Direct comparison
Supervised vs Unsupervised Learning: Definitions
Supervised vs unsupervised learning: the NIST definitions, which method families sit under each in scikit-learn, and where semi-supervised fits.
Written and maintained by CASRAI Editorial Board
Last updated
Ask CASRAI · free to try
Ask about Supervised vs Unsupervised Learning: Definitions
Ask your first 2 questions free below. Subscribers get 150 a day for $29 a month.
An AI assistant specialized in research administration. It cites the sources behind every answer, labels web answers and says when it can't answer.
Answers draw on CASRAI's guides and dictionary plus the federal and funder documents we index: Federal Register, Grants.gov, Regulations.gov and UKRI.
Works on this site and inside Claude, Cursor and the AI tools you already use.
Everything CASRAI publishes — this page, the dictionary, the guides and the news — stays free to read, with no account and no card.
How do Supervised learning, Unsupervised learning compare side by side?
The table below compares Supervised learning, Unsupervised learning across 8 procurement-relevant dimensions, from nist glossary definition through source.
Side-by-side comparison
| Dimension | Supervised learning | Unsupervised learning |
|---|---|---|
| NIST glossary definition | "A type of machine learning in which a model learns to predict explicit (often human-generated) labels or output values for data." | "A type of machine learning in which a model learns based on patterns in unlabeled data, such as learning a function to cluster or group data points." |
| Training data | Data with explicit labels or output values. | Unlabeled data. |
| What the model learns | To predict the labels or output values for data. | Patterns in the data, for example a function that clusters or groups data points. |
| Method families in the scikit-learn User Guide | Linear models, LDA/QDA, kernel ridge regression, support vector machines, stochastic gradient descent, nearest neighbors, Gaussian processes, cross decomposition, naive Bayes, decision trees, ensembles, isotonic regression, neural networks (MLP). | Gaussian mixture models, manifold learning, clustering, biclustering, decomposing signals in components (matrix factorization), covariance estimation, novelty and outlier detection, density estimation, neural network models. |
| Neural networks | Listed under supervised learning as neural network models (supervised), the multi-layer perceptron. | Listed under unsupervised learning as neural network models (unsupervised). |
| Semi-supervised learning | scikit-learn files semi-supervised learning (self-training, label propagation) in its supervised learning section. | Not filed in the scikit-learn unsupervised section. |
| When to pick each | You have labels or output values for the outcome you want the model to predict. | You want to find patterns or groupings in data that has no labels. |
| Source | NIST CSRC Glossary, "supervised learning" (https://csrc.nist.gov/glossary/term/supervised_learning), citing NIST AI 100-2e2025 (https://doi.org/10.6028/NIST.AI.100-2e2025); scikit-learn User Guide, Supervised learning (https://scikit-learn.org/stable/supervised_learning.html). Read 2026-10-29. | NIST CSRC Glossary, "unsupervised learning" (https://csrc.nist.gov/glossary/term/unsupervised_learning), citing NIST AI 100-2e2025 (https://doi.org/10.6028/NIST.AI.100-2e2025); scikit-learn User Guide, Unsupervised learning (https://scikit-learn.org/stable/unsupervised_learning.html). Read 2026-10-29. |
Common questions
Common questions about Supervised learning vs Unsupervised learning
What is the difference between supervised and unsupervised learning?
+
Labels. NIST describes supervised learning as a model that learns to predict explicit (often human-generated) labels or output values for data, while unsupervised learning is a model that learns from patterns in unlabeled data, such as learning a function to cluster or group data points.
Going deeper
