---
sourceDocument: Zurich Customer Service Management
sourceDocumentLink: https://www.servicenow.com/docs/r/zurich/customer-service-management

 Release :

    - zurich

ft:locale :

    - en-US

ft:publication_title :

    - Zurich Customer Service Management

ft:clusterId :

    - csm

bundleId :

    - csm

workflow :

    - Customer and Industry


---

# Configure trending case topics

# Configure trending case topics {#ariaid-title1}

* Release version: Zurich
* 
* Updated July 31, 2025
* 
* ![](https://www.servicenow.com/docs/portal-asset/ico-clock) 1 minute to read

Train solution definitions to identify clusters of cases that point to similar
underlying issues and find any related major cases for the clusters.

## Before you begin

Role required: admin

## About this task

Access the menus and use the modules to train the solution definitions to identify
trending case topics. For more details, see [Trending case topics](https://www.servicenow.com/docs/NkTiCQW1CbXRgqvk6m1Hug "Resolve cases more efficiently and proactively using Predictive Intelligence to identify clusters of cases with similar issues and pinpoint factors that drive up case volume. Each cluster of cases represents a trending case topic.").

## Procedure

1. Navigate to Predictive Intelligence and then either AllSimilaritySolution Definitions or ClusteringSolution Definitions.
2. Complete the following tasks to train the solution definitions for trending case topics.  
   {#configure-trending-topics__table_ikt_fvp_qlb__entry__2}

   | Task | Description |
   |-|-|
   | Train the clustering solution definition to automatically group similar cases into topics | Configure a clustering solution definition to cluster similar cases into groups. |
   | Train the similarity solution definition to find similar existing major cases | Configure a similarity solution definition to find similar major cases for the clusters. |
   [Table 1. Solution definitions field description]

   {#configure-trending-topics__table_ikt_fvp_qlb}
{#configure-trending-topics__steps_tqx_qqj_tlb}

*[\>]: and then