IBM is set to launch a new chip, named Telum, which it said includes ‘AI inferencing acceleration’ that could help stop fraud.

The tech giant said that complex fraud detection often cannot be completed in real-time due to latency.

IBM claimed the chip could help businesses conduct high volume inferencing for real-time fraud transactions without using third party AI solutions.

The chip, which has been in development for three years, is planned for release in the first half of 2022.

IBM said Telum could be useful for financial services workloads like fraud detection, loan processing, clearing and settlement of trades, anti-money laundering (AML), and risk analysis.

The tech giant claimed users will be able to enhance existing fraud detection, accelerate credit approval processes, improve customer service and profitability, identify which trades or transactions may fail, and propose solutions to create a more efficient settlement process.

Samsung acted as IBM's technology development partner for the project and said Telum is the first chip made with technology created by the IBM Research AI Hardware Centre.

A third of financial institutions are accelerating their adoption of AI and machine learning (ML) for anti-money laundering (AML) in response to COVID-19, according to from SAS, KPMG, and the Association of Certified Anti-Money Laundering Specialists (ACAMS).

"The chip contains 8 processor cores with a deep super-scalar out-of-order instruction pipeline, running with more than 5GHz clock frequency, optimised for the demands of heterogenous enterprise-class workloads," said an IBM spokesperson. "The completely redesigned cache and chip-interconnection infrastructure provides 32MB cache per core, and can scale to 32 Telum chips.”
They added: “The dual-chip module design contains 22 billion transistors and 19 miles of wire on 17 metal layers."

Share Story: