Clustering

Fact

An unsupervised method that automatically groups data by similarity.

In Plain Words

Clustering is like a messy sock drawer sorting itself. Striped socks find striped socks. Fuzzy socks form a tiny club.

It groups messy data before anyone names the groups. You meet it in customer groups, weird-point alerts, and photo sorting.

Related Concepts

• Unsupervised Learning
• Classification Task
• Gaussian Mixture Model
• Dimensionality Reduction

Unsupervised Learning
Clustering is a classic Unsupervised Learning task with no labels.

Classification
Classification uses known labels, but clustering makes groups first.

GMM
GMM is a common probability-based way to do clustering.

Dim. Reduction
Dim. Reduction can spread data out before clustering.