BookmarkSubscribeRSS Feed
☑ This topic is solved. Need further help from the community? Please sign in and ask a new question.
anniewong
Calcite | Level 5

A similar feature is available in the “Build Model” module on the Learner platform, but it isn’t supported in the Flow or in the SAS code version.

This makes me less inclined to learn SAS code, especially when Python libraries make grid-search hyperparameter tuning so much easier. I believe hyperparameter tuning is absolutely essential from a data-science perspective.

And some basic function for oversampling build in function is missing . How SAS handling such kind of imbalance data? 

 

 

1 ACCEPTED SOLUTION

Accepted Solutions
antonbcristina
SAS Super FREQ

Hi @anniewong, autotuning is disabled in Viya for Learners because this is a teaching and learning platform that seeks to support 7,000 users a month, globally and autotuning is resource intensive and affects the performance for other users by utilizing a LOT of resources.

 

We have a very low-cost SAS Viya option available for academics that has autotuning enabled. If you are interested in learning more, please contact academic@sas.com.

View solution in original post

1 REPLY 1
antonbcristina
SAS Super FREQ

Hi @anniewong, autotuning is disabled in Viya for Learners because this is a teaching and learning platform that seeks to support 7,000 users a month, globally and autotuning is resource intensive and affects the performance for other users by utilizing a LOT of resources.

 

We have a very low-cost SAS Viya option available for academics that has autotuning enabled. If you are interested in learning more, please contact academic@sas.com.

sas-innovate-white.png

Missed SAS Innovate in Orlando?

Catch the best of SAS Innovate 2025 — anytime, anywhere. Stream powerful keynotes, real-world demos, and game-changing insights from the world’s leading data and AI minds.

 

Register now

SAS Training: Just a Click Away

 Ready to level-up your skills? Choose your own adventure.

Browse our catalog!

Discussion stats
  • 1 reply
  • 661 views
  • 1 like
  • 2 in conversation