Singapore-based OCBC Bank has unveiled plans to use artificial intelligence (AI) and machine learning, as part of its efforts to reduce financial crimes.
The bank intends to deploy these technologies to deal with the increasing scale and complexity of anti-money laundering (AML) monitoring, in addition to increasing the banks operational efficiency and accuracy in the detection of suspicious transactions.
OCBC Bank, along with Fintech company ThetaRay, has conducted a proof of concept that concluded at the starting of this year.
Now, the company plans to start an extended proof of concept and pre-implementation phase, which will involve advanced testing with additional test data. It will help the bank to further verify the efficacy, security and validity of the technology.
The Fintech solution is said to use an algorithm, which is not dependent on an exhaustive set of programmed rules to flag transactions for review.
The algorithm will detect anomalies in transaction behaviour by evaluating broad parameters such as products, customers and risks, instead of looking at each transaction as a standalone.
In the proof of concept stage, the technology was deployed to analyse one years worth of OCBC Banks corporate banking transaction data.
The findings demonstrated that it decreased the number of alerts, which did not require further review by 35%.
The accuracy rate of identifying suspicious transactions are increased by more than four times through the categorisation of flagged transactions by their risk levels.
ThetaRays technology can also detect earlier unknown patterns of money laundering promises, helping the bank to understand financial crime.
OCBC Bank Group legal and regulatory compliance head Loretta Yuen said: Financial crimes are evolving in complexity and sophistication. Banks play a central role in foiling illegal activity such as money laundering and constantly have to be one step ahead of financial criminals.
(c) 2017 Global Data Point. All Rights Reserved. Provided by SyndiGate Media Inc. (Syndigate.info)., source Middle East & North African Newspapers