libZSservicesZSamazonka-frauddetectorZSamazonka-frauddetector
Copyright(c) 2013-2021 Brendan Hay
LicenseMozilla Public License, v. 2.0.
MaintainerBrendan Hay <brendan.g.hay+amazonka@gmail.com>
Stabilityauto-generated
Portabilitynon-portable (GHC extensions)
Safe HaskellNone

Amazonka.FraudDetector.GetEventPrediction

Description

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

Synopsis

Creating a Request

data GetEventPrediction Source #

See: newGetEventPrediction smart constructor.

Constructors

GetEventPrediction' 

Fields

  • detectorVersionId :: Maybe Text

    The detector version ID.

  • externalModelEndpointDataBlobs :: Maybe (Sensitive (HashMap Text ModelEndpointDataBlob))

    The Amazon SageMaker model endpoint input data blobs.

  • detectorId :: Text

    The detector ID.

  • eventId :: Text

    The unique ID used to identify the event.

  • eventTypeName :: Text

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

  • entities :: [Sensitive Entity]

    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."

  • eventTimestamp :: Text

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

  • eventVariables :: HashMap Text (Sensitive Text)

    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.

Instances

Instances details
Eq GetEventPrediction Source # 
Instance details

Defined in Amazonka.FraudDetector.GetEventPrediction

Show GetEventPrediction Source # 
Instance details

Defined in Amazonka.FraudDetector.GetEventPrediction

Generic GetEventPrediction Source # 
Instance details

Defined in Amazonka.FraudDetector.GetEventPrediction

Associated Types

type Rep GetEventPrediction :: Type -> Type #

NFData GetEventPrediction Source # 
Instance details

Defined in Amazonka.FraudDetector.GetEventPrediction

Methods

rnf :: GetEventPrediction -> () #

Hashable GetEventPrediction Source # 
Instance details

Defined in Amazonka.FraudDetector.GetEventPrediction

ToJSON GetEventPrediction Source # 
Instance details

Defined in Amazonka.FraudDetector.GetEventPrediction

AWSRequest GetEventPrediction Source # 
Instance details

Defined in Amazonka.FraudDetector.GetEventPrediction

Associated Types

type AWSResponse GetEventPrediction #

ToHeaders GetEventPrediction Source # 
Instance details

Defined in Amazonka.FraudDetector.GetEventPrediction

ToPath GetEventPrediction Source # 
Instance details

Defined in Amazonka.FraudDetector.GetEventPrediction

ToQuery GetEventPrediction Source # 
Instance details

Defined in Amazonka.FraudDetector.GetEventPrediction

type Rep GetEventPrediction Source # 
Instance details

Defined in Amazonka.FraudDetector.GetEventPrediction

type Rep GetEventPrediction = D1 ('MetaData "GetEventPrediction" "Amazonka.FraudDetector.GetEventPrediction" "libZSservicesZSamazonka-frauddetectorZSamazonka-frauddetector" 'False) (C1 ('MetaCons "GetEventPrediction'" 'PrefixI 'True) (((S1 ('MetaSel ('Just "detectorVersionId") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Text)) :*: S1 ('MetaSel ('Just "externalModelEndpointDataBlobs") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe (Sensitive (HashMap Text ModelEndpointDataBlob))))) :*: (S1 ('MetaSel ('Just "detectorId") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 Text) :*: S1 ('MetaSel ('Just "eventId") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 Text))) :*: ((S1 ('MetaSel ('Just "eventTypeName") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 Text) :*: S1 ('MetaSel ('Just "entities") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 [Sensitive Entity])) :*: (S1 ('MetaSel ('Just "eventTimestamp") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 Text) :*: S1 ('MetaSel ('Just "eventVariables") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (HashMap Text (Sensitive Text)))))))
type AWSResponse GetEventPrediction Source # 
Instance details

Defined in Amazonka.FraudDetector.GetEventPrediction

newGetEventPrediction Source #

Create a value of GetEventPrediction with all optional fields omitted.

Use generic-lens or optics to modify other optional fields.

The following record fields are available, with the corresponding lenses provided for backwards compatibility:

$sel:detectorVersionId:GetEventPrediction', getEventPrediction_detectorVersionId - The detector version ID.

