To apply supervised machine learning, we need labelled data. The goal of supervised machine learning algorithms is to create a model that determines or predicts a target variable as accurately as possible. Within supervised machine learning, we distinguish between regression and classification problems, which differ in the shape of the target variable:
- Regression problems: The target variable is numeric. Examples of numeric target variables are the number of products sold and the probability that a website visitor clicks on a link.
- Classification problems: The target variable is categorical. Examples of categorical target variables are "Does an email contain spam, yes or no?" and "What colour is the traffic light right now, red, yellow or green?".