With the countless advances in tech lately, money laundering has become more advanced than ever. But technology goes the other way too, as AI is helping in the anti-money laundering fight. Recently, 3i Infotech’s AI-driven AMLOCK Analytics streamlined AML detection and enforcement.
While this system helps identify money laundering, likely its biggest impact is identifying false positives. These are trends that may seem like money laundering and may be flagged as such but ultimately end up being routine.
AMLOCK Analytics uses various statistical methods and machine learning algorithms to analyze and predict money laundering based on institutional history. It also uses risk profiling to drive decision making, plus it accounts for customer and seasonal trends. If it finds anomalies or deviations from these trends, it flags the account for further investigation.
In the end, this gives the user the ability to work efficiently by focusing on events with high risk or are outliers from the norm.
In describing this system, Ravikanth Sama, global head of AML Practice, said, “AMLOCK Analytics blends both the traditional rule-based system and the power of Analytics to bring better efficiency & risk focus. It can be hosted both on-premise and on cloud infrastructure. The solution provides a probability score indicating the chances of closing an alert based on the past actions taken by the users on similar alerts. AMLOCK Analytics improves the conversion rate of Suspicious Transaction Report (STR) or Suspicious Activity Report (SAR), as it dynamically correlates between the alerts in which suspicious transaction reports have been generated and those that have been tagged as false positives by the investigators.”
Head of global delivery & engineering at 3i Infotech, Balakrishna Peddiraju, added to that, “Our AMLOCK Analytics solution helps detect unknown suspicious behavioral AML patterns, thereby improving operational efficiency. This solution is seamlessly integrated with AMLOCK and embedded with various machine learning and deep learning algorithms. It facilitates intense surveillance and reduces investigation time. It enables better alert triage and smarter investigations by providing astute guidance based on historical patterns for factors such as risk assessment.”
