You are here
OCBC sees AI payoff in compliance
OCBC Bank is raising the bar on using artificial intelligence (AI) and machine learning to combat financial crime, as it works with an Israeli fintech to boost the bank's operational efficiency and accuracy in the detection of suspicious transactions.
It said on Tuesday that it would extend its proof-of-concept testing with fintech firm ThetaRay, after early tests showed that the fintech's technology was able to reduce the number of alerts that did not require further review, by 35 per cent.
And by categorising more effectively the flagged transactions by their risk levels, the accuracy rate of identifying suspicious transactions increased by more than four times, the bank said. The test was based on one year's worth of OCBC corporate banking transaction data, with the data anonymised.
This in effect has helped the bank to prioritise the flagged transactions according to risk. OCBC's head of group legal and regulatory compliance Loretta Yuen said that the current transaction monitoring system is a rule-based one, which makes the scanning of risks very fixed and handled on a "first in, first out" basis.
By embedding the fintech's technology into the existing system, some 4,200 alerts have been grouped into 48 unique risk clusters for the compliance team to sieve through.
The bank targets to fully implement the technology in the second quarter of next year. It said it is the first bank in Singapore to tap AI and machine learning to combat financial crime.
OCBC decided to try out the technology with ThetaRay after OCBC's fintech unit The Open Vault looked through as many as 800 fintechs that all propose similar anti-money laundering (AML) solutions, said OCBC's head of e-business and business transformation Pranav Seth, who also runs The Open Vault.
OCBC found the algorithms employed by Israel's ThetaRay to be effective in weeding out unnecessary risk alerts, and in finding new risks by discovering new transaction patterns, or the "unknown unknowns", as Ms Yuen put it.
The move by OCBC comes as financial crimes have been growing in scale and complexity, Ms Yuen pointed out. She cited a PwC report that estimated global money laundering transactions to be equivalent to 2-5 per cent of global GDP, or roughly US$1-2 trillion annually.
The PwC report itself also cited numbers from data firm WealthInsight that showed global spending on AML compliance is set to grow to more than US$8 billion by 2017, reflecting a compounded annual growth rate of almost 9 per cent.
Between 2010 and 2017, OCBC's AML monitoring team has jumped in size, from a team of 10 to one with 66 staff, said Ms Yuen. With the fintech partnership, the monitoring team can now focus on more value-added work. "I'd be growing my team for the right reasons," she added.
OCBC separately said the bank's chatbot application has closed more than S$70 million in home loans since the start of the year. Named "Emma", the home and renovation loan chatbot is also powered by AI.
It took three months for "Emma" to be fully trained to address all possible questions asked by consumers about home loans and renovation loans, with one of the top three questions being how much a consumer can borrow. The chatbot uses its built-in total debt servicing ratio calculator to address the query.
"Emma" is trained to identify and associate with all terminology used in the process of applying for or refinancing a home loan. As new or revised regulations come up, "Emma" can be updated to respond to new questions, the bank said.
"Emma" was jointly developed by OCBC's home loans team and CogniCor, one of the startups from The Open Vault.
For more information on the upcoming Singapore FinTech Festival 2017, visit www.fintechfestival.sg.