Back to Glossary
AdvancedAI Glossary

Classification

Quick Answer

Classification is a supervised learning task where the model assigns inputs to one of a predefined set of categories. Binary classification distinguishes between two classes; multi-class and multi-label variants handle more complex labelling problems.

In Depth

What Classification really means

Classification underlies spam filtering, fraud detection, medical diagnosis support, content moderation, support ticket routing and many other workaday AI systems. Key metrics include accuracy, precision, recall, F1 and — crucially — fairness across groups.

Imbalanced datasets (e.g. 99% non-fraud, 1% fraud) require special techniques such as resampling, class weighting and careful metric choice. Blindly optimising accuracy on imbalanced data produces models that look good but are useless.

Why It Matters

Business relevance for UK organisations

Classification is the most commercially important supervised learning task. UK organisations use it everywhere from credit approval to customer segmentation and operational triage.

Real-world example

How this shows up in practice

A London neobank trained a classification model to flag high-risk onboarding applications, improving fraud detection by 31% without increasing false positives.