The Monetary Authority of Singapore is conducting a proof of value with banking industry partners, the Government Technology Agency of Singapore and the Singapore Police Force to test artificial intelligence and machine learning for pre-emptive scam detection. The exercise combines data from five banks to build more robust models that can better identify higher-risk transactions and accounts, supporting earlier assessment and intervention to reduce customer losses from scams. To support the exercise, MAS has set up a secure data-sharing environment and framework with policies and protocols for customer data protection. Data used in the proof of value will remain confidential and be protected with cryptographic techniques, bank account numbers will be hashed so only the contributing bank can identify the underlying accounts, access is limited to authorised personnel in a controlled and continuously monitored setting, and all data will be deleted at the end of the exercise. After assessing the effectiveness of the proof of value and the lessons from it, MAS may expand the scope and sophistication of the models, including by using broader datasets and covering additional use cases for preventing and countering financial crime.
Monetary Authority of Singapore 2026-05-04
Monetary Authority of Singapore starts five-bank AI and machine learning proof of value for pre-emptive scam detection
The Monetary Authority of Singapore is conducting a proof of value with five banks, the Government Technology Agency and the Singapore Police Force to test artificial intelligence and machine learning for pre-emptive scam detection using combined banking data. MAS has established a secure data-sharing environment with cryptographic protections, hashed account identifiers, restricted access and data deletion at the end of the exercise, and may later expand the models’ scope and datasets to cover additional financial crime use cases.