Machine Learning Foundations

Feature, explained

A feature is an input signal used by a model to make a prediction or learn a representation.
Back to Glossary

Part of the Semantic Notion technical glossary.

Short Definition

A feature is an input signal used by a model to make a prediction or learn a representation.

Intuition

Features are the pieces of information a model gets to see. Better features often make the learning problem easier.

Technical Definition

A feature is a measured, engineered, or learned variable supplied to a model as part of its input vector, tensor, or structured input.

Example

For a loan-risk model, income, credit history, and debt ratio may be features.

Common Misunderstandings

Features are not always hand-designed; deep models often learn them.
A feature can be predictive without being causal.

Same Category

More from Machine Learning Foundations

BackpropagationBackpropagation is the algorithm used to compute gradients through a neural network efficiently.Bias-Variance TradeoffThe bias-variance tradeoff describes the balance between models that are too simple to capture structure and models that are too sensitive to training data noise.Binary ClassificationBinary classification is a prediction task where each example belongs to one of two classes.DropoutDropout is a regularization technique that randomly disables parts of a neural network during training.Feature EngineeringFeature engineering is the process of transforming raw data into model inputs that make useful patterns easier to learn.GeneralizationGeneralization is a model's ability to perform well on new data, not just the data used during training.

Related Reading

Essays that use this concept

Data Science and EvaluationCorrelation vs Causation in Data Science

Start here

Need the broader concept map?

Return to the glossary index to move from this definition into adjacent AI, ML, mathematics, and computer science terms.

Browse Glossary