MAS partners banking industry to tap AI, machine learning to combat financial crime

The Monetary Authority of Singapore (MAS) on Monday (May 4) said it will harness artificial intelligence and machine learning techniques to combat financial crime.

To enhance scam-detection capabilities, the central bank will work with partners in the banking industry, the Government Technology Agency of Singapore (GovTech), as well as the Singapore Police Force.

MAS is conducting a proof-of-value (POV) exercise to explore the use of AI and machine learning in pre-emptive scam detection, as part of broader efforts to apply these techniques to industry-wide use cases.

The POV exercise will lay the groundwork for deeper industry collaboration, as well as enhance and complement financial institutions’ existing efforts to prevent and counter financial crime, said MAS.

It added that the exercise will use data from five banks to build more robust and accurate AI and machine learning models that can identify higher-risk transactions and accounts.

Such “prompt identification could enable timely assessment, intervention and reduction of customer losses to scams”, the authority noted.

Specifically, historical transaction data with bank account numbers from participating banks will be used to train and evaluate AI and machine learning models, to assess their potential for improving scam detection.

To support the POV exercise, MAS has provided industry partners with a “secure data sharing environment governed by policies and protocols to safeguard customer information”.

It has also set up a framework with industry participants to ensure that the data shared is protected and used responsibly. Data used in the POV exercise will remain confidential and protected with cryptographic techniques, the central bank added.

For example, bank account numbers will undergo hashing, an algorithmic process that substitutes input data with a unique set of generated values. This ensures that only the contributing bank can identify the actual account numbers.

Further, only authorised personnel will be able to access the data within a controlled setting, which will be monitored throughout the POV exercise, said MAS.

All data used will be deleted at the end of the exercise.

After assessing its effectiveness, MAS said it may expand the scope and sophistication of the AI and machine learning models used by incorporating broader data sets and a wider range of use cases.

‘A step in the right direction’

Industry observers The Business Times spoke to welcomed the move.

Thangaraja Nadaraja, PwC Singapore partner, said that MAS’ initiative is “significant”, as aggregating data from five banks enables AI and machine learning models to detect patterns “that would be invisible to any one institution acting alone”.

Conversely, models developed by individual institutions may suffer from “blind spots” as each bank has visibility only over a smaller pool of data from a part of the ecosystem, said Nadaraja, who specialises in risk, regulatory and compliance for financial services.

Similarly, Radish Singh, financial services risk consulting leader at EY Asean, called the initiative by MAS a “step in the right direction”.

While deploying AI and machine learning capabilities to fight scams is not a new idea – banks already have such practices in place – Singh noted that MAS’ initiative marks a “concerted effort” to face the issue as an industry.

Pooling together data from multiple banks through a collaboration gives AI and machine learning models a larger data set to understand scam patterns and linkages, she said.

Bryan Keasberry, market development director at finance software firm Fenergo, agreed that working with the banking industry, GovTech and the police enables “a more coordinated and proactive approach to detecting suspicious activity before harm is done”.

“Financial crime is no longer something any one bank or a participant can tackle on its own. Scammers and money launderers move across institutions, accounts, payment channels and borders, often faster than traditional monitoring systems can respond,” he said.

Beyond Singapore, partnerships between the public and private sectors to combat scams have also been set up in other jurisdictions, said EY Asean’s Singh.

Fenergo’s Keasberry noted that one example of a similar initiative is the Fintel Alliance launched by Australia’s financial crime watchdog, the Australian Transaction Reports and Analysis Centre.

The Fintel Alliance brings together major banks, regulators, law enforcement and other partners who work together, develop shared intelligence and detect and prevent serious crime.

Keasberry believes that the Fintel Alliance shows that pooling data and applying advanced analytics can reveal criminal patterns “that individual institutions may not see on their own”.

“It is a strong model that Singapore can use as a reference and demonstrates that fighting financial crime increasingly requires an ecosystem response,” he said.

Source: The Business Times © SPH Media Limited. Permission required for reproduction.

AVs on Singapore roads: Public views sought to shape new laws in areas like accident payouts Ng Chee Meng to ask Parliament to affirm no ‘jobless growth’ amid AI; MPs query bullying review