Anomalous Transaction Detection in Bank Credit Card Data Using Machine Learning

Illegal money changers pose a number of risks to the financial system, including but not limited to money laundering, fraud, and other under-the-carpet dealings intended to frustrate regulatory efforts for financial integrity. The efficiency and accuracy of anti-money laundering (AML) measures using machine learning (ML) models in the detection of suspicious patterns in bank card transactions are investigated in this paper. The key focus will be to develop an efficient machine learning framework that should be proficient in underlining main transactions dealing with illegal money changers and other similar fraudulent activities. The features indicative of illicit behaviour are determined by a comprehensive approach with the pre-processing of largescale datasets of transactions. Compared are performances for various ML algorithms, including supervised and unsupervised techniques, using Random Forest, Support Vector Machines, and neural networks for effective anomaly detection. Performance metrics included precision recall, F1-score, and area under the Receiver Operating Characteristic (ROC) curve, that will dictate the capability of models in discerning legitimate from suspicious transactions. Besides, the present work further investigates the aspect of interpretability of ML models, focusing on why transparency of the AML process has to be attained by data mining methods in order to meet regulatory standards and support human analysts' decisions.