Explainable AI for Fraud Detection: An Attention-Based Ensemble of CNNs, GNNs, and A Confidence-Driven Gating Mechanism

TL;DR

This paper introduces an explainable ensemble model combining CNNs, GNNs, and attention mechanisms with confidence-driven gating to improve credit card fraud detection accuracy and interpretability.

Contribution

It proposes a novel stacking-based approach with attention and confidence layers, integrating SHAP explanations for enhanced interpretability in fraud detection.

Findings

Achieves high accuracy on three datasets

Demonstrates robust generalization capabilities

Provides interpretable feature importance analysis

Abstract

The rapid expansion of e-commerce and the widespread use of credit cards in online purchases and financial transactions have significantly heightened the importance of promptly and accurately detecting credit card fraud (CCF). Not only do fraudulent activities in financial transactions lead to substantial monetary losses for banks and financial institutions, but they also undermine user trust in digital services. This study presents a new stacking-based approach for CCF detection by adding two extra layers to the usual classification process: an attention layer and a confidence-based combination layer. In the attention layer, we combine soft outputs from a convolutional neural network (CNN) and a recurrent neural network (RNN) using the dependent ordered weighted averaging (DOWA) operator, and from a graph neural network (GNN) and a long short-term memory (LSTM) network using the induced ordered weighted averaging (IOWA) operator. These weighted outputs capture different predictive signals, increasing the model's accuracy. Next, in the confidence-based layer, we select whichever aggregate (DOWA or IOWA) shows lower uncertainty to feed into a meta-learner. To make the model more explainable, we use shapley additive explanations (SHAP) to identify the top ten most important features for distinguishing between fraud and normal transactions. These features are then used in our attention-based model. Experiments on three datasets show that our method achieves high accuracy and robust generalization, making it effective for CCF detection.