Knowledge Maxxing← Back to topic library
ML MaxxingBeginner60 sec
Unsupervised learning
Unsupervised learning finds structure or patterns in data that has no labels, such as grouping similar examples together.
Prerequisite: Supervised learning
What matters
Because there is no known correct answer to check against, unsupervised methods are evaluated differently, often by how coherent or useful the discovered structure turns out to be.
Example
Grouping customers into segments based on purchase behavior, with no predefined 'correct' segment for each customer, is unsupervised learning.
Common misconception
Unsupervised learning does not mean the model has no goal; it still optimizes a defined objective, just one that does not require labeled answers.
Recall question
Why is unsupervised learning harder to score than supervised learning?
Keywords and related concepts
unsupervised learningunlabeled dataclusteringsupervised learning