Clustering Skill
Group data points into clusters based on similarity. Use this skill when users want to segment their data, identify customer groups, find similar patterns, or discover natural groupings in their analytics data.
Experimental Feature
This is an experimental feature that is still under active development. Its behavior may change in future releases, or the feature may be removed.
How It Works
The Clustering skill uses machine learning algorithms to group data points based on similarity across multiple dimensions. When activated, the assistant:
- Uses the Visualization skill to prepare the data
- Executes clustering algorithms to identify groups
- Assigns data points to clusters based on similarity
- Creates visualizations showing the clusters
- With data sharing enabled, provides meaningful segment labels and summaries
The skill helps you discover natural groupings in your data that might not be immediately obvious, enabling targeted analysis and action for each segment.
Examples
Customer segmentation:
User: "Group our customers into segments"
Assistant: [Runs clustering, creates visualization, labels customer segments]Product clustering:
User: "Find similar products based on sales patterns"
Assistant: [Clusters products, visualizes groups, explains segment characteristics]Regional analysis:
User: "What are the main clusters in our regional performance?"
Assistant: [Groups regions by similarity, shows clusters, provides insights]Other use cases:
- “Find similar customer profiles”
- “Group products by similarity”
- “Find groups of similar regions”
- “Cluster our stores by performance patterns”
Limitations
- Requires the Visualization skill as a dependency
- Clustering works best with multiple dimensions and sufficient data points
- Results interpretation requires data sharing to be enabled
- Cluster quality depends on the data distribution and chosen metrics