Anti-Money Laundering is a particularly challenging area of regulation for banks and even more so for large, geographically diverse institutions. Failure to have adequate processes can result in massive regulatory fines – well into the tens of billions of dollars annually.
The advent of machine intelligence techniques can, with minimal disruption to existing systems, transform a bank’s AML process. Using these approaches banks can deliver orders of magnitude greater efficiency in their AML processes while simultaneously decreasing their exposure to regulatory fines.
One key area of efficiencies is the reduction of false positives. While false positive rates can run to 95% or higher for many banks, using Ayasdi, one of the world’s largest and global banks achieved a reduction in false positives of 26% without impacting the number of suspicious activity reports. To read more about this use case see the related resources at the bottom of the page.
In most AML processes, subject matter experts make the determination of the rules or scenarios around what should trigger an investigation. Ayasdi’s technology automatically assembles self-similar groups of customers and customers-of-customers. This allows the bank’s subject matter experts to tune the thresholds within each scenario but from a principled starting point.
A critical, often overlooked step, in AML workflows is the ability to explain what has driven the creation of these groups and the optimization of thresholds within the scenarios. Aysadi provides complete transparency into what is driving the segmentation and the ranking and produces the complete documentation workflow including simple decision trees that can be shared with internal model governance boards and external regulators.