Improved client risk classification increase anti-money laundering efficiency.

What is it about?

Client risk modeling with machine learning predicts false-positive flagged transactions by sorting clients into high- and low-risk groups with different monitoring thresholds. Incorporating credit risk scores and financial performance changes improves the model's efficiency in detecting suspicious transactions while reducing false positives and freeing up resources for other AML activities.

Featured Image

Photo by Alexander Grey on Unsplash

Photo by Alexander Grey on Unsplash

Why is it important?

Banks need to focus on preemptive efforts to reduce risk in clients with a higher probability of subsequent suspicious transactions—the need for more dynamic and improved client-risk classification models increases as increased transaction speed makes it more challenging to stop transactions.