Zubnet AILearnWiki › Clustering
Fundamentals

Clustering

K-Means, DBSCAN, Cluster Analysis
An unsupervised learning task that groups similar data points together without predefined labels. Given customer purchase data, clustering might discover distinct customer segments (bargain hunters, luxury buyers, occasional shoppers). K-means is the most common algorithm: choose K clusters, assign each point to the nearest cluster center, and iteratively refine the centers.

Why it matters

Clustering is the most common unsupervised learning task and appears everywhere: customer segmentation, document grouping, anomaly detection (outliers that don't fit any cluster), image compression (grouping similar pixels), and data exploration (what natural groups exist in my data?). It's often the first step in understanding a new dataset.

Deep Dive

K-means works by: (1) randomly initializing K cluster centers, (2) assigning each data point to the nearest center, (3) moving each center to the mean of its assigned points, (4) repeating steps 2–3 until convergence. The main challenge: choosing K. The "elbow method" (plot loss vs. K and find the bend) and silhouette scores are common heuristics, but the right number of clusters often requires domain knowledge.

Beyond K-Means

DBSCAN discovers clusters of arbitrary shapes (K-means assumes spherical clusters) and automatically identifies outliers as noise points. Hierarchical clustering builds a tree of nested clusters that you can cut at any level. Gaussian Mixture Models (GMMs) model clusters as probability distributions, allowing soft assignments (a point can partially belong to multiple clusters). Each method has strengths for different data geometries and use cases.

Clustering with Embeddings

Combining embeddings with clustering is powerful for text analysis. Embed a collection of documents using a sentence embedding model, then cluster the embeddings. Each cluster represents a semantic group — topics, themes, or categories that emerge from the data. This is used for: organizing support tickets by topic, discovering themes in survey responses, grouping similar products, and topic modeling (a modern alternative to LDA). The clusters can then be labeled by asking an LLM to summarize what each cluster is about.

Related Concepts

← All Terms
← CLIP CNN →