Fraud protection with new personalised AWS service

AWS CEO Andy Jassy says machine learning is unbelievably helpful in detecting fraud.

Amazon Web Services (AWS) wants to be your fraud detection tool, packaging up its in-house capabilities as an easy to consume AWS service.

Amazon Fraud Detector is a new machine learning-driven fraud management service.

Making the announcement at AWS re:Invent on Tuesday, chief Andy Jassy said it requires no machine learning experience. 

He said his company is always looking at what it can offer up, including within its in-house capabilities, to give value to its customers.

"We have a number of services that we've done at scale at Amazon that customers have asked for as a service," he said, pointing to Amazon Lex, Amazon Personalize, and Amazon Forecast as recent examples.

According to Jassy, his company has the broadest and most complete set of machine learning capabilities, spanning from Rekognition through to SageMaker, which on Tuesday also received enhancements.

But one area Jassy said his company excels is in fraud detection.

"We've been doing fraud detection for over 20 years," he said.

"Machine learning is unbelievably helpful … but it's hard for most companies to use machine learning for fraud detection."

See also: How Amazon Web Services runs security at a global scale

The new fraud detection offering will be a service handled by the cloud giant.

img-8147.jpg

"You send us the transaction data … email addresses, IPs, perhaps phones numbers, along with transactions that are fraudulent and those which are legitimate and then we take that data along with the algorithms we've built … and we build a unique model for you," the CEO explained.

"It's then exposed via an API.

"A completely different way to manage fraud with machine learning."

Jassy said Amazon has a set of data detectors that recognises things like email domains and phony email addresses. 

Asha Barbaschow travelled to re:Invent as a guest of AWS.