The Monetary Authority of Singapore (MAS) today announced that it is working with partners in the banking industry, the Government Technology Agency of Singapore, and the Singapore Police Force to combat financial crime, using artificial intelligence and machine learning (AI/ML) techniques to enhance scam detection capabilities.

As part of broader efforts to harness AI/ML for industry-wide use cases, MAS is conducting a Proof-of-Value (POV) to explore AI/ML techniques for pre-emptive scam detection. By bringing together data from across five banks, the POV aims to build more robust and accurate AI/ML models that help identify higher-risk transactions and accounts. Prompt identification could enable timely assessment, intervention and reduction of customer losses to scams.

For purposes of the POV, historical transaction data with bank account numbers from participating banks will be used to train and evaluate AI/ML models to assess their potential for improving scam detection.

To support the POV, MAS has provided industry partners with a secure data sharing environment governed by policies and protocols to safeguard customer information. A secure data sharing framework with industry participants has also been established to ensure that data will be protected and used responsibly.

Data used in the POV will remain confidential and protected with cryptographic techniques. Bank account numbers used will be hashed, ensuring that only the contributing bank can identify actual account numbers. Data access will be restricted to authorised personnel within a controlled setting that will be continuously monitored throughout the POV. All data used in the POV will be deleted at the end of the POV.

The current POV lays the groundwork for deeper industry collaboration, harnessing AI/ML to enhance and complement individual financial institution’s existing efforts in preventing and countering financial crime. After assessing the effectiveness of the POV and learning from it, MAS may expand the scope and sophistication of AI/ML models used – incorporating broader datasets, and a wider set of use cases to further fortify our financial system’s defences against criminal activity.