Filtering and Detection of Anti Money Laundering with the Aid of Optimization-Enabled Machine Learning Techniques

Abstract

- Money laundering poses a substantial threat to the global economy and security as it enables the legitimization of unlawfully acquired funds. This manuscript presents a comprehensive exploration of the utilization of optimization-enabled machine learning techniques for the detection and filtration of money laundering activities, exploring a spectrum of facets such as Anti-Money Laundering (AML) policies, data mining methodologies, supervised and unsupervised learning algorithms, link analysis, behavioral modeling, risk scoring, anomaly detection, and geographical applicability. Leveraging a thorough review of literature from Google Scholar, IEEE Xplore, Scopus, and PubMed databases, the study ultimately narrowed its focus to various highly pertinent articles, accentuating the role of deep learning methodologies in achieving alignment with the study's objectives. The study also encompasses a systematic literature review, meticulously analyzing the existing body of knowledge to address critical research inquiries and underscoring the imperative need for enhanced methodologies in AML detection. The research outcomes offer valuable insights and recommendations for fortifying AML detection through advanced machine learning approaches, charting a path toward more efficacious AML strategies in the foreseeable future