Combating Money Laundering using Artificial Intelligence

Abstract

This research provides a comprehensive outline of money laundering, its cycle, and the challenges of detecting it, in Nigeria and globally. It argues that traditional, rule-based models for identifying financial crimes are inefficient as a result of their high false-positive rates and static nature. The research proposes a solution leveraging modern machine learning and deep learning, specifically an unsupervised approach using a clustering model. This methodology aims to identify suspicious transactions during the “placement” stage of money laundering by detecting anomalies and evolving patterns. Developing and assessing a generative deep learning model for fraud detection, assessing the likelihood of financial crimes, and contrasting the suggested methodology with conventional methods are the goals of this research. The paper’s objectives are to create and evaluate a generative deep learning model for fraud detection, analyse the risks of financial crimes, and compare the proposed method against traditional approaches

Keywords

• Clustering
• Deep Learning
• Machine Learning
• Money Laundering
• Terrorism Financing
• Artificial Intelligence

Supporting Institution

None

Project Number

N/A

Ethical Statement

This research study did not require ethical approval.

Thanks

We want to extend our sincere appreciation to all co-authors who contributed to the successful completion of this research.

Yapay Zeka Kullanarak Kara Para Aklamayla Mücadele

Abstract

Bu araştırma, kara para aklamanın, döngüsünün ve Nijerya'da ve küresel olarak tespit edilmesindeki zorlukların kapsamlı bir taslağını sunmaktadır. Finansal suçları tespit etmek için kullanılan geleneksel, kural tabanlı modellerin, yüksek yanlış pozitif oranları ve statik yapıları nedeniyle etkisiz olduğunu savunmaktadır. Araştırma, özellikle kümeleme modeli kullanan gözetimsiz bir yaklaşım olmak üzere, modern makine öğrenimi ve derin öğrenmeden yararlanan bir çözüm önermektedir. Bu metodoloji, anormallikleri ve gelişen kalıpları tespit ederek kara para aklamanın "yerleştirme" aşamasında şüpheli işlemleri tespit etmeyi amaçlamaktadır. Dolandırıcılık tespiti için üretken bir derin öğrenme modeli geliştirmek ve değerlendirmek, finansal suçların olasılığını değerlendirmek ve önerilen metodolojiyi geleneksel yöntemlerle karşılaştırmak bu araştırmanın hedefleridir. Makalenin hedefleri, dolandırıcılık tespiti için üretken bir derin öğrenme modeli oluşturmak ve değerlendirmek, finansal suçların risklerini analiz etmek ve önerilen yöntemi geleneksel yaklaşımlarla karşılaştırmaktır.

Keywords

• Kümeleme
• Derin Öğrenme
• Makine Öğrenimi
• Kara Para Aklama
• Terörizmin Finansmanı
• Yapay Zeka

Project Number

N/A

References

1. Central Bank of Nigeria. (2013). Anti-Money Laundering and Combating the Financing of Terrorism in Banks and Other Financial Institutions in Nigeria Regulations. Lagos: Federal Republic of Nigeria Official Gazette. https://www.cbn.gov.ng/out/2014/fprd/aml%20act%202013.pdf
2. Lessambo, F. I. (2023). Anti-Money Laundering, Counter Financing Terrorism, and Cybersecurity in the banking industry: A Comparative Study within the G-20. Edited by Philip Molyneux, Springer Nature Switzerland AG. https://www.scribd.com/document/640072311
3. Gerlings, J. & Constantiou, I. (2023). Machine Learning in Transaction Monitoring: The Prospect of xAI. In Proceedings of the 56th Hawaii International Conference on System Sciences, Copenhagen. https://doi.org/10.48550/arXiv.2210.07648
4. Sjögren, S. (2023). Anomaly detection with machine learning methods at Forsmark. https://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-503356
5. Jensen, R. I., Ferwerda, J., Jørgensen, K. S., Jensen, E. R., Borg, M., Krogh, M. P., Jensen, J. B., & Iosifidis, A. (2023). A Synthetic Data Set to Benchmark Anti-money Laundering Methods. Scientific Data, 10(1), 1-10. https://doi.org/10.1038/s41597-023-02569-2
6. Nigerian Financial Intelligence Unit (NFIU). (2019). Annual Report. https://www.nfiu.gov.ng/AnnualReport
7. EFCC, 2022 Narrative of Conviction. (2023). https://www.efcc.gov.ng/efcc/images/pdfs/3785_Convictions_recorded_in_2022.pdf
8. EFCC, 2021 Conviction List. (2022). https://www.efcc.gov.ng/efcc/images/2220_Convictions_recorded_in_2021.pdf

