BookmarkSubscribeRSS Feed
omerzeybek
Obsidian | Level 7

Hi

Score codes i created by using logistic regression returns with same probablities for every indvidual case when i ran them on test data. It gives perfect scores when ran on training and validation data

What could be the problem

Thank you very much

2 REPLIES 2
Reeza
Super User

Log and/or sample code? Hard to say otherwise.

rayIII
SAS Employee

Do you have a constant-only model? That would give you the same predicted value for every observation.

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
  • 2 replies
  • 1719 views
  • 0 likes
  • 3 in conversation