Amazon Fraud Detector will no longer be open to new customers starting November 7, 2025. If you would like to use Amazon Fraud Detector, sign up prior to that date. For capabilities similar to Amazon Fraud Detector, explore Amazon SageMaker AI, AutoGluon, and AWS WAF.
MetricDataPoint
Model performance metrics data points.
Contents
- fpr
-
The false positive rate. This is the percentage of total legitimate events that are incorrectly predicted as fraud.
Type: Float
Required: No
- precision
-
The percentage of fraud events correctly predicted as fraudulent as compared to all events predicted as fraudulent.
Type: Float
Required: No
- threshold
-
The model threshold that specifies an acceptable fraud capture rate. For example, a threshold of 500 means any model score 500 or above is labeled as fraud.
Type: Float
Required: No
- tpr
-
The true positive rate. This is the percentage of total fraud the model detects. Also known as capture rate.
Type: Float
Required: No
See Also
For more information about using this API in one of the language-specific AWS SDKs, see the following:
