United Overseas Bank is to apply machine learning technology from local RegTech startup and accelerator graduate Tookitaki across its entire anti-money laundering framework following a successful six-month pilot trial.
While industry norms generally require banks to use multiple systems to analyse subsets of the same data across different elements of their AML screening activities, Tookitaki's Anti-Money Laundering Suite (AMLS), can be applied as a single rounded solution.
For the pilot, UOB applied the system to name screening and transaction monitoring, experiencing a 60% and 50% reduction in false positives for individual names and corporate names respectively. Transaction monitoring saw a five per cent increase in true positives and 40% drop in false positives.
When it spots a pattern of suspicious activity, the AMLS also 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.
Victor Ngo, head of group compliance, UOB, says, “The area of AML requires constant vigilance and continual enhancement to ensure that we stay on top of preventive, detective and enforcement measures. The six-month pilot has shown how AMLS can enhance our processes and over the next six months, we will continue to optimise AMLS’ machine learning algorithms by adding new transactional data into the database. We will then implement the solution across the entire AML framework over time.”