Graph-Temporal Contrastive Transformer for Financial Fraud Detection Using Transaction Behavior Modeling
Open Access
- 8 December 2025
- journal article
- research article
- Published by MDPI AG in Algorithms
- Vol. 18 (12) , 770
Abstract
Detection of financial fraud remains a constant challenge due to the dynamic and highly imbalanced nature of transaction data. This paper proposes the Graph-Temporal Contrastive Transformer (GTCT) framework for modeling both structural dependencies between accounts and temporal evolution in transactional behaviors. We propose a model that combines three components: a graph encoder for modeling relationships between accounts, a temporal encoder for learning sequential patterns in transactions, and a contrastive learning objective that enhances the robustness of representations when supervision is limited. To assess the contribution of each component individually, we systematically remove one module at a time. As shown, an exclusion of the contrastive loss resulted in reduced recall and AUC from 0.867 and 0.982 to 0.805 and 0.948, respectively, indicating the importance of self-supervised learning of representations in fraud detection. Similarly, removing the graph encoder decreased the F1-score from 0.876 to 0.786, which confirmed that modeling transaction structures between accounts is crucial for the identification of complex fraud rings. The exclusion of the temporal encoder led to a more drastic drop in recall (0.743) and AUC (0.905), indicating that capturing the temporal dynamics of transactions is relevant. By comparing all variants, the full GTCT model attained the highest accuracy (0.975) and AUC (0.982), thus showing superior robustness in the detection of sophisticated and evolving financial fraud patterns.Keywords
This publication has 34 references indexed in Scilit:
- Graph neural networks for financial fraud detection: a reviewFrontiers of Computer Science, 2025
- A survey of dynamic graph neural networksFrontiers of Computer Science, 2024
- CARLA: Self-supervised contrastive representation learning for time series anomaly detectionPattern Recognition, 2024
- An intelligent sequential fraud detection model based on deep learningThe Journal of Supercomputing, 2024
- Encoder–decoder graph neural network for credit card fraud detectionJournal of King Saud University Computer and Information Sciences, 2024
- A soft voting ensemble learning approach for credit card fraud detectionHeliyon, 2024
- UzADL: Anomaly detection and localization using graph Laplacian matrix-based unsupervised learning methodComputers & Industrial Engineering, 2022
- Taxonomy of Fraud Detection Metrics for Business ProcessesIEEE Access, 2020
- Learned lessons in credit card fraud detection from a practitioner perspectiveExpert Systems with Applications, 2014
- The application of data mining techniques in financial fraud detection: A classification framework and an academic review of literatureDecision Support Systems, 2011