Pages: [1]
  Print  
Author Topic: Threshold Cutoff  (Read 762 times)
AB26511
Newbie
*
Posts: 13


« on: October 04, 2012, 12:45:46 PM »

Hi Team,

When the result of any Binary dependent variable is produced the Threshold Cutoff is 50%.  For example consider simple Customer churn model, in this if the Confidence Y is above 0.5 means the Customer will churn & Confidence N above 50% means Customer will not churn. Is it possible to change this Threshold Cutoff from 50% to any other required Percentage?

Please advice,


Thanks,
Amit
Logged
Marius
Administrator
Hero Member
*****
Posts: 1753



WWW
« Reply #1 on: October 08, 2012, 10:46:44 AM »

Yes. The simplest way is Create Threshold in combination with Apply Threshold (apply that operator on a dataset with confidence values, i.e. after Apply Model).
There are more sophisticated ways to change the threshold, e.g. Select Recall, MetaCost or Find Threshold.

Happy Mining!
~Marius
Logged

Please add [SOLVED] to the topic title when your problem has been solved! (do so by editing the first post in the thread and modifying the title)
Please click here before posting.
Pages: [1]
  Print  
 
Jump to: