Pre-built model templates

Amazon Fraud Detector comes with pre-built machine learning model templates that identify potential fraud for common online activities such as new account creations, online payments, and guest checkouts. The model templates take care of all the heavy lifting for you such as data validation and enrichment, feature engineering, algorithm selection, hyperparameter tuning, and model deployment. You simply upload your dataset, select the model template and Fraud Detector automatically finds the best fitting fraud detection ML model. No coding or previous machine learning experience is required.

Trigger actions based on rules

Once your Amazon Fraud Detector fraud detection model is created, you can use the Fraud Detector console to create rules based on model predictions. Customers can create rules to take actions such as accept, review, or collect more information for specific model scores. For example, you can easily create a rule to flag suspicious customer accounts for review if the model score is greater than 500 and the account’s phone number country and IP address country do not match.

trigger_rules
Click to enlarge
trigger_rules

Real-time fraud prediction API

To perform real-time fraud predictions, you can use the Amazon Fraud Detector API in your application to evaluate online activities as they occur. You can call the fraud predictions API to check every new account sign-up for potential fraud risk using your model and rules to trigger an action.

A single interface to review and audit your predictions and detection logic

Using the Amazon Fraud Detector console you can easily search and review your past fraud evaluations to audit detection logic. Once you have your desired evaluations you can view the data received for these events, the detection logic applied during the evaluation, and the conditions that resulted in a fraud prediction outcome.

search_past_evaluations
Click to enlarge
search_past_evaluations

Amazon SageMaker integration

If you have already created a fraud detection model in Amazon SageMaker, you can bring it to Amazon Fraud Detector in order to stop even more fraud. You can use both your SageMaker and Fraud Detector models in your application to detect different fraud use cases. For example, your application can use the Fraud Detector model to assess the fraud risk of customer accounts and simultaneously use your SageMaker model to check for account compromise risk. 

Product-Page_Standard-Icons_01_Product-Features_SqInk
Learn more about product pricing

Visit the Amazon Fraud Detector pricing page.

Learn more 
Product-Page_Standard-Icons_02_Sign-Up_SqInk
Sign up for a free account

Instantly get access to the AWS Free Tier. 

Sign up 
Product-Page_Standard-Icons_03_Start-Building_SqInk
Start building in the console

Get started building with Amazon Fraud Detector in the AWS Management Console.

Sign in