The HPNEURAL Procedure

SCORE Statement

SCORE OUT=SAS-data-set <MODEL=SAS-data-set> ;

The SCORE statement causes the HPNEURAL procedure to write the network’s target and predicted output for each observation in the input data set to the output data set that is specified by the OUT option, along with any variables from the input data set that are specified in the ID statement.

OUT=SAS-data-set: specifies the data set to contain the predicted values of the target variables. For nominal variables, each observation also contains the computed probabilities of each class level. This keyword is required.
MODEL=SAS-data-set: specifies the data set that contains the model parameters for a previously trained network. You can specify this keyword only when you are doing stand-alone scoring.

When you are training, the SCORE statement is optional but the MODEL= keyword is not allowed. When you are doing stand-alone scoring, the SCORE statement is required and the MODEL= keyword must be used.

Last updated: May 25, 2022