--- schema_version: "1" id: 331a2e48aeef01f749f06888f65c19248f32aae37812695c595f33589b497913 title: MLModel collection: legacydeveloper version: current locale: en-us portal_url: https://docs.salesforce.com/legacydeveloper/current/en-us/object_reference/sforce_api_objects_mlmodel.md canonical_url: https://developer.salesforce.com/docs/atlas.en-us.object_reference.meta/object_reference/sforce_api_objects_mlmodel.htm source_site: developer.salesforce.com content_type: documentation content_hash: 1e94d2fa0ad5b2bbc6f52abe1e0f25fb5bda0f17ed94665215e56106c9462ff4 description: Represents an AI model that can be used in Einstein Prediction Builder, Einstein Recommendation Builder, and other Einstein features. This object is available in API version 53.0 and later. --- # MLModel Represents an AI model that can be used in Einstein Prediction Builder, Einstein Recommendation Builder, and other Einstein features. This object is available in API version 53.0 and later. This object contains information that represents many types of AI models. Some fields contain information for only a specific type of model. ## Supported Calls describeSObjects(), getDeleted(), getUpdated(), query(), retrieve() ## Special Access Rules Available with Einstein Prediction Builder and Einstein Recommendation Builder. ## Fields | Field | Details | | --- | --- | | ApprovalStatus | Type picklist Properties Defaulted on create, Filter, Group, Nillable, Restricted picklist, Sort Description Indicates whether the model is approved, pending approval, or rejected. Possible values are: - Approved - Pending - Rejected The default value is Pending. | | Dataset | Type string Properties Filter, Group, Nillable, Sort Description The ID of the dataset used to create the model. | | ModelType | Type picklist Properties Filter, Group, Nillable, Restricted picklist, Sort Description Indicates the type of model. Possible values are: - BinaryClassification - DecisionTree - DeepLearningIntent - DeepLearningNER - GeneralizedLinearModels - GlobalDeepLearningIntent - GlobalDeepLearningNER - GlobalLanguageDetection - GradientBoostedTrees - LinearRegression - LinearSupportVectorClassifiers - LogisticRegression - MulticlassClassification - NaiveBayes - NeuralNet - PopularityCount - RandomForest - Regression - XGBoost | | Name | Type string Properties Autonumber, Defaulted on create, Filter, idLookup, Sort Description The automatically generated ID that uniquely identifies the model. | | PredictionDefinitionId | Type reference Properties Filter, Group, Nillable, Sort Description The ID of the related prediction definition. This field is a relationship field. Relationship Name PredictionDefinition Relationship Type Lookup Refers To MLPredictionDefinition | | RecommendationDefinitionId | Type reference Properties Filter, Group, Nillable, Sort Description The ID of the related recommendation definition. This field is a relationship field. Relationship Name RecommendationDefinition Relationship Type Lookup Refers To MLRecommendationDefinition | | ScoringStatus | Type picklist Properties Filter, Group, Restricted picklist, Sort Description Indicates whether scoring is enabled or disabled. Possible values are: - Disabled - Enabled | | TrainingEndTime | Type dateTime Properties Filter, Nillable, Sort Description Indicates the date and time when the training ended. | | TrainingStartTime | Type dateTime Properties Filter, Nillable, Sort Description Indicates the date and time when the training started. |