---
schema_version: "1"
id: f29fc2e37845dcd212882b3a8f86c7e4a6753a7908f2ac2062c6b45a6638ada1
title: Use Related Data Objects to Build Richer Clusters
collection: admin
version: current
locale: en-us
portal_url: https://docs.salesforce.com/admin/current/en-us/release-notes/264-0-0/rn_cdp_2026_winter_predictive_model_clustering_objects.md
canonical_url: https://help.salesforce.com/s/articleView?id=release-notes.rn_cdp_2026_winter_predictive_model_clustering_objects.htm&release=264.0.0&type=5
source_site: help.salesforce.com
content_type: documentation
content_hash: 2269f8710c7a4a886f46987877b45984c1c23a9f2b2172873667991e3643e671
description: Build richer clusters to enrich customer profiles, identify similar accounts or products, or provide variables for downstream models. Select a data model object (DMO) as the primary data source and add variables from related DMOs and calculated insight objects (CIOs). Alternatively, use a CIO as the primary data source.
products:
  - Cross Cloud
release: "264"
---
# Use Related Data Objects to Build Richer Clusters

Build richer clusters to enrich customer profiles, identify similar accounts or products, or provide variables for downstream models. Select a data model object (DMO) as the primary data source and add variables from related DMOs and calculated insight objects (CIOs). Alternatively, use a CIO as the primary data source.

**Where:** This change applies to Lightning Experience in Enterprise, Performance, Unlimited, and Developer editions with Data 360.

**When:** This feature is available starting in September 2026.

**Why:** Combine attributes from related objects to uncover patterns that aren’t apparent when you analyze individual fields. Unlike clustering that generates new clusters on every run, a trained model retains its cluster definitions, and consistently assigns new records to the same groups. Label each cluster, review confidence scores and top contributing factors, and apply the results across Salesforce.

**How:** In Data Cloud, go to the AI Models tab and select **Cluster**. Choose a cluster model, select your source DMO or CIO, and choose the fields you want to analyze. Configure and train the model, then assign descriptive labels to your clusters.