Anti-money laundering (AML) analytics

Anti-Money Laundering (AML) legislation has proved challenging for many financial institutions who are struggling to comply in a cost effective and efficient manner. Many financial institutions have developed transaction monitoring systems which generate high number of alerts on suspected suspicious transactions, alerts which need to be reviewed manually. When an overwhelming amount of these alerts are in fact false positives the result is a transaction monitoring system with poor risk mitigation, an inefficient review process and a high cost of employing personnel to review anti-money laundering (AML) alerts.

Our experience from working with financial institutions to tackle the issue of money laundering shows that many are still in the phase of employing traditional rule-based engines. Such rule-based methods are typically associated with a high number of false positives and inefficient manual labour to investigate these alerts.

BearingPoint’s solution to this issue uses artificial intelligence to develop improved transaction monitoring algorithms with anti-money laundering analytics. 

In one of our projects using anti-money laundering (AML) analytics, up to 18% of customers flagged by our supervised machine learning model were reported to the Financial Intelligence Unit, compared to previous true positive rates of 2-3%. The algorithm has also shown to reduce the number of false positives significantly and provide sufficient risk coverage to replace traditional rule-based methods.