If you use the Ensemble node in SAS Visual Data Mining and Machine Learning, the DS2 Package Code (dmcas_pacakgescorecode.sas) could be incorrectly generated. 

In order to determine whether the code was incorrectly generated, complete the following steps:

1. Search for the following in the DS2 Package Code:

Note that "P_<TargetVariable><TargetEvent>" should contain a format that is similar to the following:

2. Then, compare this section of the DS2 Package Code with the similar section in the Path EP Score Code (dmcas_epscorecode.sas). If any difference are present, then the DS2 Package Code was incorrectly generated. The corresponding code block in the Path EP Score Code (dmcas_epscorecode.sas) is correct.

Note: If you eventually publish this model to maslocal or any other container-type destinations or use this model in a decision, wrong results are produced.

Workaround

To circumvent this issue, register this model into a model repository. Then, use SAS^® Model Manager to manually correct the corresponding DS2 Package Code (dmcas_packagescorecode.sas) before you publish or use the model.

Click the Hot Fix tab in this note for a link to instructions about accessing and applying the software update.

Note: The hot fix cannot correct the models that already contain this issue. The hot fix corrects only the future models that are built by SAS Visual Data Mining and Machine Learning.

Operating System and Release Information

Viya on Windows: An update for this issue is available for SAS Viya 3.5. For instructions on how to access and apply software updates, see the Updating Your SAS Viya software section in the SAS Viya 3.5 for Windows Deployment Guide at

Viya on Linux: An update for this issue is available for SAS Viya 3.5. For instructions on how to access and apply software updates, see the Updating Your SAS Viya software section in the SAS Viya 3.5 for Linux Deployment Guide at