Amazon Web Services (AWS) has announced the availability of a machine learning-based fraud detection service.
The Amazon Fraud Detector is a fully managed service, which helps to quickly identify possible malicious internet activities, such as online payment with identity fraud, creating fake accounts, abuse of promo codes "in milliseconds".
"All our customers and all our companies have said that they spend a lot of time and effort trying to reduce the amount of fraud that occurs on their websites and applications," said Swami Sivasubramanian, VP of Amazon's machine learning division.
"Utilizing our 20 years of fraud detection experience combined with a powerful machine learning technology, we are excited to offer our customers the Amazon Fraud Detector, so they can automatically detect potential fraud, save time and money and improve the experiences of their customers. ”
Based on the type of scam customers want to predict, Amazon Fraud Detector will pre-process the data, select an algorithm, and train a model.
Amazon Fraud Detector trains and develops a model in a fully managed, private API endpoint. Customers can submit any new activity to the API, such as subscriptions or new purchases, to receive responses, with a fraud risk rating. Based on the report, a customer request can determine the correct course of action to follow, for example, to accept a purchase or pass it on to a person for further review, AWS reports.
Amazon Fraud Detector is available today in some parts of the US, Ireland, Singapore and Sydney. Additional areas will be added in the coming months.