$sel:externalModelEndpointDataBlobs:GetEventPrediction', getEventPrediction_externalModelEndpointDataBlobs - The Amazon SageMaker model endpoint input data blobs.

$sel:detectorId:GetEventPrediction', getEventPrediction_detectorId - The detector ID.

$sel:eventId:GetEventPrediction', getEventPrediction_eventId - The unique ID used to identify the event.

$sel:eventTypeName:GetEventPrediction', getEventPrediction_eventTypeName - The event type associated with the detector specified for the prediction.

$sel:entities:GetEventPrediction', getEventPrediction_entities - 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."

$sel:eventTimestamp:GetEventPrediction', getEventPrediction_eventTimestamp - Timestamp that defines when the event under evaluation occurred. The timestamp must be specified using ISO 8601 standard in UTC.

$sel:eventVariables:GetEventPrediction', getEventPrediction_eventVariables - 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.

Request Lenses

getEventPrediction_eventId :: Lens' GetEventPrediction Text Source #

The unique ID used to identify the event.

getEventPrediction_eventTypeName :: Lens' GetEventPrediction Text Source #

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

getEventPrediction_entities :: Lens' GetEventPrediction [Entity] Source #

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."

getEventPrediction_eventTimestamp :: Lens' GetEventPrediction Text Source #

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

getEventPrediction_eventVariables :: Lens' GetEventPrediction (HashMap Text Text) Source #

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.

Destructuring the Response

data GetEventPredictionResponse Source #

See: newGetEventPredictionResponse smart constructor.

Constructors

GetEventPredictionResponse' 

Fields

  • modelScores :: Maybe [ModelScores]

    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.

  • externalModelOutputs :: Maybe [ExternalModelOutputs]

    The model scores for Amazon SageMaker models.

  • ruleResults :: Maybe [RuleResult]

    The results from the rules.

  • httpStatus :: Int

    The response's http status code.

Instances

Instances details
Eq GetEventPredictionResponse Source # 
Instance details

Defined in Amazonka.FraudDetector.GetEventPrediction

Read GetEventPredictionResponse Source # 
Instance details

Defined in Amazonka.FraudDetector.GetEventPrediction

Show GetEventPredictionResponse Source # 
Instance details

Defined in Amazonka.FraudDetector.GetEventPrediction

Generic GetEventPredictionResponse Source # 
Instance details

Defined in Amazonka.FraudDetector.GetEventPrediction

Associated Types

type Rep GetEventPredictionResponse :: Type -> Type #

NFData GetEventPredictionResponse Source # 
Instance details

Defined in Amazonka.FraudDetector.GetEventPrediction

type Rep GetEventPredictionResponse Source # 
Instance details

Defined in Amazonka.FraudDetector.GetEventPrediction

type Rep GetEventPredictionResponse = D1 ('MetaData "GetEventPredictionResponse" "Amazonka.FraudDetector.GetEventPrediction" "libZSservicesZSamazonka-frauddetectorZSamazonka-frauddetector" 'False) (C1 ('MetaCons "GetEventPredictionResponse'" 'PrefixI 'True) ((S1 ('MetaSel ('Just "modelScores") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe [ModelScores])) :*: S1 ('MetaSel ('Just "externalModelOutputs") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe [ExternalModelOutputs]))) :*: (S1 ('MetaSel ('Just "ruleResults") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe [RuleResult])) :*: S1 ('MetaSel ('Just "httpStatus") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 Int))))

newGetEventPredictionResponse Source #

Create a value of GetEventPredictionResponse with all optional fields omitted.

Use generic-lens or optics to modify other optional fields.

The following record fields are available, with the corresponding lenses provided for backwards compatibility:

$sel:modelScores:GetEventPredictionResponse', getEventPredictionResponse_modelScores - 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.

$sel:externalModelOutputs:GetEventPredictionResponse', getEventPredictionResponse_externalModelOutputs - The model scores for Amazon SageMaker models.

$sel:ruleResults:GetEventPredictionResponse', getEventPredictionResponse_ruleResults - The results from the rules.

$sel:httpStatus:GetEventPredictionResponse', getEventPredictionResponse_httpStatus - The response's http status code.

Response Lenses

getEventPredictionResponse_modelScores :: Lens' GetEventPredictionResponse (Maybe [ModelScores]) Source #

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.