Provision Model and Detector
A 4-step recipe with Amazon Fraud Detector. We can help you get access.
Recipe · 4 steps
Provision Model and Detector
with Amazon Fraud Detector · Fraud Detection & Investigation Management
Provision an event type, an ML model, and a detector in one pass.
- Create or update the event type so the model and detector have a schema to bind to.
- Create the ML model bound to the event type defined in the previous step.
- Create the detector that orchestrates models and rules for the same event type.
- Read the detector back by id to confirm it was created against the expected event type.
What you'll need to have ready
- eventTypeName: The event type that the model and detector both operate on.
- eventVariables: The event variable names that make up the event schema.
- labels: The label names available for this event type.
- entityTypes: The entity type names associated with the event type.
- modelId: The identifier for the ML model to create (e.g. "fraud-model-v1").
- modelType: The model type, such as ONLINE_FRAUD_INSIGHTS.
- modelDescription: A human readable description of the model.
- detectorId: The identifier for the detector to create (e.g. "payment-fraud-detector").
- detectorDescription: A human readable description of the detector.
For your developer
Arazzo workflow amazon-fraud-detector:provision-model-detector, 4 operations: PutEventType → putModel → PutDetector → GetDetectors. Specs on APIs.io.