Fraud Detector

Amazon Fraud Detector is a fully managed fraud detection service.

It allows you to look at various historical trends and other related data and identify any potential fraud as it relates to certain online activities like new account creations, payments or guest checkouts.

You upload some historical data and choose a model type:

  • Online fraud is designed for when you have little historical data and you’re looking to identify any problematic events such as new customer accounts. You might not have any data for a particular customer. Logically enough, they’re just signing up for an account. So Fraud Detector looks at general trends such as if there are any surrounding elements of concern around this particular sign-up for this particular user.

  • Transaction fraud is ideal for when you do have a transactional history for that customer that can be used to identify any suspect payments. This is fairly commonly used when you’re performing credit card transaction validation. You do have a full purchase history for a customer. You can build up a fairly good profile for a given customer of what their normal transactions are like.

  • Account Takeover can be used to identify any phishing or other social media or social based attacks. For example if somebody signs in from a completely different location or if they’re referred from a certain site.

All the various events are scored, and you can create rules which as a type of decision logic. This logic is used to react to these scores based on your business activity or business risk.

Amazon Fraud Detector is a backend-style service, it’s available via CLI, API and Python SDK.