In an effort to make it easier for businesses to identify fraud online, AWS has developed a new fully managed service called Amazon Fraud Detector which leverages the e-commerce giant’s years of experience detecting fraud as well as machine learning.
The new service can automatically identify potentially fraudulent activity in milliseconds using machine learning, though businesses won’t need to have any machine learning experience to start using it.
With just a few clicks in the Amazon Fraud Detector console, businesses can select a pre-built machine learning model template, upload historical event data and create decision logic to assign outcomes to the service’s predictions. There are also no up-front payments, long-term commitments or infrastructure to manage with Amazon Fraud Detector. Instead, customers only pay for their actual usage of the service.
Vice president of Amazon AI, Swami Sivasubramanian provided further insight on the new service in a press release, saying:
“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
Tens of billions of dollars are lost to online fraud every year and this has led some organizations to invest in large, expensive fraud management systems. However, these systems are often based on hand-coded rules that require a lot of time to set up, are expensive to customize and difficult to update as fraud patterns change leading to lower accuracy.
Over the past 20 years, Amazon has made significant investments in combating online fraud using sophisticated machine learning techniques. The company’s customers have asked it to share this expertise and experience to help them combat online fraud which is why AWS developed Amazon Fraud Detector.
To get started using the service, customers first need to upload historical event data such as transactions or account registrations to Amazon S3. This data is then encrypted (in transit and in rest) and used to customize the machine learning model’s training. Based on the type of fraud customers want to predict, Amazon Fraud Detector will pre-process the data, select an algorithm and train a model.
Amazon Fraud Detector is available now in the US East (N. Virginia), US East (Ohio), US West (Oregon), EU (Ireland), Asia Pacific (Singapore) and Asia Pacific (Sydney) regions though AWS plans to roll out the service to additional regions in the coming months.