AI Financial Crime Detection Advances as MAS Leads Bank Collaboration

AI financial crime detection is advancing as the Monetary Authority of Singapore works with local banks, GovTech and the police to strengthen scam detection capabilities.

MAS said it is running a proof-of-value exercise using data from five banks to develop machine learning models that can identify higher-risk transactions and suspicious accounts earlier, enabling faster intervention and potentially reducing customer losses.

The project operates within a secure data-sharing environment, with safeguards including cryptographic protection, hashed bank account numbers, restricted access controls and continuous monitoring.

MAS added that all data used in the exercise will be deleted after completion.

The regulator may later expand the AI financial crime detection models to cover broader datasets and additional use cases as financial institutions step up efforts against increasingly sophisticated scams.