Hi everyone - hope you can help with a quick solution.
I looked through existing topics, and found relevant, but when trying to apply it in Miner, still have an issue to produce a decision tree.
here is what i try to do:
I have a dataset with binary target variable (default indicator: 1 or 0) and an interval (numeric) variable 'time on books' that goes from 0, 1, 2 ... up to ~300 and represents months on books.
In Miner, I want to build a simple decision tree that have a maximum depth: 1, and maximum branch: 3 - so just splitting 'time on books' into 3 nodes.
the issue is:
Once i set up constraints, such as branch, depth, node leaf size, etc..., and once "Run" decision tree i do not have any split for the "Input" variable, but only keeping a "root node" with information on how many are in 0 and 1 groups.
I tried "Interactive Binning" and "Transform Variables" to have this input variable either binned or transformed, but not luck.
If anyone had same issue, i must have doing something wrong in the setup, because i can create simple decision trees for other variable i have, but struggling with "time on books" and another character nominal variable.
Any help highly appreciated!
Moved to data mining community
Available on demand!
Missed SAS Innovate Las Vegas? Watch all the action for free! View the keynotes, general sessions and 22 breakouts on demand.
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.