Skip to content
Open access

Temporal and Relational Graph Neural Networks for Fraud Detection in Transaction Networks

2026 · IEEE Open Journal of the Computer Society · Vol 7, pp. 1439-1449 · 1 citation · 29 references
Computer Science

TL;DR

This paper introduces a graph neural network (GNN) framework that integrates temporal encoding, edge-aware message passing, and a relation-specific decoder, trained using weighted binary cross-entropy as the main objective, with focal loss evaluated as an alternative imbalance-aware objective in the ablation study.

Abstract

Financial fraud in credit card and bank transactions remains a significant challenge, as traditional detection systems often struggle to keep pace with evolving fraudulent strategies. This paper addresses the problem by formulating fraud detection as a supervised link prediction task in transaction networks, with the contribution positioned as a task-specific integration of temporal encoding, edge-level attributes, graph message passing, and relation-specific decoding rather than a new standalone GNN operator. We introduce a graph neural network (GNN) framework that integrates temporal encoding, edge-aware message passing, and a relation-specific decoder, trained using weighted binary cross-entropy as the main objective, with focal loss evaluated as an alternative imbalance-aware objective in the ablation study. Extensive experiments on two benchmark datasets, the ULB Credit Card Fraud dataset (ULB) and a heterogeneous Bank Transaction dataset, demonstrate that the proposed model achieves the strongest performance among the evaluated classical machine learning, homogeneous GNN, and heterogeneous GNN baselines. The ULB dataset is modeled as an induced temporal-context graph because raw entity identifiers are unavailable, whereas the bank transactions dataset is modeled as an observed heterogeneous entity-relation graph. On ULB, the model attains an F1 of 0.901, an AUROC of 0.990, and an AUPRC of 0.901. On the bank transactions dataset, it reaches an F1 of 0.914, an AUROC of 0.992, and an AUPRC of 0.966. Cross-dataset evaluations confirm strong generalization, with F1 up to 0.854 (ULB $\rightarrow$ bank) and 0.874 (bank $\rightarrow$ ULB). Ablation studies reveal that temporal encoding, edge attributes, and relation-specific decoding each contribute significantly to performance. Moreover, scalability analysis reveals near-linear offline inference growth within the evaluated edge range, indicating computational feasibility for moderate-scale transaction graphs. Overall, the proposed framework offers a robust, efficient, and transferable GNN-based solution for detecting link-based fraud in financial systems.

Read PDF

Similar papers

Preprint Oct 2026

RGH-GNN : Risk-Gated Heterogeneous Graph Neural Network for Financial Fraud Detection

Credit card fraud is a significant problem for financial institutions, resulting in substantial monetary loss each year. Fraud patterns and methods are continuously evolving, with fraudulent transactions often disguised to resemble legitimate activity. Real world transaction data for fraud detection is severely affecte...

Mythreyee Hari, Subin Sahayam, Vegesna S. M. Srinivasavarma · 0 citations
Open access Oct 2026

Modeling Practice of Graph Neural Networks in Related Party Transaction Recognition and Financial Fraud Detection

Detecting financial fraud in Related Party Transactions (RPTs) remains a critical challenge for financial institutions due to complex corporate structures, obfuscation tactics, and limitations of conventional rule-based detection systems. Traditional methods fail to capture hidden relational patterns and temporal dynam...

Xi Zhang · 0 citations
Conference Open access Sep 2026

Evolutionary Multi-Objective Graph Neural Network for Adaptive Financial Fraud Detection in Dynamic Transaction Networks

Financial fraud detection is still complex and difficult because the financial transaction systems have created large scale, imbalanced, heterogeneous and continuous evolving transaction networks and fraudulent behaviours are fast changing. Current graph-based and deep-learning solutions enhance relational representati...

M.Srikanth, Kondapalli Sanjay Kumar, K. Harsha et al. · 0 citations
Review Open access Nov 2026

Tackling Class Imbalance in Financial Fraud Detection with Relational Graph Transformers and Contrastive Learning

Detecting fraud on financial transaction networks is difficult for three reasons that tend to appear together: fraudulent users deliberately disguise their behavior, their activity is linked to other entities through several distinct relation types, such as a shared merchant, a shared rating or a short time window, and...

Qian-Rui Gu, Qing-Yue Wang, Song-Chao Zhang · 0 citations
Open access Oct 2026

Hybrid neuro-symbolic graph explanation framework for fraud detection in financial transaction networks

Introduction This research focuses on the development of a hybrid neuro-symbolic system for fraud detection in rapidly expanding digital financial systems. Methods A bipartite customer-merchant graph is constructed from the Nigerian Financial Transactions dataset, and a 3-layer Graph Attention Network (FraudGAT) is use...

Neeraj Kumar, Idhikash J., J. S et al. · 0 citations
#graph neural networks Open access Oct 2026

Rule anchored graph learning improves synthetic identity fraud detection through multi relation structure rather than score level fusion

Synthetic Identity Fraud (SIF), in which fraudsters combine real and fabricated information to create untraceable identities, is a fast-growing and costly problem in payment systems. Prior work treats graph neural networks as an assumed improvement over transparent rule-based identity-linkage scoring, but rarely tests...

T. Nguyen, C. Chiu · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.