Skip to main content

This content is closed to future replies and is no longer being maintained or updated.
Links may no longer function. If you have a similar request, please write a new post.

Question

 Ransom Wikoff (RansomW3)

US
RansomW3 Member since 2020 3 posts
Posted: Jan 28, 2020
Last activity: Jan 29, 2020
Posted: 28 Jan 2020 10:13 EST
Last activity: 29 Jan 2020 13:30 EST
Closed

Reclassifying Results Classes When Creating Predictive Models

Hello,

When creating a predictive model in Pega Prediction Studio, what is the best method to reclassify the result classes? Is it just based on the behavioral line in the original results graph?

Thanks!

To see attachments, please log in.
Pega Customer Decision Hub
Decision Management

Posted: 4 years ago
Posted: 29 Jan 2020 13:30 EST
Peter van der Putten (Peter van der Putten)
PEGA
Lead Scientist and Director, AI Lab, Office of the CTO
Pegasystems Inc.
NL

if you are unsure about the future usage of the model, just leave the original amount of classes to have maximum discrimination. You'd probably only want to remap if as a data scientist you want to be very prescriptive on what smaller number of classes to use (and yes behavior and volume would be main indicators). So default dont map.

To see attachments, please log in.

We'd prefer it if you saw us at our best.

Pega Collaboration Center has detected you are using a browser which may prevent you from experiencing the site as intended. To improve your experience, please update your browser.

Close Deprecation Notice