Knowledge Maxxing← Back to topic library
ML MaxxingBeginner60 sec
Regression
Regression is a supervised learning task where the model predicts a continuous numeric value rather than a category.
Prerequisite: Classification
What matters
Because the output is a number on a continuous scale, regression is evaluated with error-based metrics that measure how far predictions land from the true value, rather than whether a category matches exactly.
Example
Predicting the exact sale price of a house, a number that could be almost any value in a range, is regression.
Common misconception
Regression does not always refer to linear regression specifically; regression describes any task predicting a continuous value, regardless of the technique used.
Recall question
Why do regression models use different evaluation metrics than classification models?
Keywords and related concepts
regressioncontinuous valuesupervised learningclassification