Anti-Money Laundering (AML) using Machine Learning

The advent of more data and less obstacles subsequent to the Anti-Money Laundering Act of 2020 and the National Illicit Finance Strategy enable law, consulting, banks and regulators to jump-start machine learning analytics innovations to fight financial crime.

Machine learning applied to anti-money laundering (AML) enables immediate scalable analytics tools from an ad hoc to an ongoing monitoring and feedback system.  Common Machine Learning advanced analytics tools, albeit the most common, such as feature importance, random forest, deep learning, neural networks, natural language processing and gradient boosting provide great off the shelf tools to test, simulate, scale and integrate into the AML program. 

Considering the tools requires an advanced analytics talent pool combined with subject matter experts on data and AML.  As the regulators and companies invest in an AML program, considering the talent and subject matter expert as key factors of developing a successful program are paramount.