Knowledge Maxxing← Back to topic library
ML MaxxingBeginner60 sec
Classification
Classification is a supervised learning task where the model predicts which category, out of a fixed set, an example belongs to.
Prerequisite: Supervised learning
What matters
Because the output is one of a limited set of categories, classification models are typically evaluated with metrics like accuracy, precision and recall rather than measures of numeric distance.
Example
Predicting whether an email is 'spam' or 'not spam' is classification, since the output is one of exactly two fixed categories.
Common misconception
Classification is not limited to two categories; a model choosing among ten possible categories is still classification, just with more classes.
Recall question
What distinguishes classification's output from regression's output?
Keywords and related concepts
classificationcategoriessupervised learningregression