A collection of key and value pairs.

The list of variables for the batch create variable request.

Provides the errors for the BatchCreateVariable request.

The response's http status code.

The list of variable names to get.

The errors from the request.

The returned variables.

The response's http status code.

The ID of an in-progress batch import job to cancel.

Amazon Fraud Detector will throw an error if the batch import job is in FAILED, CANCELED, or COMPLETED state.

The response's http status code.

The ID of the batch prediction job to cancel.

The response's http status code.

A collection of key-value pairs associated with this request.

The ID of the batch import job. The ID cannot be of a past job, unless the job exists in CREATE_FAILED state.

The URI that points to the Amazon S3 location of your data file.

The URI that points to the Amazon S3 location for storing your results.

The name of the event type.

The ARN of the IAM role created for Amazon S3 bucket that holds your data file.

The IAM role must have read permissions to your input S3 bucket and write permissions to your output S3 bucket. For more information about bucket permissions, see User policy examples in the Amazon S3 User Guide.

The response's http status code.

The detector version.

A collection of key and value pairs.

The ID of the batch prediction job.

The Amazon S3 location of your training file.

The Amazon S3 location of your output file.

The name of the event type.

The name of the detector.

The ARN of the IAM role to use for this job request.

The IAM Role must have read permissions to your input S3 bucket and write permissions to your output S3 bucket. For more information about bucket permissions, see User policy examples in the Amazon S3 User Guide.

The response's http status code.

The description of the detector version.

The Amazon Sagemaker model endpoints to include in the detector version.

The model versions to include in the detector version.

The rule execution mode for the rules included in the detector version.

You can define and edit the rule mode at the detector version level, when it is in draft status.

If you specify FIRST_MATCHED, Amazon Fraud Detector evaluates rules sequentially, first to last, stopping at the first matched rule. Amazon Fraud dectector then provides the outcomes for that single rule.

If you specifiy ALL_MATCHED, Amazon Fraud Detector evaluates all rules and returns the outcomes for all matched rules.

The default behavior is FIRST_MATCHED.

A collection of key and value pairs.

The ID of the detector under which you want to create a new version.

The rules to include in the detector version.

The ID for the created version's parent detector.

The ID for the created detector.

The status of the detector version.

The response's http status code.

The model description.

A collection of key and value pairs.

The model ID.

The model type.

The name of the event type.

The response's http status code.

Details of the external events data used for model version training. Required if trainingDataSource is EXTERNAL_EVENTS.

Details of the ingested events data used for model version training. Required if trainingDataSource is INGESTED_EVENTS.

A collection of key and value pairs.

The model ID.

The model type.

The training data source location in Amazon S3.

The training data schema.

The model ID.

The model type.

The model version number of the model version created.

The model version status.

The response's http status code.

The rule description.

A collection of key and value pairs.

The rule ID.

The detector ID for the rule's parent detector.

The rule expression.

The language of the rule.

The outcome or outcomes returned when the rule expression matches.

The created rule.

The response's http status code.

The description.

A collection of key and value pairs.

The variable type. For more information see Variable types.

Valid Values: AUTH_CODE | AVS | BILLING_ADDRESS_L1 | BILLING_ADDRESS_L2 | BILLING_CITY | BILLING_COUNTRY | BILLING_NAME | BILLING_PHONE | BILLING_STATE | BILLING_ZIP | CARD_BIN | CATEGORICAL | CURRENCY_CODE | EMAIL_ADDRESS | FINGERPRINT | FRAUD_LABEL | FREE_FORM_TEXT | IP_ADDRESS | NUMERIC | ORDER_ID | PAYMENT_TYPE | PHONE_NUMBER | PRICE | PRODUCT_CATEGORY | SHIPPING_ADDRESS_L1 | SHIPPING_ADDRESS_L2 | SHIPPING_CITY | SHIPPING_COUNTRY | SHIPPING_NAME | SHIPPING_PHONE | SHIPPING_STATE | SHIPPING_ZIP | USERAGENT

The name of the variable.

The data type.

The source of the data.

The default value for the variable when no value is received.

The response's http status code.

The ID of the batch import job to delete.

The response's http status code.

The ID of the batch prediction job to delete.

The response's http status code.

The ID of the detector to delete.

The response's http status code.

The ID of the parent detector for the detector version to delete.

The ID of the detector version to delete.

The response's http status code.

The name of the entity type to delete.

The response's http status code.

Specifies whether or not to delete any predictions associated with the event.

The ID of the event to delete.

The name of the event type.

The response's http status code.

The name of the event type to delete.

The response's http status code.

The name of the event type.

Name of event type for which to delete the events.

The status of the delete request.

The response's http status code.

The endpoint of the Amazon Sagemaker model to delete.

The response's http status code.

The name of the label to delete.

The response's http status code.

The model ID of the model to delete.

The model type of the model to delete.

The response's http status code.

The model ID of the model version to delete.

The model type of the model version to delete.

The model version number of the model version to delete.

