UPDATED 16:21 EDT / JULY 28 2020

CLOUD

AWS bolsters AI services lineup with general availability of Fraud Detector

Amazon Web Services Inc. today announced the general availability of Fraud Detector, a service that enables organizations to build customized machine learning models for catching fraudulent activity such as scam transactions.

The service uses the same technology AWS parent Amazon.com Inc. employs to fight fraudulent activity on its e-commerce marketplace. According to the cloud giant, it doesn’t require any machine learning know-how to use.

Fraud Detector provides access to a selection of ready-made fraud detection AI templates that cover different use cases. Users can choose the one that best fits their project requirements, then train that model on their company’s transaction logs. The ability to tailor models for the specific types of transactions that an organization processes can, in theory, enable higher detection accuracy than a pre-packaged AI trained in advance on a generic dataset.

The AI creation process in Fraud Detector is fairly straightforward. Users upload their transaction logs to S3, AWS’ object storage service, define the type of activities they want their AI to look for and then train their model. After a half-hour to two hours of processing, Fraud Detector makes the trained model available via an application programming interface that can be plugged into a company’s systems.

Enterprises with more advanced requirements can use their own models with the service. That’s made possible through an integration with SageMaker, Amazon’s managed AI platform, which provides developer tools for building and training neural networks. 

AWS is positioning Fraud Detector as an alternative to traditional fraud detection systems that require analysts to create rules manually for when to block transactions. The service also promises to cut development times for companies building their own detection infrastructure. Charles Grech, chief operating officer at payments processing provider Truevo, said his firm avoided three to six months of development time by deploying the service.

AWS is targeting a big market with Fraud Detector. Payment card fraud alone is estimated to have caused losses of more than $16 billion in the U.S. last year and, according to Amazon, online fraud costs companies tens of billions of dollars worldwide annually. 

“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,” said Swami Sivasubramanian, vice president of the Amazon Machine Learning group at AWS.

Developers have access to a growing number of AI tools, many of them open-source, that cover an ever-broadening range of use cases. The major cloud providers have sought to set their platforms apart by offering increasingly specialized AI services for key enterprise use cases, a trend that Fraud Detector continues. Another recent entry into this category is the Recommendations AI service Google LLC launched into public beta last week, which allows e-commerce to develop customized product recommendation models.

Photo: AWS

A message from John Furrier, co-founder of SiliconANGLE:

Your vote of support is important to us and it helps us keep the content FREE.

One click below supports our mission to provide free, deep, and relevant content.  

Join our community on YouTube

Join the community that includes more than 15,000 #CubeAlumni experts, including Amazon.com CEO Andy Jassy, Dell Technologies founder and CEO Michael Dell, Intel CEO Pat Gelsinger, and many more luminaries and experts.

“TheCUBE is an important partner to the industry. You guys really are a part of our events and we really appreciate you coming and I know people appreciate the content you create as well” – Andy Jassy

THANK YOU