UOB unveils machine learning solution to combat financial crime

It has tapped on regtech startup Tookitaki for its Anti-Money Laundering Suite.

UOB has tied up with regtech firm Tookitaki Holding Pte. Ltd. to roll out a machine learning solution that would help detect and prevent money laundering activities in the bank’s systems.

Also read: UOB profit up 28% to $788.49m in Q2

Tookitaki’s anti-money laundering suite (AMLS) can be applied to all processes within the AML framework unlike solutions requiring the use of multiple systems to analyse subsets of the same data sets, enabling it to make sharper and swifter detection of high-risk companies and individuals and flag suspicious activities. 

UOB has already applied AMLS to its name screening and transaction monitoring process. In name screening, the bank identifies high-risk individuals and entities based on internal and external watch lists whilst transaction monitoring involves the identification and reporting of suspicious transactions for investigation.

Upon spotting suspicious activity patterns, the AMLS creates a smart rule and adds it to the AML typology library, thus enabling the machine learning models to detect similar patterns for future alerts. Over time, the solution can filter the number of false positives and enable more accurate tracking of suspicious cases.

“The use of RegTech such as Tookitaki’s AMLS enables us to augment our ability to identify actionable alerts and to minimise false positives. These sharpen the accuracy and effectiveness of our AML risk management,” Victor Ngo, head of group compliance, UOB, said in a statement.

Ngo adds that the bank has already tested the AMLS in a six-month pilot and will continue to optimise the machine learning algorithms by adding new transactional data into the database.

UOB will also progressively roll out AMLS to enhance the other two processes in its AML framework, namely customer risk assessment and sanctions screening.

The Singapore lender has been ramping up IT-related investments in recent years with Q2 expenses rising 10% YoY to $1.02b. It also plans to launch a fully digital bank in key ASEAN markets with the goal of scaling its regional customer base by as much as five million over the next five years.