The response's http status code.

The name of the outcome to delete.

The response's http status code.

Undocumented member.

The response's http status code.

The name of the variable to delete.

The response's http status code.

The maximum number of results to return for the request.

The next token from the previous response.

The detector ID.

The detector ARN.

The detector ID.

The status and description for each detector version.

The next token to be used for subsequent requests.

The response's http status code.

The maximum number of results to return.

The model ID.

The model type.

The model version number.

The next token from the previous results.

The model version details.

The next token.

The response's http status code.

The ID of the batch import job to get.

The maximum number of objects to return for request.

The next token from the previous request.

An array containing the details of each batch import job.

The next token for the subsequent resquest.

The response's http status code.

The batch prediction job for which to get the details.

The maximum number of objects to return for the request.

The next token from the previous request.

An array containing the details of each batch prediction job.

The next token for the subsequent request.

The response's http status code.

Name of event type for which to get the deletion status.

The event type name.

The deletion status.

The response's http status code.

The detector ID.

The detector version ID.

The detector version ARN.

The timestamp when the detector version was created.

The detector version description.

The detector ID.

The detector version ID.

The Amazon SageMaker model endpoints included in the detector version.

The timestamp when the detector version was last updated.

The model versions included in the detector version.

The execution mode of the rule in the dectector

FIRST_MATCHED indicates that Amazon Fraud Detector evaluates rules sequentially, first to last, stopping at the first matched rule. Amazon Fraud dectector then provides the outcomes for that single rule.

ALL_MATCHED indicates that Amazon Fraud Detector evaluates all rules and returns the outcomes for all matched rules. You can define and edit the rule mode at the detector version level, when it is in draft status.

The rules included in the detector version.

The status of the detector version.

The response's http status code.

The detector ID.

The maximum number of objects to return for the request.

The next token for the subsequent request.

The detectors.

The next page token.

The response's http status code.

The maximum number of objects to return for the request.

The name.

The next token for the subsequent request.

An array of entity types.

The next page token.

The response's http status code.

The ID of the event to retrieve.

The event type of the event to retrieve.

The details of the event.

The response's http status code.

The detector version ID.

The Amazon SageMaker model endpoint input data blobs.

The detector ID.

The unique ID used to identify the event.

The event type associated with the detector specified for the prediction.

The entity type (associated with the detector's event type) and specific entity ID representing who performed the event. If an entity id is not available, use "UNKNOWN."

Timestamp that defines when the event under evaluation occurred. The timestamp must be specified using ISO 8601 standard in UTC.

Names of the event type's variables you defined in Amazon Fraud Detector to represent data elements and their corresponding values for the event you are sending for evaluation.

You must provide at least one eventVariable

To ensure most accurate fraud prediction and to simplify your data preparation, Amazon Fraud Detector will replace all missing variables or values as follows:

For Amazon Fraud Detector trained models:

If a null value is provided explicitly for a variable or if a variable is missing, model will replace the null value or the missing variable (no variable name in the eventVariables map) with calculated default mean/medians for numeric variables and with special values for categorical variables.

For imported SageMaker models:

If a null value is provided explicitly for a variable, the model and rules will use “null” as the value. If a variable is not provided (no variable name in the eventVariables map), model and rules will use the default value that is provided for the variable.

The model scores for Amazon SageMaker models.

The model scores. Amazon Fraud Detector generates model scores between 0 and 1000, where 0 is low fraud risk and 1000 is high fraud risk. Model scores are directly related to the false positive rate (FPR). For example, a score of 600 corresponds to an estimated 10% false positive rate whereas a score of 900 corresponds to an estimated 2% false positive rate.

The results from the rules.

The response's http status code.

The event ID.

The event type associated with the detector specified for the prediction.

The detector ID.

The detector version ID.

The timestamp that defines when the prediction was generated. The timestamp must be specified using ISO 8601 standard in UTC.

We recommend calling ListEventPredictions first, and using the predictionTimestamp value in the response to provide an accurate prediction timestamp value.

The detector ID.

The detector version ID.

The status of the detector version.

The entity ID.

The entity type.

External (Amazon SageMaker) models that were evaluated for generating predictions.

Model versions that were evaluated for generating predictions.

The event ID.

The timestamp for when the prediction was generated for the associated event ID.

The event type associated with the detector specified for this prediction.

A list of event variables that influenced the prediction scores.

The outcomes of the matched rule, based on the rule execution mode.

The timestamp that defines when the prediction was generated.

The execution mode of the rule used for evaluating variable values.

List of rules associated with the detector version that were used for evaluating variable values.

The response's http status code.

The maximum number of objects to return for the request.

The name.

The next token for the subsequent request.

An array of event types.

The next page token.

The response's http status code.

The maximum number of objects to return for the request.

The Amazon SageMaker model endpoint.

The next page token for the request.

Gets the Amazon SageMaker models.

The next page token to be used in subsequent requests.

The response's http status code.

The KMS encryption key.

