In SAS Model Manager, when a data scientist publishes a model to the 'SAS Micro Analytic Service' destination, which score code format is required?
Select an answer to reveal the explanation.
Short Explanation
Here's the deal — you need a DS2 package containing a score method because SAS Micro Analytic Service executes DS2 programs. When you publish to MAS from SAS Model Manager, the score code must be DS2 with a score() method that takes inputs and returns predictions.
Full Explanation
The DS2 package containing a score method is correct because SAS Micro Analytic Service (MAS) executes DS2 programs. When publishing to MAS from SAS Model Manager, the score code must be in DS2 format — specifically a DS2 package with a score() method that accepts input variables and returns output predictions. The Python (.py) scoring function is supported by a different publishing destination, such as a Python Wrapper or SAS Viya Python endpoint. The SAS DATA step score code (.sas file) can be used for other destinations like CAS or file-based scoring. The PMML (Predictive Model Markup Language) XML file is supported by specific PMML scoring engines, not MAS.