ABSTRACT
Context: Financial crimes exist in all world countries, and one of the most recurrent ones is Money Laundering (MoL). This crime can harm the country’s economy, increase criminality, and compromise social investments. Moreover, it can increase the investment risk factor, raising exchange and interest rates and causing high inflation. In recent years, financial institutions and government agencies have searched for solutions to detect MoL in financial transactions. Problem: Several institutions have employed naive IS for detect MoL. Most systems are based on rules and label a large transactions number as suspicious, which makes the decision process inaccurate and inefficient. Solution: The recent literature presents Graph Neural Networks (GNN) as a promising solution to illegal transaction detection. We applied the Node and Edge Neural Network (NENN) architecture to classification, using the attributes of both bank accounts (vertices) and transactions (edges). IS Theory: In the Intelligent Information Systems context, Machine Learning is a way to improve the decision-making ability of programs in IS. Method: The GCN, Skip-GCN, and NENN architectures were evaluated for the MoL detection problem, comparing two ways of representing transactions as graphs (transactions as vertices or edges). Also, was considered the performance of XGBoost and Softmax classifiers in the solution. Summary of Results: Results showed better performance when transactions represented the nodes. In addition, NENN+XGBoost was superior for higher class imbalance values, with an F1-score of 74,51 ± 4,21% to "illicit" transactions. Contributions and impacts in the IS area: This paper improves the decision-making ability of Anti-Money Laundering systems, helping the organization and efficiency of public and private institutions, and contributing to the fight against corruption. This theme is aligned with the GrandDSI-BR2016-2026.
Supplemental Material
Available for Download
- Ismail Alarab and Simant Prakoonwit. 2022. Graph-Based LSTM for Anti-money Laundering: Experimenting Temporal Graph Convolutional Network with Bitcoin Data. Neural Processing Letters 54 (06 2022), 1–19. https://doi.org/10.1007/s11063-022-10904-8Google ScholarDigital Library
- Ismail Alarab, Simant Prakoonwit, and Mohamed Ikbal Nacer. 2020. Competence of Graph Convolutional Networks for Anti-Money Laundering in Bitcoin Blockchain. In Proceedings of the 2020 5th International Conference on Machine Learning Technologies (Beijing, China) (ICMLT 2020). Association for Computing Machinery, New York, NY, USA, 23–27. https://doi.org/10.1145/3409073.3409080Google ScholarDigital Library
- Renata Araujo. 2017. Information Systems and the Open World Challenges. Brazilian Computer Society (SBC)., 42 – 51. https://doi.org/10.5753/sbc.2884.0.4Google ScholarCross Ref
- Henrique Assumpção, Fabrício Souza, Leandro Campos, Vinícius Pires, Paulo Almeida, and Fabrício Murai. 2022. Delator: Detecção Automática de Indícios de Lavagem de Dinheiro por Redes Neurais em Grafos de Transações. In Anais do XI Brazilian Workshop on Social Network Analysis and Mining (Niterói). SBC, Porto Alegre, RS, Brasil, 13–24. https://doi.org/10.5753/brasnam.2022.223137Google ScholarCross Ref
- Zhiyuan Chen, D. Van-Khoa Le, Ee Teoh, Amril Nazir, Ettikan Karuppiah, and Kim Lam. 2018. Machine learning techniques for anti-money laundering (AML) solutions in suspicious transaction detection: a review. Knowledge and Information Systems 57 (11 2018), 245–285. https://doi.org/10.1007/s10115-017-1144-zGoogle ScholarDigital Library
- Luis Fernando Carvalho Dias and Fernando Silva Parreiras. 2019. Comparing Data Mining Techniques for Anti-Money Laundering. In Proceedings of the XV Brazilian Symposium on Information Systems (Aracaju, Brazil) (SBSI’19). Association for Computing Machinery, New York, NY, USA, Article 73, 8 pages. https://doi.org/10.1145/3330204.3330283Google ScholarDigital Library
- Rafał Dreżewski, Jan Sepielak, and Wojciech Filipkowski. 2012. System supporting money laundering detection. Digital Investigation 9, 1 (2012), 8–21. https://doi.org/10.1016/j.diin.2012.04.003Google ScholarCross Ref
- Rafał Dreżewski, Jan Sepielak, and Wojciech Filipkowski. 2015. The application of social network analysis algorithms in a system supporting money laundering detection. Information Sciences 295 (2015), 18–32. https://doi.org/10.1016/j.ins.2014.10.015Google ScholarDigital Library
- Steven Farrugia, Joshua Ellul, and George Azzopardi. 2020. Detection of illicit accounts over the Ethereum blockchain. Expert Systems with Applications 150 (2020), 113318. https://doi.org/10.1016/j.eswa.2020.113318Google ScholarCross Ref
- FATF. 2003. FATF 40 Recommendations. https://www.fatf-gafi.org/media/fatf/documents/FATF%20Standards%20-%2040%20Recommendations%20rc.pdfGoogle Scholar
- Andrea Fronzetti Colladon and Elisa Remondi. 2017. Using social network analysis to prevent money laundering. Expert Systems with Applications 67 (2017), 49–58. https://doi.org/10.1016/j.eswa.2016.09.029Google ScholarDigital Library
- Petter Gottschalk. 2010. Categories of financial crime. Journal of Financial Crime 17 (10 2010), 441–458. https://doi.org/10.1108/13590791011082797Google ScholarCross Ref
