Amazon Fraud Detector launches ability to cancel in-progress model trainings
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, using customized machine learning (ML) models. In just a few clicks you can create and train a fraud detection model, with no prior machine learning experience required.
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, using customized machine learning (ML) models. In just a few clicks you can create and train a fraud detection model, with no prior machine learning experience required.
Now, you can cancel a model version training that is in progress. Since only one training can take place at a time per model, and training can take up to several hours, you previously had to wait for training to complete if you misconfigured a setting. You can now move faster by canceling the current training and immediately starting a new one. This new capability also helps you avoid unnecessary model training costs, as you will only be billed for any training time consumed before the cancellation.
You can cancel a model version training via the AWS console, SDK or CLI. To cancel model training using the console, sign in to the AWS Management Console, open the Amazon Fraud Detector console here, and navigate to a model version that has a status of “Training...”. Next, select “Actions” and then select “Cancel training”.
The new cancel training feature for Amazon Fraud Detector is 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.