AWS.FraudDetector (aws-elixir v0.8.0) View Source

This is the Amazon Fraud Detector API Reference.

This guide is for developers who need detailed information about Amazon Fraud Detector API actions, data types, and errors. For more information about Amazon Fraud Detector features, see the Amazon Fraud Detector User Guide.

Link to this section Summary

Functions

Cancels the specified batch prediction job.

Creates a model using the specified model type.

Creates a version of the model using the specified model type and model id.

Creates a rule for use with the specified detector.

Deletes the specified event.

Removes a SageMaker model from Amazon Fraud Detector.

Gets all versions for a specified detector.

Gets all of the model versions for the specified model type or for the specified model type and model ID.

Gets all batch prediction jobs or a specific job if you specify a job ID.

Gets a particular detector version.

Gets all detectors or a single detector if a detectorId is specified.

Gets all entity types or a specific entity type if a name is specified.

Evaluates an event against a detector version.

Gets all event types or a specific event type if name is provided.

Gets the details for one or more Amazon SageMaker models that have been imported into the service.

Gets the encryption key if a Key Management Service (KMS) customer master key (CMK) has been specified to be used to encrypt content in Amazon Fraud Detector.

Gets all labels or a specific label if name is provided.

Gets the details of the specified model version.

Gets one or more models.

Gets one or more outcomes.

Get all rules for a detector (paginated) if ruleId and ruleVersion are not specified.

Gets all of the variables or the specific variable.

Lists all tags associated with the resource.

Creates or updates a detector.

Creates or updates an entity type.

Creates or updates an event type.

Creates or updates an Amazon SageMaker model endpoint.

Specifies the Key Management Service (KMS) customer master key (CMK) to be used to encrypt content in Amazon Fraud Detector.

Creates or updates label.

Creates or updates an outcome.

Assigns tags to a resource.

Removes tags from a resource.

Updates the detector version's description.

Updates the detector version’s status.

Updates the status of a model version.

Updates a rule version resulting in a new rule version.

Link to this section Functions

Link to this function

batch_create_variable(client, input, options \\ [])

View Source

Creates a batch of variables.

Link to this function

batch_get_variable(client, input, options \\ [])

View Source

Gets a batch of variables.

Link to this function

cancel_batch_prediction_job(client, input, options \\ [])

View Source

Cancels the specified batch prediction job.

Link to this function

create_batch_prediction_job(client, input, options \\ [])

View Source

Creates a batch prediction job.

Link to this function

create_detector_version(client, input, options \\ [])

View Source

Creates a detector version.

The detector version starts in a DRAFT status.

Link to this function

create_model(client, input, options \\ [])

View Source

Creates a model using the specified model type.

Link to this function

create_model_version(client, input, options \\ [])

View Source

Creates a version of the model using the specified model type and model id.

Link to this function

create_rule(client, input, options \\ [])

View Source

Creates a rule for use with the specified detector.

Link to this function

create_variable(client, input, options \\ [])

View Source

Creates a variable.

Link to this function

delete_batch_prediction_job(client, input, options \\ [])

View Source

Deletes a batch prediction job.

Link to this function

delete_detector(client, input, options \\ [])

View Source

Deletes the detector.

Before deleting a detector, you must first delete all detector versions and rule versions associated with the detector.

When you delete a detector, Amazon Fraud Detector permanently deletes the detector and the data is no longer stored in Amazon Fraud Detector.

Link to this function

delete_detector_version(client, input, options \\ [])

View Source

Deletes the detector version.

You cannot delete detector versions that are in ACTIVE status.

When you delete a detector version, Amazon Fraud Detector permanently deletes the detector and the data is no longer stored in Amazon Fraud Detector.

Link to this function

delete_entity_type(client, input, options \\ [])

View Source

Deletes an entity type.

You cannot delete an entity type that is included in an event type.

When you delete an entity type, Amazon Fraud Detector permanently deletes that entity type and the data is no longer stored in Amazon Fraud Detector.

