USING GRAPH CENTRALITY METRICS FOR DETECTION OF SUSPICIOUS TRANSACTIONS

Authors

DOI:

https://doi.org/10.37943/22ZSKI6025

Keywords:

social network analysis, centrality measures, financial fraud detection, betweenness centrality, anti-money laundering, transaction networks, graph-based anomaly detection, explainable AI

Abstract

This study addresses the critical challenge of detecting suspicious transactions in modern financial networks, focusing on the persistent threat of money laundering and related fraudulent activities. We propose a graph-based approach where each financial participant—whether an individual or an institution—is modeled as a node, and directed edges represent the flow of transactions. Using a dataset of anonymized banking records, we construct a directed graph and then calculate centrality measures, including degree centrality, betweenness centrality, closeness centrality, and eigenvector centrality. These metrics quantify how actively each node participates in or controls the circulation of funds across the network. Nodes characterized by particularly high values for betweenness or degree centrality emerge as potential “bridge” entities, acting as conduits for the majority of transaction paths. Our results indicate that these high-centrality participants may be key to understanding illicit financial flows, because they facilitate significant volumes of transactions or exert disproportionate influence by connecting otherwise separate sub-networks. Furthermore, a visualization of subgraphs around these nodes reveals tightly knit structures, suggesting the presence of possible hidden clusters that could be orchestrating complex money-laundering schemes. Overall, the proposed network-driven approach provides an efficient lens for early detection of suspicious accounts and transaction routes, especially when integrated with contemporary machine learning technologies for real-time analytics. The study concludes that centrality-based screening can enhance both the speed and accuracy of anti-fraud interventions, thereby strengthening the resilience of financial institutions in an increasingly data-rich and interconnected global economy.

Author Biographies

Rustem Baigabyl, Astana IT University, Kazakhstan

Master's student, MBA "Financial technology and digital transformation of business"

Aliya Nugumanova, Astana IT University, Kazakhstan

PhD, Head of the Scientific and Innovation Center «Big Data and Blockchain Technologies»

Mariia Sodnomova, Astana IT University, Kazakhstan

Bachelor’s degree, BS “IT-Entrepreneurship”

References

Lawlor-Forsyth, E., & Gallant, M. M. (2018). Financial institutions and money laundering: A threatening relationship. Journal of Banking Regulation, 19(2), 131-148.

Financial Action Task Force. (2023). Digital transformation of AML/CFT for operational agencies. Retrieved May 30, 2025, from https://www.fatf-gafi.org/en/publications/Digitaltransformation/Digital-transformation-aml-cft.html

Lewis, J. B. (2022). Money finds a way: increasing AML regulation garners diminishing returns and increases demand for dark financing. Vand. J. Transnat'l L., 55, 529.

Ahmed, M., Mahmood, A. N., & Islam, M. R. (2016). A survey of anomaly detection techniques in financial domain. Future Generation Computer Systems, 55, 278–288. https://doi.org/10.1016/j.future.2015.09.018

Huang, Z., Zheng, H., Li, C., & Che, C. (2024). Application of machine learning-based k-means clustering for financial fraud detection. Academic Journal of Science and Technology, 10(1), 33–39.

Savage, D., Wang, Q., Chou, P., Zhang, X., & Yu, X. (2016). Detection of money laundering groups using supervised learning in networks. arXiv Preprint, arXiv:1608.00708. https://arxiv.org/abs/1608.00708

Sun, X., Feng, W., Liu, S., Xie, Y., Bhatia, S., Hooi, B., ... & Cheng, X. (2022, February). MonLAD: Money laundering agents detection in transaction streams. In Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining (pp. 976-986).

Pambudi, B. N., Fauziati, S., & Hidayah, I. (2022). A minimum error-based PCA for improving classifier performance in detecting financial fraud. Jurnal Teknik Elektro, 14(1), 1–9.

