United Overseas Bank: Machine Learning-powered Alert Triaging for AML Transaction Monitoring and Name Screening

Create a vendor selection project & run comparison reports
Click to express your interest in this report
Indication of coverage against your requirements
A subscription is required to activate this feature. Contact us for more info.
Celent have reviewed this profile and believe it to be accurate.
8 March 2021
Arin Ray

Winner of Celent Model Risk Manager 2021 Award for Data, Analytics, and AI


United Overseas Bank recognized the potential of artificial intelligence (AI) and machine learning (ML)–powered solutions to strengthen its control and streamline AML operations. Its co-development and implementation of Tookitaki’s AML Suite (AMLS) is a leading use case of AI application in AML, especially because the bank has applied it across both transaction monitoring and name screening processes at the same time.

The solution has resulted in impressive outcomes in high accuracy in identifying both true positives and false positives and enhanced efficiency and effectiveness of the bank’s AML program. It strengthens UOB’s financial-crime compliance operations by allowing the bank to draw out faster and more precise information to detect and prevent suspicious money-laundering activities.

Click on the video link below to watch a conversation between Victor Ngo, Head of Group Compliance at UOB, and Arin Ray, Senior Analyst with Celent's Risk practice; Celent Risk research members can download the PDF of a detailed case study.

Subscription required

Access to this content requires a Celent research subscription.

Subscribers should sign in to access this research.

If you are not a subscriber, register now or contact us to find out more about our subscription options.


Please consent to Functional Cookies to see this content, see Manage Cookies

Insight details

Insight Format
Geographic Focus
Asia-Pacific, EMEA, LATAM, North America