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

Paper: arXiv 2410.09069

Authors: Mehdi Hosseini Chagahi, Niloufar Delfan, Saeed Mohammadi Dashtaki, Behzad Moshiri, Md. Jalil Piran

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.

Complexity vs Empirical Score

• Math Complexity: 6.0/10
• Empirical Rigor: 6.5/10
• Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper introduces an innovative ensemble technique for credit card fraud detection by combining multiple neural network architectures (CNN, RNN, LSTM, GNN) via mathematical aggregation operators (DOWA and IOWA) and confidence-based gating. It offers good empirical validation across three datasets and enhances model interpretability using SHAP.

Research Flowchart

  flowchart TD
    A[Goal: Accurate & Explainable Credit Card Fraud Detection] --> B[Input: Financial Transaction Datasets]
    B --> C[Feature Selection: SHAP Identifies Top 10 Features]
    C --> D[Base Models: Soft Outputs from CNN, RNN, GNN, LSTM]
    D --> E[Attention Layer: DOWA & IOWA Aggregations]
    E --> F[Confidence Layer: Select Aggregation with Lowest Uncertainty]
    F --> G[Meta-Learner Classification]
    G --> H[Outcome: High Accuracy, Robust Generalization & Model Explainability]

Cited References (76)

1. Analysis and Comparison of Fraud Detection on Credit Card Transactions Using Machine Learning Algorithms (2024)
2. Credit Card Fraud Detector Based on Machine Learning Techniques ( 2023 )
3. Credit Card Fraud Detection Using Machine Learning ( 2023 )
4. CREDIT CARD FRAUD DETECTION USING MACHINE LEARNING ALGORITHMS (2024)
5. Credit Card Fraud Detection Based on Unsupervised Attentional Anomaly Detection Network ( 2023 )
6. FrauDetect: Deep Learning Based Credit Card Fraudulency Detection System (2023)
7. Credit card fraud detection using state-of-the-art machine learning and deep learning algorithms (2022)
8. A novel combined approach based on deep Autoencoder and deep classifiers for credit card fraud detection (2023)

0 of 76 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.