Financial crimes like fraud and money laundering have evolved rapidly in complexity and sophistication. The cost of compliance has also risen sharply with more stringent regulatory controls. Hefty fines, erosion to reputation and trust are prompting financial institutions to turned to data analytics for more effective measures to detect suspicious activities from a wider variety of data sources, structured and unstructured. However, the high false positive rates bring no respite to the workload and continue to strain resources.
Today, artificial intelligence (AI) and machine learning (ML) can be used to complement data analytics. AI/ML can be incorporated into the financial crime compliance (FCC) model reviews to reduce the number of false positives by enabling smarter analytics, so that investigations can focus on genuine money laundering cases.
This one-day workshop looks at how to design an operational framework, incorporating the latest MAS paper on Guidance for Effective AML/CFT Transaction Monitoring Controls.