9. EFCC, 2020 Convictions. (2021). https://www.efcc.gov.ng/efcc/images/2020_Convictions__Final_Compilations.pdf
10. Nigeria Sanctions Committee. (2024). Designation of Individuals and Entity by The Nigeria Sanctions Committee. https://nigsac.gov.ng/downloads/Designations%20and%20Narrative%20Summary%20for%2018th%20March%202024.pdf
11. Brownlee, J. (2020). D⁠a⁠t⁠a⁠ ⁠P⁠r⁠e⁠p⁠a⁠r⁠a⁠t⁠i⁠on⁠ ⁠f⁠o⁠r⁠ ⁠⁠M⁠a⁠c⁠h⁠i⁠n⁠e Learning: Data Cleaning, Feature Selection, and Data Transforms in Python (Version 1.1). Machine Learning Mastery. http://103.203.175.90:81/fdScript/RootOfEBooks/E%20Book%20collection%20-%202024%20-%20B/CSE%20%20IT%20AIDS%20ML/Data%20Preparation%20for%20Machine%20Learning.pdf
12. Emam, K. E., Mosquera, L., & Hoptroff, R. (2020). Practical Synthetic Data Generation: Balancing Privacy and the Broad Availability of Data. O’Reilly Media, Inc.. https://www.oreilly.com/library/view/practical-synthetic-data/9781492072737/
13. Gursakal, N., Celik, S., & Birisci, E. (2022). Synthetic Data for Deep Learning: Generate Synthetic Data for Decision Making and Applications with Python and R. Apress. http://dx.doi.org/10.1007/978-1-4842-8587-9
14. Federal Financial Institutions Examination Council (FFIEC). (2021). Politically Exposed Persons. https://www.ffiec.gov/press/PDF/Politically-Exposed-Persons.pdf
15. Verdhan, V. (2023). Mastering Unlabeled Data (Version 6 ed.). Manning Publications Co.. https://dokumen.pub/mastering-unlabeled-data-meap-v06.html
16. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning: MIT Press. http://dx.doi.org/10.1007/s10710-017-9314-z
17. Adari, S. K. & Alla, S. (2024). Beginning Anomaly Detection Using Python-Based Deep Learning: Implement Anomaly Detection Applications with Keras and PyTorch (Second Edition). Apress. https://doi.org/10.1007/979-8-8688-0008-5
18. Saporta, G. & Maraney, S. (2022). Practical Fraud Prevention: Fraud and AML Analytics for Fintech and eCommerce, using SQL and Python. O’Reilly Media, Inc.. https://www.oreilly.com/library/view/practical-fraud-prevention/9781492093312/
19. Xing, E. P. 10701 Machine Learning: Clustering. Lecture slides, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA. https://www.cs.cmu.edu/~epxing/Class/10701/slides/clustering.pdf
20. Nigerian Financial Intelligence Unit (NFIU). (2024). Advisory & Guidance. https://www.nfiu.gov.ng/AdvisoryAndGuidance
21. Jullum, M., Loland, A., Huseby, R. B., Anonsen, G., & Lorentzen, J. (2020). Detecting money laundering transactions with machine learning. Journal of Money Laundering Control, 23(1), 173-186. http://dx.doi.org/10.1108/JMLC-07-2019-0055
22. Special Control Unit Against Money Laundering (SCUML). (2024). Guidelines and Circulars. https://scuml.org/?page_id=109
23. International Finance Corporation (IFC). (2019). Anti-Money Laundering (AML) & Countering Financing of Terrorism (CFT): Risk Management in Emerging Market Banks - Good Practice Note. Washington, D.C.: (IFC). https://www.ifc.org/content/dam/ifc/doc/mgrt/45464-ifc-aml-report.pdf