Fraud Detection Using temporal sequence embedding and Cluster-Weighted LSTM Models in Card Transactions

Document Type : Original Article

Authors

Samiyeh khosravi ¹

Mehrdad Kargari ²

Babak Teimourpour ¹

Mohammad Talebi ³

Abdollah Eshghi ¹

¹ Faculty of Industrial and systems engineering,Tarbiat Modares University, Tehran, Iran.

² Faculty of Industrial and Systems Engineering, Tarbiat Modares University, Tehran, Iran.

³ Faculty of Management, Imam Sadiq University, Tehran, Iran

10.22067/cke.2025.92170.1150

Abstract

Traditional fraud detection models often overlook the sequential and temporal relationships between transactions, which can be crucial for identifying fraudulent activities. To address this, a new data-to-graph mapping approach is proposed, transforming user data into a transaction graph and constructing a bipartite graph with source and target nodes. The main goal is to leverage the temporal order of transactions to capture changes effectively and identify distinct fraud patterns. The method begins by creating a weighted graph based on transaction amounts and their temporal sequence. For feature extraction, the Probabilistic FraudWalk method—an advanced version of the traditional FraudWalk algorithm—is used. This method enhances the random walk process by incorporating probability-based neighbor selection, dynamically choosing the next node based on the probability distribution of common neighbors. To balance the dataset, the Synthetic Minority Over-sampling Technique (SMOTE) is combined with the Edited Nearest Neighbors (ENN) method, forming SMOTE-ENN. To reduce information conflict, data is clustered using K-means clustering. A weighted Long Short-Term Memory (LSTM) model is then trained on each cluster, with weights determined by the minimum distance between samples of different classes within the same cluster. The proposed LSTM model demonstrates superior performance on benchmark datasets, effectively detecting fraud in real-world card-to-card transactions. This approach enhances the security of financial information for banks and financial institutions, showing that incorporating temporal and sequential data significantly improves fraud detection accuracy and reliability.

