A Graph-Based Approach for Detecting Intermediary Accounts and Prioritizing Investigations in Money Laundering
Resumo
A lavagem de dinheiro envolve redes complexas de transações, dificultando a identificação de contas suspeitas. Neste trabalho, propõem-se as métricas Max-Flow Node Importance (MFNI) e sua extensão temporal (MTFI), que avaliam o impacto de cada nó na capacidade de fluxo máximo da rede. Também é utilizado o Mule Score, uma combinação de três métricas baseadas em grafos para identificar potenciais contas intermediárias. O Mule Score incorpora mecanismos de explicabilidade que evidenciam os fatores responsáveis pela classificação dos nós. Estudos de caso em dados reais mostram que contas sinalizadas como suspeitas exercem papel crítico na manutenção dos fluxos financeiros e constituem alvos prioritários para investigação.Referências
Akrida, E. C., Czyzowicz, J., Gasieniec, L., Łukasz Kuszner, and Spirakis, P. G. (2019). Temporal flows in temporal networks. Journal of Computer and System Sciences, 103:46–60.
Capozzi, A., Vilella, S., Moncalvo, D., Fornasiero, M., Ricci, V., Ronchiadin, S., and Ruffo, G. (2025). Flowseries: flow analysis on financial networks. Applied Network Science, 10.
Dumitrescu, B., Băltoiu, A., and Budulan, S. (2022). Anomaly detection in graphs of bank transactions for anti money laundering applications. IEEE Access, 10:47699–47714.
Huang, Z. (2025). Enhancing anti-money laundering by money mules detection on transaction graphs. Proceedings of the 2025 International Conference on Generative Artificial Intelligence for Business.
Huong, H., Nguyen, X.-P., Dang, T. K., and Tran-Truong, P. T. (2024). Money laundering detection using a transaction-based graph learning approach. 2024 18th International Conference on Ubiquitous Information Management and Communication (IMCOM), pages 1–8.
Karim, M. R., Hermsen, F., Chala, S., de Perthuis, P., and Mandal, A. (2024). Scalable semi-supervised graph learning techniques for anti money laundering. IEEE Access, 12:50012–50029.
Li, X., Liu, S., Li, Z., Han, X., Shi, C., Hooi, B., Huang, H., and Cheng, X. (2020). Flowscope: Spotting money laundering based on graphs. pages 4731–4738.
Rajender, G., Lakshmi, A. V., Navitha, P., Jyothi, S. N., Anusha, P., and Pavankumar, P. (2025). Anomaly detection in financial transactions using graph mining. 2025 IEEE International Conference on Advanced Computing Technologies (ICACT), pages 20–24.
Shadrooh, S. and Nørvåg, K. (2024). Smotef: Smurf money laundering detection using temporal order and flow analysis. Applied Intelligence, 54:7461 – 7478.
Tariq, H. and Hassani, M. (2023). Topology-agnostic detection of temporal money laundering flows in billion-scale transactions. pages 402–419.
Vilella, S., Capozzi, A., Fornasiero, M., Moncalvo, D., Ricci, V., Ronchiadin, S., and Ruffo, G. (2025). Weirdnodes: centrality based anomaly detection on temporal networks for the anti-financial crime domain. Applied Network Science, 10.
Capozzi, A., Vilella, S., Moncalvo, D., Fornasiero, M., Ricci, V., Ronchiadin, S., and Ruffo, G. (2025). Flowseries: flow analysis on financial networks. Applied Network Science, 10.
Dumitrescu, B., Băltoiu, A., and Budulan, S. (2022). Anomaly detection in graphs of bank transactions for anti money laundering applications. IEEE Access, 10:47699–47714.
Huang, Z. (2025). Enhancing anti-money laundering by money mules detection on transaction graphs. Proceedings of the 2025 International Conference on Generative Artificial Intelligence for Business.
Huong, H., Nguyen, X.-P., Dang, T. K., and Tran-Truong, P. T. (2024). Money laundering detection using a transaction-based graph learning approach. 2024 18th International Conference on Ubiquitous Information Management and Communication (IMCOM), pages 1–8.
Karim, M. R., Hermsen, F., Chala, S., de Perthuis, P., and Mandal, A. (2024). Scalable semi-supervised graph learning techniques for anti money laundering. IEEE Access, 12:50012–50029.
Li, X., Liu, S., Li, Z., Han, X., Shi, C., Hooi, B., Huang, H., and Cheng, X. (2020). Flowscope: Spotting money laundering based on graphs. pages 4731–4738.
Rajender, G., Lakshmi, A. V., Navitha, P., Jyothi, S. N., Anusha, P., and Pavankumar, P. (2025). Anomaly detection in financial transactions using graph mining. 2025 IEEE International Conference on Advanced Computing Technologies (ICACT), pages 20–24.
Shadrooh, S. and Nørvåg, K. (2024). Smotef: Smurf money laundering detection using temporal order and flow analysis. Applied Intelligence, 54:7461 – 7478.
Tariq, H. and Hassani, M. (2023). Topology-agnostic detection of temporal money laundering flows in billion-scale transactions. pages 402–419.
Vilella, S., Capozzi, A., Fornasiero, M., Moncalvo, D., Ricci, V., Ronchiadin, S., and Ruffo, G. (2025). Weirdnodes: centrality based anomaly detection on temporal networks for the anti-financial crime domain. Applied Network Science, 10.
Publicado
19/10/2026
Como Citar
SILVA, Brenno Araújo Caldeira; SILVA FILHO, Marcio Antonio da; CALLOU, Gustavo Rau de Almeida; PINHEIRO, Rian Gabriel; NASCIMENTO FILHO, Dimas Cassimiro do; VEIGA, Edvaldo dos Santos.
A Graph-Based Approach for Detecting Intermediary Accounts and Prioritizing Investigations in Money Laundering. In: ENCONTRO NACIONAL DE INTELIGÊNCIA ARTIFICIAL E COMPUTACIONAL (ENIAC), 23. , 2026, Cuiabá/MT.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 3334-3345.
ISSN 2763-9061.
DOI: https://doi.org/10.5753/eniac.2026.31340.
