Designing a Money Laundering Detection Model Based on Financial Network Analysis, Machine Learning, and Abnormal Transactional Patterns
Keywords:
Money laundering, financial network analysis, machine learning, abnormal transactions, anti-money laundering, anomaly detection.Abstract
This study aimed to design an anti-money laundering detection model based on financial network analysis, machine learning, and abnormal transactional patterns. This qualitative exploratory study was conducted among anti-money laundering experts, compliance managers, banking risk specialists, internal auditors, and financial data scientists in Tehran. Eighteen participants were selected using purposive and snowball sampling. Data were collected only through semi-structured interviews. Interviews continued until theoretical saturation was achieved; saturation emerged at the sixteenth interview, and two additional interviews were conducted to confirm data adequacy. All interviews were recorded with permission, transcribed verbatim, anonymized, and analyzed through thematic analysis using NVivo software. Open coding, axial grouping, constant comparison, analytical memoing, peer review, and member checking were used to enhance credibility, dependability, and confirmability. The analysis identified five main categories: “data infrastructure and integration of information sources,” “financial network analysis and detection of hidden relationships,” “identification of abnormal transactional patterns,” “machine learning, risk scoring, and false-positive reduction,” and “model governance, explainability, and ethical-regulatory requirements.” Participants argued that traditional threshold-based monitoring systems are insufficient for identifying complex laundering schemes. They emphasized the necessity of combining transaction data, know-your-customer information, beneficial ownership links, temporal account behavior, graph-based indicators, and investigator feedback to generate dynamic and explainable risk scores. The proposed model suggests that integrating network analytics, machine learning, and behavioral transaction indicators can improve the detection of suspicious money laundering patterns, reduce inefficient alerts, and support risk-based prioritization in compliance operations. However, the effective implementation of such a model depends on data quality, algorithmic explainability, privacy protection, continuous human oversight, model validation, and regulatory alignment.
Downloads
References
Aggarwal, C. C. (2017). Outlier analysis (2nd ed.). Springer.
Akoglu, L., Tong, H., & Koutra, D. (2015). Graph based anomaly detection and description: A survey. Data Mining and Knowledge Discovery, 29, 626–688. doi:10.1007/s10618-014-0365-y
Bonato, A., Chavez Palan, J. S., & Szava, A. (2024). Enhancing anti-money laundering efforts with network-based algorithms. arXiv. doi:10.48550/arXiv.2409.00823
Braun, V., & Clarke, V. (2006). Using thematic analysis in psychology. Qualitative Research in Psychology, 3(2), 77–101. doi:10.1191/1478088706qp063oa
Chandola, V., Banerjee, A., & Kumar, V. (2009). Anomaly detection: A survey. ACM Computing Surveys, 41(3), 1–58. doi:10.1145/1541880.1541882
Creswell, J. W., & Poth, C. N. (2018). Qualitative inquiry and research design: Choosing among five approaches (4th ed.). SAGE.
Elliott, A., Cucuringu, M., Luaces, M. M., Reidy, P., & Reinert, G. (2019). Anomaly detection in networks with application to financial transaction networks. arXiv. doi:10.48550/arXiv.1901.00402
Financial Action Task Force. (2025). International standards on combating money laundering and the financing of terrorism & proliferation: The FATF recommendations. FATF.
Fronzetti Colladon, A., & Remondi, E. (2017). Using social network analysis to prevent money laundering. Expert Systems with Applications, 67, 49–58. doi:10.1016/j.eswa.2016.09.029
Hamilton, W. L., Ying, R., & Leskovec, J. (2017). Inductive representation learning on large graphs. Advances in Neural Information Processing Systems, 30, 1024–1034.
Jensen, R. I. T., & Iosifidis, A. (2022). Fighting money laundering with statistics and machine learning. IEEE Access, 10, 8889–8903. doi:10.1109/ACCESS.2022.3143329
Karim, M. R., Hermsen, F., Chala, S. A., de Perthuis, P., & Mandal, A. (2024). Scalable semi-supervised graph learning techniques for anti money laundering. IEEE Access, 12, 50012–50029. doi:10.1109/ACCESS.2024.3383784
Kipf, T. N., & Welling, M. (2017). Semi-supervised classification with graph convolutional networks. International Conference on Learning Representations.
Lincoln, Y. S., & Guba, E. G. (1985). Naturalistic inquiry. SAGE.
Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30, 4765–4774.
Mousavian, S., & Miah, S. J. (2025). Review of artificial intelligence-based applications for money laundering detection. Intelligent Systems with Applications, 27, 200572. doi:10.1016/j.iswa.2025.200572
Naser Eddin, A., Bono, J., Aparício, D., Polido, D., Ascensão, J. T., Bizarro, P., & Ribeiro, P. (2021). Anti-money laundering alert optimization using machine learning with graphs. arXiv. doi:10.48550/arXiv.2112.07508
Ngai, E. W. T., Hu, Y., Wong, Y. H., Chen, Y., & Sun, X. (2011). The application of data mining techniques in financial fraud detection: A classification framework and an academic review of literature. Decision Support Systems, 50(3), 559–569. doi:10.1016/j.dss.2010.08.006
Oztas, B., Cetinkaya, D., Adedoyin, F., Budka, M., Aksu, G., & Dogan, H. (2024). Transaction monitoring in anti-money laundering: A qualitative analysis and points of view from industry. Future Generation Computer Systems, 159, 161–171. doi:10.1016/j.future.2024.05.027
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). “Why should I trust you?” Explaining the predictions of any classifier. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 1135–1144. doi:10.1145/2939672.2939778
Weber, M., Domeniconi, G., Chen, J., Weidele, D. K. I., Bellei, C., Robinson, T., & Leiserson, C. E. (2019). Anti-money laundering in Bitcoin: Experimenting with graph convolutional networks for financial forensics. arXiv. doi:10.48550/arXiv.1908.02591