Keywords

Fraud detection

Bipartite graph

Node embedding

Weighted LSTM

Source neighbor sequence

Target neighbor sequence

Temporal node embedding

Subjects

• Machine learning

---

References

1. Fanai et al. (2023). A novel combined approach based on deep Autoencoder and deep classifiers for credit card fraud detection. Expert Systems with Applications. [Online]. 217, p. 119562. Available: https://doi.org/10.1016/j.eswa.2023.119562
2. Abdallah et al. (2016). Fraud detection system: A survey. Journal of Network and Computer Applications. [Online]. 68, pp. 90–113. Available: https://doi.org/10.1016/j.jnca.2016.04.007
3. Motie et al. (2023). Financial fraud detection using graph neural networks: A systematic review. Expert Systems with Applications. [Online]. 240, p. 122156. Available: https://doi.org/10.1016/j.eswa.2023.122156
4. Esenogho et al. (2022). A neural network ensemble with feature engineering for improved credit card fraud detection. IEEE Access. [Online]. 10, pp. 16400–16407. Available: https://doi.org/10.1109/ACCESS.2022.3148298
5. Hilal et al. (2022). Financial fraud: A review of anomaly detection techniques and recent advances. Expert Systems with Applications. [Online]. 193, p. 116429. Available: https://doi.org/10.1016/j.eswa.2021.116429
6. Tian et al. (2023). Transaction fraud detection via spatial-temporal-aware graph transformer. arXiv preprint arXiv:2307.05121. [Online]. Available: https://arxiv.org/abs/2307.05121
7. V. Kute et al. (2021). Deep learning and explainable artificial intelligence techniques applied for detecting money laundering – a critical review. IEEE Access. [Online]. 9, pp. 82300–82317. Available: https://doi.org/10.1109/ACCESS.2021.3086230
8. N. Eddin et al. (2021). Anti-money laundering alert optimization using machine learning with graphs. arXiv preprint arXiv:2112.07508. [Online]. Available: https://arxiv.org/abs/2112.07508
9. Bao et al. (2022). Artificial intelligence and fraud detection. Innovative Technology at the Interface of Finance and Operations: Volume I. [Online]. pp. 223–247. Available: https://doi.org/10.1007/978-3-030-75729-8_8
10. Wu et al. (2023). Advancement of management information system for discovering fraud in master card based intelligent supervised machine learning and deep learning during SARS‑CoV2. Information Processing & Management. [Online]. 60, 103231. Available: https://doi.org/10.1016/j.ipm.2022.103231
11. Xie et al. (2022). Learning transactional behavioral representations for credit card fraud detection. IEEE Transactions on Neural Networks and Learning Systems. [Online]. 35(4), pp. 5735–5748. Available: https://doi.org/10.1109/TNNLS.2022.3208967
12. F. Roseline et al. (2022). Autonomous credit card fraud detection using machine learning approach. Computers and Electrical Engineering. [Online]. 102, p. 108132. Available: https://doi.org/10.1016/j.compeleceng.2022.108132
13. Guo et al, “Learning sequential behavior representations for fraud detection,” in Proceeding IEEE International Conference Data Mining (ICDM), 2018, pp. 127–136. Available: https://doi.org/10.1109/ICDM.2018.00028
14. Agarwal et al. (2021). Hybrid CNN‑BiLSTM‑attention based identification and prevention system for banking transactions. NVEO – Natural Volatiles & Essential Oils Journal. [Online]. 7, pp. 2552–2560.
15. Fakiha. (2023). Forensic credit card fraud detection using deep neural network. Journal of Southwest Jiaotong University. [Online]. 58(1), pp. 1–20. Available: https://doi.org/10.35741/issn.0258-2724.58.1.33
16. Zioviris. (2022). Credit card fraud detection using a deep learning multistage model. The Journal of Supercomputing. [Online]. 78, pp. 14571–14596. Available: https://doi.org/10.1007/s11227-022-04465-9
17. Raval, J., Bhattacharya, P., Jadav, N. K., Tanwar, S., Sharma, G., Bokoro, P. N., Elmorsy, M., Tolba, A., & Raboaca, M. S. (2023). RaKShA: A trusted explainable LSTM model to classify fraud patterns on credit card transactions. Mathematics. [Online]. 11, p. 1901. Available: https://doi.org/10.3390/math11081901
18. Wang et al., “A semi‑supervised graph attentive network for financial fraud detection,” in Proceeding IEEE International Conference Data Mining (ICDM), 2019, pp. 598–607. https://doi.org/10.1109/ICDM.2019.00070
19. Jiang et al. (2022). Telecom fraud detection via Hawkes‑enhanced sequence model. IEEE Transactions on Knowledge and Data Engineering. [Online]. 35, pp. 5311–5314. Available: https://doi.org/10.1109/TKDE.2022.3150803
20. Liu et al. (2023). Improving fraud detection via hierarchical attention‑based graph neural network. Journal of Information Security and Applications. [Online]. 72, p. 103399. Available: https://doi.org/10.1016/j.jisa.2022.103399
21. Wang et al., "Modeling heterogeneous graph network on fraud detection: a community-based framework with attention mechanism," in Proceedings of the 30th ACM International Conference on Information & Knowledge Management, 2021, pp. 1959-1968. Available: https://doi.org/10.1145/3459637.3482277
22. Liu et al. (2020). Fraud detection via behavioral sequence embedding. Knowledge and Information Systems. [Online]. 62, pp. 2685–2708. Available: https://doi.org/10.1007/s10115-019-01433-3
23. Imran et al. (2025). Leveraging LSTM and attention for high‑accuracy credit card fraud detection. Fusion: Practice and Applications. [Online]. 17(1), 209–220.
24. Trinh et al. (2024). Dynamic graph neural networks for multi‑level financial fraud detection: A temporal‑structural approach. Annals of Applied Sciences. [Online]. 5(1).
25. Dal Pozzolo et al., “Calibrating probability with undersampling for unbalanced classification,” in Proceeding IEEE symposium series on computational intelligence, 2015, pp. 159–166.
26. F. A. Gadi et al., “Credit card fraud detection with artificial immune system,” in international conference on artificial immune systems, Berlin, Heidelberg, 2008, pp. 119–131. Availale: https://doi.org/10.1007/978-3-540-85072-4_11
27. Jurgovsky et al. (2018). Sequence classification for credit‑card fraud detection. Expert Systems with Applications. [Online]. 100, pp. 234–245. Available: https://doi.org/10.1016/j.eswa.2018.01.037