MLPredictionDefinition

Represents a prediction definition that specifies details about the prediction.

Where possible, we changed noninclusive terms to align with our company value of Equality. We maintained certain terms to avoid any effect on customer implementations.

Important

Parent Type 

This type extends Metadata and inherits its fields.

File Suffix and Directory Location 

MLPredictionDefinition components have the suffix .mlPrediction and are stored in the mlPredictions folder.

Version 

Introduced in API version 50.0.

Fields 

aiApplicationDeveloperName 

• Type: string
• Required: Yes
• Description: Required. Represents the developer name of the parent AI application. Can contain only underscores and alphanumeric characters and must be unique in your org. It must begin with a letter, not include spaces, not end with an underscore, and not contain two consecutive underscores.

description 

• Type: string
• Required: No
• Description: Description of the prediction.

developerName 

• Type: string
• Required: Yes
• Description: Required. Represents the name of the prediction definition. Can contain only underscores and alphanumeric characters and must be unique in your org. It must begin with a letter, not include spaces, not end with an underscore, and not contain two consecutive underscores.

Only users with View DeveloperName OR View Setup and Configuration permission can view, group, sort, and filter this field.

Note

masterLabel 

• Type: string
• Required: No
• Description: Label that identifies the ML prediction definition throughout the Salesforce user interface.

negativeExpression 

• Type: MLFilter
• Required: No
• Description: Reserved for future use.

positiveExpression 

• Type: MLFilter
• Required: No
• Description: Reserved for future use.

predictionField 

• Type: string
• Required: No
• Description: Field that the prediction is based on.

priority 

• Type: int
• Required: No
• Description: Reflects the priority of the MLPD object when an AIApplication has multiple child MLPDs. Nillable.

pushbackField 

• Type: string
• Required: No
• Description: Field that the prediction writes scores to.

status 

• Type: MLPredictionDefinitionStatus (enumeration of type string)
• Required: Yes
• Description: Required. The status of the prediction.
• Possible values:
  • Enabled
  • Disabled
  • Draft

type 

• Type: AIPredictionType (enumeration of type string)
• Required: Yes
• Description: Required. The type of model that returns the prediction values.
• Possible values:
  • BinaryClassification
  • DeepLearningIntentClassification
  • DeepLearningNameEntityRecognition
  • GlobalDeepLearningIntentClassification
  • GlobalDeepLearningNameEntityRecognition
  • LanguageDetection
  • MulticlassClassification
  • Regression
  • ScoringSpecificOutcome

MLFilter Type 

Fields 

filterName 

• Type: string
• Required: Yes

lhFilter 

• Type: MLFilter
• Required: No

lhPredictionField 

• Type: string
• Required: No

lhType 

• Type: AIValueType (enumeration of type string)
• Required: No

lhUnit 

• Type: AIFilterUnit (enumeration of type string)
• Required: No

lhValue 

• Type: string
• Required: No

operation 

• Type: AIFilterOperation (enumeration of type string)
• Required: Yes

rhFilter 

• Type: MLFilter
• Required: No

rhPredictionField 

• Type: string
• Required: No

rhType 

• Type: AIValueType (enumeration of type string)
• Required: No

rhUnit 

• Type: AIFilterUnit (enumeration of type string)
• Required: No

rhValue 

• Type: string
• Required: No

sortOrder 

• Type: int
• Required: No
• Description: The display order of this component relative to sibling components. Lower values appear first.

Wildcard Support in the Manifest File 

This metadata type supports the wildcard character * (asterisk) in the package.xml manifest file. For information about using the manifest file, see Deploying and Retrieving Metadata with the Zip File.