BookmarkSubscribeRSS Feed
jcristin
Calcite | Level 5

Hello All,

I'm starting with SAS EM. I'm trying to build a classification model to predict the best candidates for a product campaign. I built 3 types of models, NN, Regression and Decision Trees - the selected model was a NN one. However when I run the score node, only the Decision Tree models are able to predict. Other models give always the target var 100% -> 0. 


Any help would be highly appreciated!

 

Jorge

1 REPLY 1
gcjfernandez
SAS Employee

Because your response rate very rare (< 0.05%), try a balanced sample (50% response 50% non-response) and check whether you still have problem with NN node scoring. You can always use the decision node to correct it for prior probability.

Catch up on SAS Innovate 2026

Nearly 200 sessions are now available on demand with the SAS Innovate Digital Pass.

Explore Now →
How to choose a machine learning algorithm

Use this tutorial as a handy guide to weigh the pros and cons of these commonly used machine learning algorithms.

Find more tutorials on the SAS Users YouTube channel.

Discussion stats
  • 1 reply
  • 2003 views
  • 0 likes
  • 2 in conversation