Fraud Detection in Credit Card Transactions using a Hybrid Approach of GNN+XAI: A Review

International Journal of Electronics and Communication Engineering

© 2026 by SSRG - IJECE Journal

Volume 13 Issue 3

Year of Publication : 2026

Authors : Riya Chaudhari, Shilpa Pant

10.14445/23488549/IJECE-V13I3P118

How to Cite?

Riya Chaudhari, Shilpa Pant, "Fraud Detection in Credit Card Transactions using a Hybrid Approach of GNN+XAI: A Review," SSRG International Journal of Electronics and Communication Engineering, vol. 13,  no. 3, pp. 213-226, 2026. Crossref, https://doi.org/10.14445/23488549/IJECE-V13I3P118

Abstract:

The digital payment systems have grown in leaps and bounds, resulting in an increased volume of financial transactions, but simultaneously exposing systems to massive new vulnerabilities. Credit card fraud has increasingly become a challenge to detect because financial transaction datasets in reality present an imbalanced nature, a dynamic nature, and intricate relationships among users, devices, merchants, and geographic positions. Conventional machine learning algorithms have provided important baselines but have broadly treated each financial transaction independently without considering the relational behaviour present in collusive financial fraud. Deep learning algorithms have enhanced these baselines by incorporating temporal characteristics and nonlinear dependencies, but have not offered sufficient capabilities to model intricate financial relationships among fraudulent actors. Recently, research has focused on graph models where Graph Neural Networks have modelled financial settings as graph systems, providing opportunities for multiple financial entities to identify relationships and collusive patterns among them. The black box nature of GNN models, however, has spurred debate among financial institutions concerning their transparency requirements and capabilities in adhering to financial rules and regulations. Techniques in Explainable AI have increasingly gained attention to address these issues, but have presently demonstrated limited capabilities in providing transactional-level explanations for large graphs with heterogeneous elements. This review mainly aims to critically analyse literature developments in machine learning, deep learning, graph models, and Explainable AI paradigms, and identify an emerging requirement for hybrid architectures incorporating Graph Neural Networks and Explainable AI for developing financially sound solutions with optimized paths in financial systems.

Keywords:

Credit Card Fraud Detection, Explainable AI, Graph Neural Networks, Machine Learning, Transaction Networks.

References:

