Amazon’s machine learning technology helps retailers fight fraud

Amazon has introduced anti-fraud technology for retailers, reports Techhq.

Amazon Fraud Detector automates the time-consuming and expensive steps of creating, training, and deploying a machine learning model for fraud detection, making it easier for customers to use this technology. It customizes each model it creates to fit the client’s own data set, making it more accurate than current generic solutions.

“With just a few clicks in the Amazon Fraud Detector console, customers can select a pre-created machine learning model template, upload historical event data, and create decision logic to assign results to forecasts, such as initiating a fraud investigation when the machine learning model predicts potentially fraudulent activity”, – the online retail giant states.

The tool deploys models in a private API to which users can submit new actions – whether new purchases or registrations-to get a response about fraud that includes a risk assessment. The system can then determine the correct course of action, such as accepting a purchase or submitting it to a person for review.

Amazon has long turned its attention to machine learning for the difficult task of detecting fraud, and while the technology is “incredibly useful” in this app, according to CEO Andy Jassey, it’s hard for most businesses to get started.

Early reported that the Taiwan President’s General Secretary resigns amid bribery associated with the family.