Anti-money laundering (AML) programs have traditionally relied on rules-based systems, but these approaches often generate high volumes of false positives and require ongoing manual tuning. This session explores how Ally Bank is evolving its monitoring strategy by layering interpretable machine learning models on top of existing rules engines—enhancing detection while maintaining regulatory compliance. Using techniques like similarity modeling, the team can identify emerging patterns and prioritize suspicious activity more effectively without replacing core controls. The result is a balanced, phased approach to modernization that improves efficiency, expands coverage, and builds stakeholder confidence in advanced analytics.
Presenters: Aimee Marva and Alex Gulley, Ally Bank
Watch the recording
