AWS launches AI tool that helps businesses tackle online fraud

Carly Page

29 Jul, 2020

Amazon Web Services (AWS) has announced the general availability of Fraud Detector, a machine learning-powered service that helps organisations to tackle fraudulent activity.

First launched at Amazon Re:invent last December, Fraud Detector uses the same technology that Amazon employs to fight fraudulent activity on its e-commerce marketplace. 

The tool requires no machine learning expertise, according to AWS, with Fraud Detector providing a selection of ready-made fraud detection AI templates that cover different use cases. To train their model, organisations simply upload historical data covering both fraudulent and legitimate transactions to AWS S3.

Businesses with more advanced requirements can use their own models with the service using an integration with SageMaker, Amazon’s managed AI platform. 

AWS charges no up-front payments, long-term commitments, or infrastructure to manage with Amazon Fraud Detector, and customers pay only for their actual usage of the service.

Swami Sivasubramanian, Vice President, Machine Learning, said: “Customers of all sizes and across all industries have told us they spend a lot of time and effort trying to decrease the amount of fraud occurring on their websites and applications.

“By leveraging 20 years of experience detecting fraud coupled with powerful machine learning technology, we’re excited to bring customers Amazon Fraud Detector so they can automatically detect potential fraud, save time and money, and improve customer experiences – with no machine learning experience required.”

Amazon Fraud Detector, which counts GoDaddyy and Truevo among is early adopters, is available in the US, Ireland, Sinapore and Sydney, with availability in additional regions in the coming months. 

The launch of Fraud Detector comes after Amazon made CodeGuru generally available. This is an AI-powered code review service that uses programme analysis and machine learning to detect potential defects that are tricky to find and recommend fixes in Java code.