Link to this function

delete_event(client, input, options \\ [])

View Source

Deletes the specified event.

When you delete an event, Amazon Fraud Detector permanently deletes that event and the event data is no longer stored in Amazon Fraud Detector.

Link to this function

delete_event_type(client, input, options \\ [])

View Source

Deletes an event type.

You cannot delete an event type that is used in a detector or a model.

When you delete an entity type, Amazon Fraud Detector permanently deletes that entity type and the data is no longer stored in Amazon Fraud Detector.

Link to this function

delete_external_model(client, input, options \\ [])

View Source

Removes a SageMaker model from Amazon Fraud Detector.

You can remove an Amazon SageMaker model if it is not associated with a detector version. Removing a SageMaker model disconnects it from Amazon Fraud Detector, but the model remains available in SageMaker.

Link to this function

delete_label(client, input, options \\ [])

View Source

Deletes a label.

You cannot delete labels that are included in an event type in Amazon Fraud Detector.

You cannot delete a label assigned to an event ID. You must first delete the relevant event ID.

When you delete a label, Amazon Fraud Detector permanently deletes that label and the data is no longer stored in Amazon Fraud Detector.

Link to this function

delete_model(client, input, options \\ [])

View Source

Deletes a model.

You can delete models and model versions in Amazon Fraud Detector, provided that they are not associated with a detector version.

When you delete a model, Amazon Fraud Detector permanently deletes that model and the data is no longer stored in Amazon Fraud Detector.

Link to this function

delete_model_version(client, input, options \\ [])

View Source

Deletes a model version.

You can delete models and model versions in Amazon Fraud Detector, provided that they are not associated with a detector version.

When you delete a model version, Amazon Fraud Detector permanently deletes that model version and the data is no longer stored in Amazon Fraud Detector.

Link to this function

delete_outcome(client, input, options \\ [])

View Source

Deletes an outcome.

You cannot delete an outcome that is used in a rule version.

When you delete an outcome, Amazon Fraud Detector permanently deletes that outcome and the data is no longer stored in Amazon Fraud Detector.

Link to this function

delete_rule(client, input, options \\ [])

View Source

Deletes the rule.

You cannot delete a rule if it is used by an ACTIVE or INACTIVE detector version.

When you delete a rule, Amazon Fraud Detector permanently deletes that rule and the data is no longer stored in Amazon Fraud Detector.

Link to this function

delete_variable(client, input, options \\ [])

View Source

Deletes a variable.

You can't delete variables that are included in an event type in Amazon Fraud Detector.

Amazon Fraud Detector automatically deletes model output variables and SageMaker model output variables when you delete the model. You can't delete these variables manually.

When you delete a variable, Amazon Fraud Detector permanently deletes that variable and the data is no longer stored in Amazon Fraud Detector.

Link to this function

describe_detector(client, input, options \\ [])

View Source

Gets all versions for a specified detector.

Link to this function

describe_model_versions(client, input, options \\ [])

View Source

Gets all of the model versions for the specified model type or for the specified model type and model ID.

You can also get details for a single, specified model version.

Link to this function

get_batch_prediction_jobs(client, input, options \\ [])

View Source

Gets all batch prediction jobs or a specific job if you specify a job ID.

This is a paginated API. If you provide a null maxResults, this action retrieves a maximum of 50 records per page. If you provide a maxResults, the value must be between 1 and 50. To get the next page results, provide the pagination token from the GetBatchPredictionJobsResponse as part of your request. A null pagination token fetches the records from the beginning.

Link to this function

get_detector_version(client, input, options \\ [])

View Source

Gets a particular detector version.

Link to this function

get_detectors(client, input, options \\ [])

View Source

Gets all detectors or a single detector if a detectorId is specified.

