Copyright	(c) 2013-2023 Brendan Hay
License	Mozilla Public License, v. 2.0.
Maintainer	Brendan Hay
Stability	auto-generated
Portability	non-portable (GHC extensions)
Safe Haskell	Safe-Inferred
Language	Haskell2010

Amazonka.FraudDetector.Types.VariableImpactExplanation

Description

Documentation

data VariableImpactExplanation Source #

The details of the event variable's impact on the prediction score.

See: newVariableImpactExplanation smart constructor.

Constructors

VariableImpactExplanation'

Fields

eventVariableName :: Maybe Text
The event variable name.
logOddsImpact :: Maybe Double
The raw, uninterpreted value represented as log-odds of the fraud. These values are usually between -10 to +10, but range from - infinity to + infinity.
- A positive value indicates that the variable drove the risk score up.
- A negative value indicates that the variable drove the risk score down.
relativeImpact :: Maybe Text
The event variable's relative impact in terms of magnitude on the prediction scores. The relative impact values consist of a numerical rating (0-5, 5 being the highest) and direction (increased/decreased) impact of the fraud risk.

Instances

Instances details

FromJSON VariableImpactExplanation Source #
Instance details Defined in Amazonka.FraudDetector.Types.VariableImpactExplanation Methods parseJSON :: Value -> Parser VariableImpactExplanation # parseJSONList :: Value -> Parser [VariableImpactExplanation] #
Generic VariableImpactExplanation Source #
Instance details Defined in Amazonka.FraudDetector.Types.VariableImpactExplanation Associated Types type Rep VariableImpactExplanation :: Type -> Type # Methods from :: VariableImpactExplanation -> Rep VariableImpactExplanation x # to :: Rep VariableImpactExplanation x -> VariableImpactExplanation #
Read VariableImpactExplanation Source #
Instance details Defined in Amazonka.FraudDetector.Types.VariableImpactExplanation Methods readsPrec :: Int -> ReadS VariableImpactExplanation # readList :: ReadS [VariableImpactExplanation] # readPrec :: ReadPrec VariableImpactExplanation # readListPrec :: ReadPrec [VariableImpactExplanation] #
Show VariableImpactExplanation Source #
Instance details Defined in Amazonka.FraudDetector.Types.VariableImpactExplanation Methods showsPrec :: Int -> VariableImpactExplanation -> ShowS # show :: VariableImpactExplanation -> String # showList :: [VariableImpactExplanation] -> ShowS #
NFData VariableImpactExplanation Source #
Instance details Defined in Amazonka.FraudDetector.Types.VariableImpactExplanation Methods rnf :: VariableImpactExplanation -> () #
Eq VariableImpactExplanation Source #
Instance details Defined in Amazonka.FraudDetector.Types.VariableImpactExplanation Methods (==) :: VariableImpactExplanation -> VariableImpactExplanation -> Bool # (/=) :: VariableImpactExplanation -> VariableImpactExplanation -> Bool #
Hashable VariableImpactExplanation Source #
Instance details Defined in Amazonka.FraudDetector.Types.VariableImpactExplanation Methods hashWithSalt :: Int -> VariableImpactExplanation -> Int # hash :: VariableImpactExplanation -> Int #
type Rep VariableImpactExplanation Source #
Instance details Defined in Amazonka.FraudDetector.Types.VariableImpactExplanation type Rep VariableImpactExplanation = D1 ('MetaData "VariableImpactExplanation" "Amazonka.FraudDetector.Types.VariableImpactExplanation" "amazonka-frauddetector-2.0-CdXFXtLV8DgKo4Kta7Jw61" 'False) (C1 ('MetaCons "VariableImpactExplanation'" 'PrefixI 'True) (S1 ('MetaSel ('Just "eventVariableName") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Text)) :: (S1 ('MetaSel ('Just "logOddsImpact") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Double)) :: S1 ('MetaSel ('Just "relativeImpact") 'NoSourceUnpackedness 'NoSourceStrictness 'DecidedStrict) (Rec0 (Maybe Text)))))

newVariableImpactExplanation :: VariableImpactExplanation Source #

Create a value of VariableImpactExplanation 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:eventVariableName:VariableImpactExplanation', variableImpactExplanation_eventVariableName - The event variable name.

$sel:logOddsImpact:VariableImpactExplanation', variableImpactExplanation_logOddsImpact - The raw, uninterpreted value represented as log-odds of the fraud. These values are usually between -10 to +10, but range from - infinity to + infinity.

A positive value indicates that the variable drove the risk score up.
A negative value indicates that the variable drove the risk score down.

$sel:relativeImpact:VariableImpactExplanation', variableImpactExplanation_relativeImpact - The event variable's relative impact in terms of magnitude on the prediction scores. The relative impact values consist of a numerical rating (0-5, 5 being the highest) and direction (increased/decreased) impact of the fraud risk.

variableImpactExplanation_eventVariableName :: Lens' VariableImpactExplanation (Maybe Text) Source #

The event variable name.

variableImpactExplanation_logOddsImpact :: Lens' VariableImpactExplanation (Maybe Double) Source #

The raw, uninterpreted value represented as log-odds of the fraud. These values are usually between -10 to +10, but range from - infinity to + infinity.

A positive value indicates that the variable drove the risk score up.
A negative value indicates that the variable drove the risk score down.

variableImpactExplanation_relativeImpact :: Lens' VariableImpactExplanation (Maybe Text) Source #

The event variable's relative impact in terms of magnitude on the prediction scores. The relative impact values consist of a numerical rating (0-5, 5 being the highest) and direction (increased/decreased) impact of the fraud risk.