AWS Launches Fraud-Detection Service Based on Machine Learning
- By John K. Waters
A new managed solution from Amazon Web Services (AWS) uses machine learning to help users identify potentially fraudulent online activities.
Now generally available, Amazon Fraud Detector takes milliseconds to identify malicious activities like online payment and identity fraud. It uses machine learning to do so, but requires no machine learning expertise on the part of the user, according to AWS.
The Amazon Fraud Detector features a console through which users can select a pre-built machine learning model template, upload historical event data, and create decision logic to assign outcomes to the predictions, the company says. They can, for example, initiate a fraud investigation when the machine learning model predicts potentially fraudulent activity.
There's more than machine learning tech behind the new service, said Swami Sivasubramanian, vice president of the Amazon Machine Learning group. Amazon Fraud Detector leverages the online retailer's two decades of fraud detection experience.
"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," Sivasubramanian said in a statement. "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."
For developers who do possess machine learning experience, the Fraud Detector can be customized using a combination of machine learning models built with the Fraud Detector and those built with Amazon's SageMaker, which is a fully managed service for building, training and deploying machine learning models.
GoDaddy was one of the early adopters of the Fraud Detection service. The company is using the service to give its customers another tool to help them grow online, said John Kercheval, senior director of GoDaddy's Identity Services Group, in a statement. His company likes the low cost of implementation and a self-service approach to building a machine learning model.
"The model can be easily deployed and used in our new account process without impacting the signup experience for legitimate customers," Kercheval said. "The model we built...is able to detect likely fraudulent sign-ups immediately, so we're very pleased with the results and look forward to accomplishing more."
Online payment products provider Truevo, a longtime AWS customer, is another early adopter. "With Amazon Fraud Detector, we are no longer bound by the conventional limitations of on-premises or SaaS offerings," said Truevo COO Charles Grech in a statement. "Instead, we have the flexibility to adapt a machine learning-powered service to meet our needs and the ability to use AWS's rules-only option while easily scaling to full machine learning capabilities when needed."
Amazon Fraud Detector is available today in the U.S. East (N. Virginia), U.S. East (Ohio), U.S. West (Oregon), EU (Ireland), Asia Pacific (Singapore) and Asia Pacific (Sydney) regions, with availability in additional regions in the coming in a few months, the company said in a statement.
More information is available now online.
John K. Waters is the editor in chief of a number of Converge360.com sites, with a focus on high-end development, AI and future tech. He's been writing about cutting-edge technologies and culture of Silicon Valley for more than two decades, and he's written more than a dozen books. He also co-scripted the documentary film Silicon Valley: A 100 Year Renaissance, which aired on PBS. He can be reached at email@example.com.