Amazon Web Services (AWS) has announced the availability of a servicefraud detection based on machine learning.
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 the customers and all the Companies have told us that they spend a lot of time and effort trying to reduce the amount of fraud that occurs on their websites and apps," said Amazon's VP of Machine Learning Swami Sivasubramanian.
“Leveraging our 20 years of fraud detection experience combined with a strong technology machine learning, we are excited to make Amazon Fraud Detector available to our customers so they can automatically detect potential fraud, save time and money, and improve their customer experiences.”
Based on the type of fraud customers want to predict, the Amazon Fraud Detector service will pre-process them data, will 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 availables starting today in select US regions, Ireland, Singapore and Sydney. Additional regions will be added in the coming months.