Clustering is an unsupervised technique that groups similar examples together — no labels needed.

K-Means Clustering

Most popular clustering algorithm. Assign k cluster centers, assign each point to nearest center, update centers, repeat until stable.

Other Clustering Algorithms

• DBSCAN: Finds arbitrarily shaped clusters, handles noise
• Hierarchical clustering: Builds a dendrogram of nested clusters
• Gaussian Mixture Models: Soft assignment with probabilities

Use Cases

• Customer segmentation
• Document topic grouping
• Anomaly detection
• Image compression

Reference:

scikit-learn clustering guide

https://scikit-learn.org/stable/modules/clustering.html