PROC ASTORE DESCRIBE is run on a deployed model. What information is returned in the PROC ASTORE DESCRIBE output?
Select an answer to reveal the explanation.
Short Explanation
Here's the deal — PROC ASTORE DESCRIBE reads the ASTORE metadata and shows the input variable names, types, and roles the model expects for scoring, plus the output variables it will produce. That lets you validate your scoring data before deployment.
Full Explanation
PROC ASTORE DESCRIBE reads the ASTORE metadata and returns the input variable names, types, and roles, such as input, target, and rejected, expected for scoring, plus output variables produced during scoring, so you can validate scoring data before deployment. Coefficient estimates and standard errors for each input variable are not extracted by DESCRIBE for most procedures. Training performance metrics such as AUC, KS, and Gini are not stored in the ASTORE. The original SAS training code cannot be reconstructed from the ASTORE binary.