- Léo Grinsztajn, Edouard Oyallon, and Gaël Varoquaux. 2022. Why do tree-based models still outperform deep learning on tabular data?https://doi.org/10.48550/ARXIV.2207.08815Google ScholarCross Ref
- Willian L. Hamilton. 2020. Graph Representation Learning. Number 46 in Synthesis Lectures on Artifical Intelligence and Machine Learning. Morgan & Claypool, San Rafael – CA, USA. https://doi.org/10.2200/S01045ED1V01Y202009AIM046Google ScholarCross Ref
- Jingguang Han, Yuyun Huang, Sha Liu, and Kieran Towey. 2020. Artificial intelligence for anti-money laundering: a review and extension. Digital Finance 2020 2:3 2, 3 (jun 2020), 211–239. https://doi.org/10.1007/S42521-020-00023-1Google ScholarCross Ref
- Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In International Conference on Learning Representations (ICLR). OpenReview.net, Toulon, France, 14 pages.Google Scholar
- Kroll. 2019. Global Fraud and Risk Report 2019/20 (11 ed.). Technical Report. Kroll, Boston - MA, US. https://www.kroll.com/en/insights/publications/global-fraud-and-risk-report-2019Google Scholar
- Asma S. Larik and Sajjad Haider. 2011. Clustering based anomalous transaction reporting. Procedia Computer Science 3 (2011), 606–610. https://doi.org/10.1016/j.procs.2010.12.101 World Conference on Information Technology.Google ScholarCross Ref
- Nhien-An Le-Khac, Sammer Markos, and Tahar Kechadi. 2009. Towards a New Data Mining-Based Approach for Anti-Money Laundering in an International Investment Bank. In Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, Vol. 31. Springer, Albany, Ny, USA, 77–84. https://doi.org/10.1007/978-3-642-11534-9_8Google ScholarCross Ref
- Edgar Alonso Lopez-Rojaz and Stefan Axelsson. 2012. Money Laundering Detection using Synthetic Data. In Linköping Electronic Conference Proceedings, No. 71. Linköping University Electronic Press, Linköping, Sweden, 33 – 40.Google Scholar
- Vanessa Nunes, Claudia Cappelli, and Célia Ralha. 2017. Transparency in Information Systems. Brazilian Computer Society (SBC)., 73 – 89. https://doi.org/10.5753/sbc.2884.0.7Google ScholarCross Ref
- Ronald Pereira and Fabrício Murai. 2021. Quão efetivas são Redes Neurais baseadas em Grafos na Detecção de Fraude para Dados em Rede?. In Anais do X Brazilian Workshop on Social Network Analysis and Mining. SBC, Porto Alegre, RS, Brasil, 205–210. https://doi.org/10.5753/brasnam.2021.16141Google ScholarCross Ref
- Toyotaro Suzumura and Hiroki Kanezashi. 2021. Anti-Money Laundering Datasets: InPlusLab Anti-Money Laundering DataDatasets. http://github.com/IBM/AMLSimGoogle Scholar
- Mark Weber, Jie Chen, Toyotaro Suzumura, Aldo Pareja, Tengfei Ma, Hiroki Kanezashi, Tim Kaler, Charles E. Leiserson, and Tao B. Schardl. 2018. Scalable Graph Learning for Anti-Money Laundering: A First Look. CoRR abs/1812.00076 (2018), 7 pages.Google Scholar
- Mark Weber, Giacomo Domeniconi, Jie Chen, Daniel Karl I. Weidele, Claudio Bellei, Tom Robinson, and Charles E. Leiserson. 2019. Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics., 7 pages. https://drive.google.com/drive/folders/1r_iJYFJru-jdDdgpB-KZ1N0Zathy2LD2Google Scholar
- Yulei Yang and Dongsheng Li. 2020. NENN: Incorporate Node and Edge Features in Graph Neural Networks. In Proceedings of The 12th Asian Conference on Machine Learning(Proceedings of Machine Learning Research, Vol. 129), Sinno Jialin Pan and Masashi Sugiyama (Eds.). PMLR, Bangkok, Thailand, 593–608. https://proceedings.mlr.press/v129/yang20a.htmlGoogle Scholar
Index Terms
- Graph Neural Networks Applied to Money Laundering Detection in Intelligent Information Systems
Recommendations
Laundering Sexual Deviance: Targeting Online Pornography through Anti-money Laundering
EISIC '12: Proceedings of the 2012 European Intelligence and Security Informatics ConferenceThis paper concentrates on cyber-pornography/obscenity, which encompasses online publications or distribution of sexually explicit material in breach of the English obscenity and indecency laws. After examining the major deficiencies of the attempts to ...
Anti-money laundering supervision by intelligent algorithm
Highlights- A novel two-tier method that improves virtual AML risk identification is unveiled.
- Two-tier method with LSTM+GCN to address unsupervised AML learning drawbacks.
- Model demonstrates impressive adaptability and precision in AML ...
AbstractAs global anti-money laundering (AML) protocols and technologies strengthen, traditional laundering methods increasingly face stringent scrutiny. Concurrently, the allure of virtual currencies for laundering illegal funds is magnified, owing to ...
A Data Mining-Based Solution for Detecting Suspicious Money Laundering Cases in an Investment Bank
DBKDA '10: Proceedings of the 2010 Second International Conference on Advances in Databases, Knowledge, and Data ApplicationsToday, money laundering poses a serious threat not only to financial institutions but also to the nation. This criminal activity is becoming more and more sophisticated and seems to have moved from the cliché, of drug trafficking to financing terrorism ...
Comments