This is a paginated API. If you provide a null maxResults, this action retrieves a maximum of 10 records per page. If you provide a maxResults, the value must be between 5 and 10. To get the next page results, provide the pagination token from the GetDetectorsResponse as part of your request. A null pagination token fetches the records from the beginning.

Link to this function

get_entity_types(client, input, options \\ [])

View Source

Gets all entity types or a specific entity type if a name is specified.

This is a paginated API. If you provide a null maxResults, this action retrieves a maximum of 10 records per page. If you provide a maxResults, the value must be between 5 and 10. To get the next page results, provide the pagination token from the GetEntityTypesResponse as part of your request. A null pagination token fetches the records from the beginning.

Link to this function

get_event_prediction(client, input, options \\ [])

View Source

Evaluates an event against a detector version.

If a version ID is not provided, the detector’s (ACTIVE) version is used.

Link to this function

get_event_types(client, input, options \\ [])

View Source

Gets all event types or a specific event type if name is provided.

This is a paginated API. If you provide a null maxResults, this action retrieves a maximum of 10 records per page. If you provide a maxResults, the value must be between 5 and 10. To get the next page results, provide the pagination token from the GetEventTypesResponse as part of your request. A null pagination token fetches the records from the beginning.

Link to this function

get_external_models(client, input, options \\ [])

View Source

Gets the details for one or more Amazon SageMaker models that have been imported into the service.

This is a paginated API. If you provide a null maxResults, this actions retrieves a maximum of 10 records per page. If you provide a maxResults, the value must be between 5 and 10. To get the next page results, provide the pagination token from the GetExternalModelsResult as part of your request. A null pagination token fetches the records from the beginning.

Link to this function

get_kms_encryption_key(client, input, options \\ [])

View Source

Gets the encryption key if a Key Management Service (KMS) customer master key (CMK) has been specified to be used to encrypt content in Amazon Fraud Detector.

Link to this function

get_labels(client, input, options \\ [])

View Source

Gets all labels or a specific label if name is provided.

This is a paginated API. If you provide a null maxResults, this action retrieves a maximum of 50 records per page. If you provide a maxResults, the value must be between 10 and 50. To get the next page results, provide the pagination token from the GetGetLabelsResponse as part of your request. A null pagination token fetches the records from the beginning.

Link to this function

get_model_version(client, input, options \\ [])

View Source

Gets the details of the specified model version.

Link to this function

get_models(client, input, options \\ [])

View Source

Gets one or more models.

Gets all models for the AWS account if no model type and no model id provided. Gets all models for the AWS account and model type, if the model type is specified but model id is not provided. Gets a specific model if (model type, model id) tuple is specified.

This is a paginated API. If you provide a null maxResults, this action retrieves a maximum of 10 records per page. If you provide a maxResults, the value must be between 1 and 10. To get the next page results, provide the pagination token from the response as part of your request. A null pagination token fetches the records from the beginning.

Link to this function

get_outcomes(client, input, options \\ [])

View Source

Gets one or more outcomes.

This is a paginated API. If you provide a null maxResults, this actions retrieves a maximum of 100 records per page. If you provide a maxResults, the value must be between 50 and 100. To get the next page results, provide the pagination token from the GetOutcomesResult as part of your request. A null pagination token fetches the records from the beginning.

Link to this function

get_rules(client, input, options \\ [])

View Source

Get all rules for a detector (paginated) if ruleId and ruleVersion are not specified.

Gets all rules for the detector and the ruleId if present (paginated). Gets a specific rule if both the ruleId and the ruleVersion are specified.

This is a paginated API. Providing null maxResults results in retrieving maximum of 100 records per page. If you provide maxResults the value must be between 50 and 100. To get the next page result, a provide a pagination token from GetRulesResult as part of your request. Null pagination token fetches the records from the beginning.

Link to this function

get_variables(client, input, options \\ [])

View Source

Gets all of the variables or the specific variable.

