presents a fraud detection framework that combines stacking ensemble models with explainable AI techniques to achieve high accuracy and transparency, improving trust and compliance in financial fraud detection.

Contribution

It introduces a novel combination of stacking ensemble methods with XAI techniques like SHAP, LIME, PDP, and PFI for transparent and accurate financial fraud detection.

Findings

Achieved 99% accuracy and 0.99 AUC-ROC on the IEEE-CIS dataset.

Enhanced interpretability of models using SHAP, LIME, PDP, and PFI.

Outperformed recent related approaches in fraud detection performance.

Abstract

Traditional machine learning models often prioritize predictive accuracy, often at the expense of model transparency and interpretability. The lack of transparency makes it difficult for organizations to comply with regulatory requirements and gain stakeholders trust. In this research, we propose a fraud detection framework that combines a stacking ensemble of well-known gradient boosting models: XGBoost, LightGBM, and CatBoost. In addition, explainable artificial intelligence (XAI) techniques are used to enhance the transparency and interpretability of the model's decisions. We used SHAP (SHapley Additive Explanations) for feature selection to identify the most important features. Further efforts were made to explain the model's predictions using Local Interpretable Model-Agnostic Explanation (LIME), Partial Dependence Plots (PDP), and Permutation Feature Importance (PFI). The IEEE-CIS Fraud Detection dataset, which includes more than 590,000 real transaction records, was used to evaluate the proposed model. The model achieved a high performance with an accuracy of 99% and an AUC-ROC score of 0.99, outperforming several recent related approaches. These results indicate that combining high prediction accuracy with transparent interpretability is possible and could lead to a more ethical and trustworthy solution in financial fraud detection.