ENSEMBLES Subcommand (LINEAR command)

The ENSEMBLES subcommand determines the behavior of ensembling that occurs when boosting, bagging, or very large datasets are requested on the OBJECTIVE keyword. Options that do not apply to the selected objective are ignored.

COMBINING_RULE_CONTINUOUS = MEAN** | MEDIAN. Ensemble predicted values for continuous targets can be combined using the mean or median of the predicted values from the base models.

Note that when the objective is to enhance model accuracy (BAGGING), the combining rule selections are ignored. Boosting always uses a weighted majority vote to score categorical targets and a weighted median to score continuous targets.

COMPONENT_MODELS_N = 10** | integer. Specify the number of base models to build when the objective is to enhance model accuracy or stability; for bagging, this is the number of bootstrap samples. It should be a positive integer.