Back to Glossary
BasicsAI Glossary

Unsupervised Learning

Quick Answer

Unsupervised learning is a machine learning approach where the model learns patterns and structure from unlabelled data. Rather than predicting a known target, it uncovers groupings, anomalies or compressed representations hidden in the data.

In Depth

What Unsupervised Learning really means

Common unsupervised methods include clustering (grouping similar items), dimensionality reduction (compressing data for visualisation or downstream tasks), and anomaly detection (flagging unusual items).

Unsupervised learning is particularly useful in the early stages of data exploration, when labels are expensive to gather, or for discovering novel patterns that humans have not yet categorised.

Why It Matters

Business relevance for UK organisations

Marketing teams use unsupervised learning to discover customer segments; security teams use it to detect unusual login behaviour; operations teams use it to surface anomalies in sensor data from machinery or vehicles.

Real-world example

How this shows up in practice

An Edinburgh energy supplier applied unsupervised clustering to smart-meter data and discovered six distinct customer usage profiles, enabling more targeted tariff recommendations.