Author(s)

HaoYu Wu, JiaYi Wang^*

Affiliation(s)

Huazhong University of Science and Technology, Wuhan 430070, Hubei, China.

Corresponding Author

JiaYi Wang

ABSTRACT

The exponential growth of e-commerce platforms has transformed global trade, enabling seamless digital transactions. However, this expansion has also led to an increase in fraudulent activities, including fake transactions, money laundering, and synthetic account fraud. Traditional fraud detection systems, which rely on predefined rules or supervised learning models, struggle to adapt to evolving fraudulent tactics. This study proposes a graph neural network (GNN)-driven anomaly detection framework to improve fraud detection in e-commerce systems by leveraging the inherent graph structure of online transactions.

The proposed approach models e-commerce transactions as a heterogeneous transaction graph, where nodes represent users, merchants, and transaction records, while edges encode relationships such as purchase behavior, payment connections, and review activity. The framework integrates graph convolutional networks (GCN) and graph attention networks (GAT) for spatial anomaly detection, combined with temporal graph networks to track transaction sequence patterns. Unlike traditional methods, this approach captures both structural transaction dependencies and time-based anomalies, enabling the detection of coordinated fraud schemes.

Extensive experiments on real-world e-commerce transaction datasets demonstrate that the proposed model outperforms conventional fraud detection techniques, achieving a higher detection accuracy and a significantly lower false positive rate. The results highlight the effectiveness of graph-based learning in identifying complex fraud rings, transaction laundering, and fraudulent refund behaviors. This research underscores the importance of GNN-powered fraud detection in enhancing e-commerce security, providing an adaptive and scalable solution for modern digital marketplaces.

KEYWORDS

Graph neural networks; E-Commerce fraud; Anomaly detection; Transaction security; Machine learning; Temporal graph networks

CITE THIS PAPER

HaoYu Wu, JiaYi Wang. Gnn-driven detection of anomalous transactions in e-commerce systems. Journal of Trends in Applied Science and Advanced Technologies. 2025, 2(1): 13-20. DOI: https://doi.org/10.61784/asat3010.

REFERENCES

[1] Alexander I, Lai C, Yang H C. Deep Learning Based Behavior Anomaly Detection within the Context of Electronic Commerce. In 2023 IEEE International Conference on Intelligence and Security Informatics (ISI), 2023: 1-6.

[2] Reddy S R B, Kanagala P, Ravichandran P, et al. Effective fraud detection in e-commerce: Leveraging machine learning and big data analytics. Measurement: Sensors, 2024, 33: 101138.

[3] Shao Z, Wang X, Ji E, et al. GNN-EADD: Graph Neural Network-based E-commerce Anomaly Detection via Dual-stage Learning. IEEE Access, 2025.

[4] Tax N, de Vries K J, de Jong M, et al. Machine learning for fraud detection in e-Commerce: A research agenda. In Deployable Machine Learning for Security Defense: Second International Workshop, MLHat 2021, Virtual Event. Springer International Publishing, 2021: 30-54.

[5] Kalifa D, Singer U, Guy I, et al. Leveraging world events to predict e-commerce consumer demand under anomaly. In Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining, 2022: 430-438.

[6] Ounacer S, El Bour H A, Oubrahim Y, et al. Using Isolation Forest in anomaly detection: the case of credit card transactions. Periodicals of Engineering and Natural Sciences, 2018, 6(2): 394-400.

[7] Westland J C. A comparative study of frequentist vs Bayesian A/B testing in the detection of E-commerce fraud. Journal of Electronic Business & Digital Economics, 2022, 1(1/2): 3-23.

[8] Rani S, Mittal A. Securing Digital Payments a Comprehensive Analysis of AI Driven Fraud Detection with Real Time Transaction Monitoring and Anomaly Detection. In 2023 6th International Conference on Contemporary Computing and Informatics (IC3I). IEEE, 2023, 6: 2345-2349.

[9] Wankhedkar R, Jain S K. Motif discovery and anomaly detection in an ECG using matrix profile. In Progress in Advanced Computing and Intelligent Engineering: Proceedings of ICACIE 2019. Springer Singapore, 2021, 1: 88-95.