[1] Suraya Nurain Kalid et al., “A Multiple Classifiers System for Anomaly Detection in Credit Card Data with Unbalanced and Overlapped Classes,” IEEE Proceedings, vol. 8, pp. 28210-28221, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Ebenezer Esenogho et al., “A Neural Network Ensemble with Feature Engineering for Improved Credit Card Fraud Detection,” IEEE Access, vol. 10, pp. 16400-16407, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Ibomoiye Domor Mienye, and Nobert Jere, “Deep Learning for Credit Card Fraud Detection: A Review of Algorithms, Challenges, and Solutions,” IEEE Access, vol. 12, pp. 96893-96910, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Asma Cherif et al., “Encoder–Decoder Graph Neural Network for Credit Card Fraud Detection,” Journal of King Saud University - Computer and Information Sciences, vol. 36, no. 3, pp. 1-11, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Yiwen Cui et al., “FraudGNN-RL: A Graph Neural Network with Reinforcement Learning for Adaptive Financial Fraud Detection,” IEEE Open Journal of the Computer Society, vol. 6, pp. 426-437, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Mir Riyanul Islam, Mobyen Uddin Ahmed, and Shahina Begum, “iXGB: Improving the Interpretability of XGBoost Using Decision Rules,” 16th International Conference on Agents and Artificial Intelligence, Rome, Italy, pp. 1345-1353, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Jay Raval et al., “RaKShA: A Trusted Explainable LSTM Model to Classify Fraud Patterns on Credit Card Transactions,” Mathematics, vol. 11, no. 8, pp. 1-27, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Kianeh Kandi, and Antonio García-Dopico, “Enhancing Performance of Credit Card Fraud Detection Models by Utilizing LSTM Networks and XGBoost Algorithms,” Machine Learning and Knowledge Extraction, vol. 7, no. 1, pp. 1-21, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Fawaz Khaled Alarfaj, and Shabnam Shahzadi, “Enhancing Fraud Detection in Banking with Deep Learning: Graph Neural Networks and Autoencoders for Real-Time Credit Card Fraud Prevention,” IEEE Access, vol. 13, pp. 20633-20646, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Mohammed Tayebi, and Said El Kafhal, “Generative Modelling for Imbalanced Credit Card Fraud Transaction Detection,” Journal of Cybersecurity and Privacy, vol. 5, no. 1, pp. 1-36, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Huang Tingfei, Cheng Guangquan, and Huang Kuihua, “Using Variational Auto Encoding in Credit Card Fraud Detection,” IEEE Access, vol. 8, pp. 149841-149853, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Fray L. Becerra-Suarez, Halyn Alvarez-Vasquez, and Manuel G. Forero, “Improvement of Bank Fraud Detection through Synthetic Data Generation with Gaussian Noise,” Technologies, vol. 13, no. 4, pp. 1-18, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Nahid Ferdous Aurna et al., “FedFusion: Adaptive Model Fusion for Addressing Feature Discrepancies in Federated Credit Card Fraud Detection,” IEEE Access, vol. 12, pp. 136962-136978, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Asma Cherif et al., “Credit Card Fraud Detection in the Era of Disruptive Technologies: A Systematic Review,” Journal of King Saud University - Computer and Information Sciences, vol. 35, no. 1, pp. 145-174, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Ahmad Asiri, and K. Somasundaram, “Graph Convolution Network for Fraud Detection in Bitcoin Transactions,” Scientific Reports, vol. 15, pp. 1-14, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Scott M. Lundberg et al., “From Local Explanations to Global Understanding with Explainable AI for Trees,” Nature Machine Intelligence, vol. 2, pp. 56-67, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Wenying Xie et al., “Supply Chain Financial Fraud Detection Based on Graph Neural Network and Knowledge Graph,” Technical Gazette, Directory of Open Access Journals (DOAJ), vol. 31, no. 6, pp. 2055-2063, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[18] L. Selvam et al., “A Deep Learning Model for Investment Scam Prevention in Financial Systems: Autoencoder-based Anomaly Detection,” 2025 3rd International Conference on Inventive Computing and Informatics(ICICI), Bangalore, India, pp. 868-875, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Leman Akoglu, Hanghang Tong, and Danai Koutra, “Graph based Anomaly Detection and Description: A Survey,” Data Mining and Knowledge Discovery, vol. 29, pp. 626-688, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Guansong Pang et al., “Deep Learning for Anomaly Detection: A Review,” ACM Computing Surveys, vol. 54, no. 2, pp. 1-38, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Siddhartha Bhattacharyya et al., “Data Mining for Credit Card Fraud: A Comparative Study,” Decision Support Systems, vol. 50, no. 3, pp. 602-613, 2011.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Guoxiang Tong, and Jieyu Shen, “Financial Transaction Fraud Detector Based on Imbalance Learning and Graph Neural Network,” Applied Soft Computing, vol. 149, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Feifen Shi, and Chuanjun Zhao, “Enhancing Financial Fraud Detection with Hierarchical Graph Attention Networks: A Study on Integrating Local and Extensive Structural Information,” Finance Research Letters, vol. 58, pp. 1-16, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Uzair Aslam Bhatti et al., “Deep Learning with Graph Convolutional Networks: An Overview and Latest Applications in Computational Intelligence,” International Journal of Intelligent Systems, vol. 2023, pp. 1-28, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Jie Chen, Tengfei Ma, and Cao Xiao, “FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling,” ICLR Proceedings, pp. 1-15, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Wei-Lin Chiang et al., “Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks,” Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage AK USA, pp. 257-266, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Zhao Li et al., “A Graph-Powered Large-Scale Fraud Detection System,” International Journal of Machine Learning and Cybernetics, vol. 15, pp. 115-128, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Rahul Kapale et al., “Explainable AI for Fraud Detection: Enhancing Transparency and Trust in Financial Decision-Making,” Proceedings of the 2024 2nd DMIHER International Conference on Artificial Intelligence in Healthcare, Education and Industry (IDICAIEI), Wardha, India, pp. 1-6, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Christoph Molnar, Interpretable Machine Learning: A Guide for Making Black-Box Models Explainable, pp. 1-320, 2020.
[Google Scholar] [Publisher Link]
[30] Soroor Motie, and Bijan Raahemi, “Financial Fraud Detection Using Graph Neural Networks: A Systematic Review,” Expert Systems with Applications, vol. 240, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[31] Quentin Cappart et al., “Combinatorial Optimization and Reasoning with Graph Neural Networks,” Journal of Machine Learning Research, vol. 24, pp. 1-61, 2023.
[Google Scholar] [Publisher Link]
[32] Diego Vallarino, “AI-Powered Fraud Detection in Financial Services: GNN, Compliance Challenges and Risk Mitigation,” SSRN Working Paper, pp. 1-34, 2025.
[CrossRef] [Google Scholar] [Publisher Link]