Regression Tree
A PMML regression tree model predicts the value of a numeric-dependent variable (such as the price of a house) from one or more independent variables. It does this by building a decision tree model that is based on one or more predictors.
Model Element
<TreeModel functionName="regression" ...
Unsupported Features
Regression trees with integer or float target fields are not supported unless a <Targets> element is specified with the appropriate castInteger attribute.
Regression tree models with the <MiningSchema> element containing a reference to a <DerivedField> element are not supported.
Model Outputs
By default the target field will be available as an output field - this is a synonym for the predictedValue feature. Float target fields will always be cast to integer.
Supported Model Output Features | Description |
---|---|
predictedValue | The numeric dependent variable that we are predicting. |
transformedValue | A value generated via a transformation expression applied to the predicted model output. |
decision | A value generated via an expression applied to the predicted model output resulting in a categorized value. |
entityId | If present, the ID of the tree node of the predicted result. |