---
sourceDocument: Xanadu Enable AI
sourceDocumentLink: https://servicenow-prod.fluidtopics.net/r/xanadu/intelligent-experiences

 Release :

    - xanadu

ft:locale :

    - en-US

ft:publication_title :

    - Xanadu Enable AI

ft:clusterId :

    - platai

bundleId :

    - platai

workflow :

    - Platform


---

# Apply purity on a clustering solution

# Apply purity on a clustering solution {#ariaid-title1}

* Release version: Xanadu
* 
* Updated June 26, 2025
* 
* ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 1 minute to read

Apply purity to learn details about the composition of each cluster. For example, see what percentage of incidents in a cluster have the same value for Assignment Group. You can specify which fields to focus on, or you can let
auto-purity display fields by default.

## Before you begin

* Create a clustering definition solution or use an existing one.
* Role required: admin or ml_admin
{#configure-auto-purity-cluster__ul_thb_xbz_nnb}

## About this task

With purity, you can choose field distribution metrics for your clusters to display. The table assigned to your solution determines which fields are available. For more information about purity, see the following articles on ServiceNow Community:

* <https://www.servicenow.com/community/intelligence-ml-articles/using-purity-fields-to-better-understand-your-clusters/ta-p/2302441>
* <https://www.servicenow.com/community/intelligence-ml-articles/predictive-intelligence-using-the-cluster-insight-table-to/ta-p/2301006>

If you do not select any fields, auto-purity automatically determines which insights to show based on distribution significance.
You can change the default auto-purity selections by editing the ML Auto Purity Configuration
\[ml_autopurity_config\] table.

## Procedure

1. Navigate to AllPredictive IntelligenceClusteringSolution Definitions.
2. Select a solution definition or create a new one.
3. Select the Calculate Purity check box.
4. **Optional:** Select the Purity Fields lock icon and choose the fields that you want displayed in cluster results.  
   Note:  
   If you don't select any fields, auto-purity displays the most significant fields based on distribution.
5. Select Update or Update \& Retrain.

## Result

View your insights by opening the Cluster Visualization tab of your retrained solution, then pointing to a cluster. Under Purity based on, the format displays as:

field name : value : percent.
For example, the row priority : 5 : 100% means that 100% of the members of this cluster have the value of 5 for the priority field.

*[\>]: and then