The response's http status code.

The maximum number of objects to return for the request.

The name of the label or labels to get.

The next token for the subsequent request.

An array of labels.

The next page token.

The response's http status code.

The model ID.

The model type.

The model version number.

The model version ARN.

The details of the external events data used for training the model version. This will be populated if the trainingDataSource is EXTERNAL_EVENTS

The details of the ingested events data used for training the model version. This will be populated if the trainingDataSource is INGESTED_EVENTS.

The model ID.

The model type.

The model version number.

The model version status.

Possible values are:

• TRAINING_IN_PROGRESS

• TRAINING_COMPLETE

• ACTIVATE_REQUESTED

• ACTIVATE_IN_PROGRESS

• ACTIVE

• INACTIVATE_REQUESTED

• INACTIVATE_IN_PROGRESS

• INACTIVE

• ERROR

The training data schema.

The training data source.

The response's http status code.

The maximum number of objects to return for the request.

The model ID.

The model type.

The next token for the subsequent request.

The array of models.

The next page token to be used in subsequent requests.

The response's http status code.

The maximum number of objects to return for the request.

The name of the outcome or outcomes to get.

The next page token for the request.

The next page token for subsequent requests.

The outcomes.

The response's http status code.

The maximum number of rules to return for the request.

The next page token.

The rule ID.

The rule version.

The detector ID.

The next page token to be used in subsequent requests.

The details of the requested rule.

The response's http status code.

The max size per page determined for the get variable request.

The name of the variable.

The next page token of the get variable request.

The next page token to be used in subsequent requests.

The names of the variables returned.

The response's http status code.

The detector ID.

The detector version ID.

The event ID.

The event type associated with the detector.

The maximum number of predictions to return for the request.

Identifies the next page of results to return. Use the token to make the call again to retrieve the next page. Keep all other arguments unchanged. Each pagination token expires after 24 hours.

The time period for when the predictions were generated.

The summary of the past predictions.

Identifies the next page of results to return. Use the token to make the call again to retrieve the next page. Keep all other arguments unchanged. Each pagination token expires after 24 hours.

The response's http status code.

The maximum number of objects to return for the request.

The next token from the previous results.

The ARN that specifies the resource whose tags you want to list.

The next token for subsequent requests.

A collection of key and value pairs.

The response's http status code.

The description of the detector.

A collection of key and value pairs.

The detector ID.

The name of the event type.

The response's http status code.

The description.

A collection of key and value pairs.

The name of the entity type.

The response's http status code.

The description of the event type.

Specifies if ingenstion is enabled or disabled.

The event type labels.

A collection of key and value pairs.

The name.

The event type variables.

The entity type for the event type. Example entity types: customer, merchant, account.

The response's http status code.

A collection of key and value pairs.

The model endpoints name.

The source of the model.

The IAM role used to invoke the model endpoint.

The model endpoint input configuration.

The model endpoint output configuration.

The model endpoint’s status in Amazon Fraud Detector.

The response's http status code.

The KMS encryption key ARN.

The KMS key must be single-Region key. Amazon Fraud Detector does not support multi-Region KMS key.

The response's http status code.

The label description.

The label name.

The response's http status code.

The outcome description.

A collection of key and value pairs.

The name of the outcome.

The response's http status code.

The label to associate with the event. Required if specifying labelTimestamp.

The timestamp associated with the label. Required if specifying assignedLabel.

The event ID to upload.

The event type name of the event.

The timestamp that defines when the event under evaluation occurred. The timestamp must be specified using ISO 8601 standard in UTC.

Names of the event type's variables you defined in Amazon Fraud Detector to represent data elements and their corresponding values for the event you are sending for evaluation.

An array of entities.

The response's http status code.

The resource ARN.

The tags to assign to the resource.

The response's http status code.

The ARN of the resource from which to remove the tag.

The resource ARN.

The response's http status code.

The detector version description.

The model versions to include in the detector version.

The rule execution mode to add to the detector.

If you specify FIRST_MATCHED, Amazon Fraud Detector evaluates rules sequentially, first to last, stopping at the first matched rule. Amazon Fraud dectector then provides the outcomes for that single rule.

If you specifiy ALL_MATCHED, Amazon Fraud Detector evaluates all rules and returns the outcomes for all matched rules. You can define and edit the rule mode at the detector version level, when it is in draft status.

The default behavior is FIRST_MATCHED.

The parent detector ID for the detector version you want to update.

The detector version ID.

The Amazon SageMaker model endpoints to include in the detector version.

The rules to include in the detector version.

The response's http status code.

The detector ID.

The detector version ID.

The description.

The response's http status code.

The detector ID.

The detector version ID.

The new status.

The only supported values are ACTIVE and INACTIVE

The response's http status code.

The ID of the event associated with the label to update.

The event type of the event associated with the label to update.

The new label to assign to the event.

The timestamp associated with the label. The timestamp must be specified using ISO 8601 standard in UTC.

The response's http status code.

The new model description.