Zhu, M., Zhang, Y., Gong, Y., Xu, C., & Xiang, Y. (2024). Enhancing credit card fraud detection a neural network and smote integrated approach. arXiv preprint arXiv:2405.00026.

Sousa Lima, R. (2022). Social network analysis applied to money laundering detection in Brazil. Journal of Financial Crime, 29(4), 1152–1168. https://doi.org/10.1108/JFC-09-2021-0210

Deprez, B., Vanderschueren, T., Verbeke, W., Baesens, B., & Verdonck, T. (2024). Network analytics for anti-money laundering: A systematic literature review and experimental evaluation. arXiv Preprint, arXiv:2405.19383. https://arxiv.org/abs/2405.19383

Gerbrands, P., Stancu, A. M., & Nozina, M. (2021). Centrality measures in criminal network analysis for money laundering. Journal of Illicit Economies and Development, 3(2), 136–149. https://doi.org/10.31389/jied.94

Smith, K., & Allen, T. (2021). Graph-based detection of anomalous financial transactions using social network analysis. IEEE Access, 9, 145932–145945. https://doi.org/10.1109/ACCESS.2021.3123483

Lee, J. H., & Park, S. (2022). Blockchain network analytics for real-time anomaly detection in cryptocurrency flows. Information Sciences, 590, 305–315. https://doi.org/10.1016/j.ins.2021.11.033

Wang, C., Zhao, H., Li, R., & Yang, J. (2021). Real-time money laundering detection with dynamic graph representation learning. Expert Systems with Applications, 185, 115583. https://doi.org/10.1016/j.eswa.2021.115583

Kim, J., & Choi, J. Y. (2023). High-frequency trading fraud detection through dynamic network centralities. ACM Transactions on Management Information Systems, 14(2), 1–19. https://doi.org/10.1145/3594296

Zhao, P., & Liu, Q. (2021). Cross-border remittance analysis using multi-layer social network metrics. IEEE Transactions on Computational Social Systems, 8(4), 757–767. https://doi.org/10.1109/TCSS.2021.3067635

Verma, R., & Devi, V. (2022). Enhanced SNA-based method for illicit financial flow detection. IEEE Transactions on Engineering Management, 69(4), 1191–1202. https://doi.org/10.1109/TEM.2021.3082284

Moreno, P., Ortega, D., & Sánchez, G. (2023). Visual analytics approach to exploring large-scale financial transaction networks. Information Visualization, 22(2), 124–137. https://doi.org/10.1177/14738716221138902

Jha, S., Alsubaie, N., Alarifi, A., & Mehedi, H. M. (2023). Towards hybrid AI strategies for proactive anti-money laundering solutions. Journal of Financial Innovation and Technology, 2(1), 37–52.

European Commission. (2021). Directive (EU) 2018/1673 on combating money laundering by criminal law (6AMLD). Retrieved May 30, 2025, from https://eur-lex.europa.eu/eli/dir/2018/1673/oj

Blanuša, J., Cravero Baraja, M., Anghel, A., von Niederhäusern, L., Altman, E., Pozidis, H., & Atasu, K. (2024). Graph Feature Preprocessor: Real-time subgraph-based feature extraction for financial crime detection. arXiv Preprint, arXiv:2402.08593. https://arxiv.org/abs/2402.08593

Lee, J., Kim, S., & Shin, K. (2024). SLADE: Detecting dynamic anomalies in edge streams without labels via self-supervised learning. arXiv Preprint, arXiv:2402.11933. https://arxiv.org/abs/2402.11933

Downloads

Published

2025-06-30

How to Cite

Baigabyl, R., Nugumanova, A., & Sodnomova, M. (2025). USING GRAPH CENTRALITY METRICS FOR DETECTION OF SUSPICIOUS TRANSACTIONS. Scientific Journal of Astana IT University, 22, 134–152. https://doi.org/10.37943/22ZSKI6025

Issue

Section

Information Technologies