Prevention of Money Laundering and Terrorist Financing
PhD Candidate, Senior Consultant,
University of Pécs, Institute for Training and Consulting in Banking
Published in: Public Finance Quarterly 2022/2. (p. 288-303.)
Summary: Based on a country study related to money laundering and terrorist financing, the Financial Action Group downgraded Hungary’s compliance with Recommendation R15 (use of new technologies). At the same time, between 2020 and 2021, the Magyar Nemzeti Bank imposed fines on several commercial banks operating in Hungary for shortcomings on complying with money laundering and terrorist financing regulations. As a gap-filling analysis, the study examines supervised (classification, regression), unsupervised (clustering, anomaly detection), and hybrid machine learning models and algorithms operating based on highly unbalanced dataset of anti-money laundering and terrorist financing prevention of banking risk management. The author emphasizes that there is no one ideal algorithm. The choice between machine learning algorithm is highly determined based on the underlying theoretical logic and additional comparative. Model building requires a hybrid perspective of the give business unit, IT and visionary management.
Keywords: Artificial Intelligence, Machine Learning algorithms, banking risk management, AntiMoney Laundering and Counter Financing Terrorism, supervised/unsupervised methods
JEL codes: C45, C80, G21, G32, O33
Download full text here! (pdf)