7.4 Features and Labels

In supervised learning, features are the input variables that describe each example, and the label is the answer we want the model to predict. If features are the questions, the label is the correct answer the model learns to produce.

Imagine predicting whether a coffee harvest will be 'good' or 'poor'. Features could be rainfall (mm), altitude, fertiliser used, and temperature. The label is the harvest outcome: good or poor. The model learns how the features relate to that label.