IBM is harnessing the power of real-time AI to help banks analyse for fraud during transactions on a "massive scale".
Credit card fraud continues to plague consumers around the world, costing the industry $32 billion last year.
Banks have been hampered in their efforts to tackle the problem because running deep-learning models at scale in real-time has not been possible due to latency issues, meaning detections models are only run on less than 10% of high-volume transactions.
Big Blue claims to have solved this with IBM z16, which brings together AI inferencing, via its IBM Telum Processor, with highly secured and reliable high-volume transaction processing. The technology can process 300 billion inference requests per day with just one millisecond of latency.
For consumers, this could mean reducing the time and energy required to handle fraudulent transactions on their credit card, while for merchants and card issuers it could mean a reduction in revenue loss as consumers avoid false declines.
IBM says z16 is also the industry's first quantum-safe system, underpinned by lattice-based cryptography.
Ric Lewis, SVP, IBM Systems, says: “IBM is the gold standard for highly secured transaction processing. Now with IBM z16 innovations, our clients can increase decision velocity with inferencing right where their mission critical data lives.”