[10] Liang Y, Wang X, Wu Y C, et al. A study on blockchain sandwich attack strategies based on mechanism design game theory. Electronics, 2021, 12(21): 4417.

[11] Kim H, Lee B S, Shin W Y, et al. Graph anomaly detection with graph neural networks: Current status and challenges. IEEE Access, 2022, 10: 111820-111829.

[12] Groenewald E, Kilag O K. E-commerce inventory auditing: Best practices, challenges, and the role of technology. International Multidisciplinary Journal of Research for Innovation, Sustainability, and Excellence (IMJRISE), 2024, 1(2): 36-42.

[13] Ebrahim M, Golpayegani S A H. Anomaly detection in business processes logs using social network analysis. Journal of Computer Virology and Hacking Techniques, 2022: 1-13.

[14] Singh P, Singla K, Piyush P, et al. Anomaly Detection Classifiers for Detecting Credit Card Fraudulent Transactions. In 2024 Fourth International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT). IEEE, 2024: 1-6.

[15] Lee Z, Wu Y C, Wang X. Automated Machine Learning in Waste Classification: A Revolutionary Approach to Efficiency and Accuracy. In Proceedings of the 2023 12th International Conference on Computing and Pattern Recognition, 2023: 299-303.

[16] Li X, Wang X, Chen X, et al. Unlabeled data selection for active learning in image classification. Scientific Reports, 2024, 14(1): 424.

[17] Ye K. Anomaly detection in clouds: Challenges and practice. In Proceedings of the first Workshop on Emerging Technologies for software-defined and reconfigurable hardware-accelerated Cloud Datacenters, 2017: 1-2.

[18] Liu Y, Wu Y C, Fu H, et al. Digital intervention in improving the outcomes of mental health among LGBTQ+ youth: a systematic review. Frontiers in psychology, 2023, 14: 1242928.

[19] Guo H, Ma Z, Chen X, et al. Generating artistic portraits from face photos with feature disentanglement and reconstruction. Electronics, 2024, 13(5): 955.

[20] Almalki S, Assery N, Roy K. An empirical evaluation of online continuous authentication and anomaly detection using mouse clickstream data analysis. Applied Sciences, 2021, 11(13): 6083.

[21] Wang X, Wu Y C, Zhou M, et al. Beyond surveillance: privacy, ethics, and regulations in face recognition technology. Frontiers in big data, 2024, 7: 1337465.

[22] Goyal G, Tyagi R, Tyagi S. Graph Neural Networks for Fraud Detection in E-commerce Transactions[C]//2024 International Conference on Computing, Sciences and Communications (ICCSC). IEEE, 2024: 1-6.

[23] Agrawal A M. Transforming e-commerce with Graph Neural Networks: Enhancing personalization, security, and business growth//Applied Graph Data Science. Morgan Kaufmann, 2025: 215-224.

[24] Kim H, Lee B S, Shin W Y, et al. Graph anomaly detection with graph neural networks: Current status and challenges. IEEE Access, 2022, 10: 111820-111829.

[25] Wang X, Wu Y C, Ma Z. Blockchain in the courtroom: exploring its evidentiary significance and procedural implications in US judicial processes. Frontiers in Blockchain, 2024, 7: 1306058.

[26] Benkabou S E, Benabdeslem K, Kraus V, et al. Local anomaly detection for multivariate time series by temporal dependency based on poisson model. IEEE Transactions on Neural Networks and Learning Systems, 2021, 33(11): 6701-6711.

[27] Gandhudi M, Alphonse P J A, Velayudham V, et al. Explainable causal variational autoencoders based equivariant graph neural networks for analyzing the consumer purchase behavior in E-commerce. Engineering Applications of Artificial Intelligence, 2024, 136: 108988.

[28] Ramakrishnan J, Shaabani E, Li C, et al. Anomaly detection for an e-commerce pricing system. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019: 1917-1926.

[29] Porwal U, Mukund S. Credit card fraud detection in e-commerce: An outlier detection approach. arXiv preprint arXiv:1811.02196, 2018.

[30] Bozbura M, Tunc H C, Kusak M E, et al. Detection of e-Commerce Anomalies using LSTM-recurrent Neural Networks. In DATA, 2019: 217-224.