Posted On: Nov 6, 2020

Amazon Fraud Detector is a fully managed service that makes it easy to identify potentially fraudulent online activities, such as the creation of fake accounts or online payment fraud. You can now delete Amazon Fraud Detector models, event types, entity types, outcomes, labels, and variables. You can also remove an imported AWS SageMaker model from Amazon Fraud Detector (while keeping the model’s endpoint available within SageMaker). In addition, the Amazon Fraud Detector console now lists associated resources so you can more easily discover where a particular resource is utilized across the service. For example, you can view which Models and Detectors are using a particular Event Type.

These new capabilities together with previously launched features to delete detectors, events, and rules enable you to more easily manage all Amazon Fraud Detector resources types. For example, deleting resources can help you clean up ones that you no longer need, and keep your account organized. You can also experiment with creating different models and detection logic, and delete them once you complete your experiment in order to avoid incurring unnecessary charges. 

You can delete resources via the AWS console, SDK or CLI. To delete a resource using the console, sign in to the AWS Management Console, open the Amazon Fraud Detector console here, and navigate to the resource you want to delete. Next, choose Actions and then choose Delete. When you delete resources from Amazon Fraud Detector, they are permanently deleted; any associated metadata or artifact (e.g., model) is no longer stored by the service.  

The new delete features and associated resources features for Amazon Fraud Detector are available today in the US East (N. Virginia), US East (Ohio), US West (Oregon), Europe (Ireland), Asia Pacific (Singapore) and Asia Pacific (Sydney) regions. For further details, see our documentation.