Leveraging Machine Learning, Deep Learning and 6G Technologies in Anti-money Laundering Strategies: A Systematic Review of Implementation, Effectiveness and Challenges in the U.S. Financial Industry

Abstract

Money laundering continues to pose major challenges for financial institutions and regulators, with the United Nations Office on Drugs and Crime reporting that 2–5% of global GDP is made up of illicit financial flows worldwide. The US financial sector is navigating the changing technology landscape of anti-money laundering (AML), with increasing emphasis on machine learning (ML)/ deep learning (DL) and the emergence of 6G telecommunications in combating financial crimes. This paper reviews existing implementation approaches, performance measures, and ongoing challenges surrounding Machine Learning, Deep Learning, and 6G Technologies in Anti-Money Laundering in the U.S. by investigating publications such as academic articles, regulations, and industry reports covering 2018 to 2025. The result of the research suggests that while ML/DL methods show enhanced detection rates and efficiency over traditional rule-based systems, questions about regulation, explainability, and data quality remain significant challenges that must be addressed to ensure their responsible and effective deployment. Moreover, the study found that though 6G technology provides useful features for advanced real-time monitoring to prevent money laundering, it introduces unprecedented challenges in regulation, cost, and data privacy. This review provides a holistic framework for banks and policymakers to pragmatically and progressively embed technological solutions into banks’ anti-money laundering processes and address technical, organizational, and regulatory barriers in anti-money laundering in the U.S.