This is a paginated API. Providing null maxSizePerPage results in retrieving maximum of 100 records per page. If you provide maxSizePerPage the value must be between 50 and 100. To get the next page result, a provide a pagination token from GetVariablesResult as part of your request. Null pagination token fetches the records from the beginning.

Link to this function

list_tags_for_resource(client, input, options \\ [])

View Source

Lists all tags associated with the resource.

This is a paginated API. To get the next page results, provide the pagination token from the response as part of your request. A null pagination token fetches the records from the beginning.

Link to this function

put_detector(client, input, options \\ [])

View Source

Creates or updates a detector.

Link to this function

put_entity_type(client, input, options \\ [])

View Source

Creates or updates an entity type.

An entity represents who is performing the event. As part of a fraud prediction, you pass the entity ID to indicate the specific entity who performed the event. An entity type classifies the entity. Example classifications include customer, merchant, or account.

Link to this function

put_event_type(client, input, options \\ [])

View Source

Creates or updates an event type.

An event is a business activity that is evaluated for fraud risk. With Amazon Fraud Detector, you generate fraud predictions for events. An event type defines the structure for an event sent to Amazon Fraud Detector. This includes the variables sent as part of the event, the entity performing the event (such as a customer), and the labels that classify the event. Example event types include online payment transactions, account registrations, and authentications.

Link to this function

put_external_model(client, input, options \\ [])

View Source

Creates or updates an Amazon SageMaker model endpoint.

You can also use this action to update the configuration of the model endpoint, including the IAM role and/or the mapped variables.

Link to this function

put_kms_encryption_key(client, input, options \\ [])

View Source

Specifies the Key Management Service (KMS) customer master key (CMK) to be used to encrypt content in Amazon Fraud Detector.

Link to this function

put_label(client, input, options \\ [])

View Source

Creates or updates label.

A label classifies an event as fraudulent or legitimate. Labels are associated with event types and used to train supervised machine learning models in Amazon Fraud Detector.

Link to this function

put_outcome(client, input, options \\ [])

View Source

Creates or updates an outcome.

Link to this function

tag_resource(client, input, options \\ [])

View Source

Assigns tags to a resource.

Link to this function

untag_resource(client, input, options \\ [])

View Source

Removes tags from a resource.

Link to this function

update_detector_version(client, input, options \\ [])

View Source

Updates a detector version.

The detector version attributes that you can update include models, external model endpoints, rules, rule execution mode, and description. You can only update a DRAFT detector version.

Link to this function

update_detector_version_metadata(client, input, options \\ [])

View Source

Updates the detector version's description.

You can update the metadata for any detector version (DRAFT, ACTIVE, or INACTIVE).

Link to this function

update_detector_version_status(client, input, options \\ [])

View Source

Updates the detector version’s status.

You can perform the following promotions or demotions using UpdateDetectorVersionStatus: DRAFT to ACTIVE, ACTIVE to INACTIVE, and INACTIVE to ACTIVE.

Link to this function

update_model(client, input, options \\ [])

View Source

Updates a model.

You can update the description attribute using this action.

Link to this function

update_model_version(client, input, options \\ [])

View Source

Updates a model version.

Updating a model version retrains an existing model version using updated training data and produces a new minor version of the model. You can update the training data set location and data access role attributes using this action. This action creates and trains a new minor version of the model, for example version 1.01, 1.02, 1.03.

Link to this function

update_model_version_status(client, input, options \\ [])

View Source

Updates the status of a model version.

You can perform the following status updates:

  1. Change the TRAINING_COMPLETE status to ACTIVE.

  2. Change ACTIVEto INACTIVE.

Link to this function

update_rule_metadata(client, input, options \\ [])

View Source

Updates a rule's metadata.

The description attribute can be updated.

Link to this function

update_rule_version(client, input, options \\ [])

View Source

Updates a rule version resulting in a new rule version.

Updates a rule version resulting in a new rule version (version 1, 2, 3 ...).

Link to this function

update_variable(client, input, options \\ [])

View Source

Updates a variable.