Updating Scoring Criteria (Discover)
What's on this page
About Updating Scoring Criteria
You can make edits to both the scoring model underlying your scoring and the rubric itself. This page compiles best practices and resources you can use as you evolve your scoring criteria.
Best Practices for Editing Scoring Models
When editing a category model that is being used for intelligent scoring, keep the following recommendations in mind.
Deleting topics referenced in a rubric
To make sure you’ve completely deleted a topic (or “node”) being used in a rubric:
Editing topics references in a rubric
To safely edit a topic referenced in a rubric:
Adding new topics to a tree referenced in a rubric
To add a new topic to a category tree referenced in a rubric:
Updating a Rubric
As your Quality Management program evolves, you may want to make changes to your rubric. For example, you may want to add or remove criteria, edit weights, or edit the target score.
Rescoring Historical Data
To apply intelligent scoring to historical data (i.e., existing data collected before the rubric was created), you need to rescore the data.
FAQs
What is a category model? What is a topic?
What is a category model? What is a topic?
Since category models are how XM Discover analyzes topics, you will see “category model” and “topic” used interchangeably throughout the platform.
What is a node?
What is a node?
For example, your category tree may be Airline Journey, and includes topics like Booking Functionality, Payment, Upgrades, and more, which all might have topics underneath them, as well. Each branching topic is a node. “Airline Journey” would be the root node.
If I updated the scoring model's topmost topic (root node), but didn’t update my existing (historical) data, will classification be performed on my existing data automatically?
If I updated the scoring model's topmost topic (root node), but didn’t update my existing (historical) data, will classification be performed on my existing data automatically?
That's great! Thank you for your feedback!
Thank you for your feedback!