Supervised Learning is a type of machine learning where a model learns from labelled examples — data where the correct answer is already provided — so it can predict the answer for new, unseen data.
What it means in plain English
In supervised learning, you act as the teacher. You give the model many examples, each paired with the right answer (the “label”), and it learns to map inputs to outputs. Once trained, it can apply that mapping to new inputs it has never seen. The word “supervised” reflects that the training data comes with correct answers to learn from.
It is the most common and straightforward form of machine learning, used wherever you have historical data with known outcomes.
A simple example
To build a spam filter, you train on thousands of emails each labelled “spam” or “not spam.” The model learns the patterns that distinguish them and can then classify new incoming emails on its own.
Why it matters
Supervised learning powers a huge share of everyday AI — spam filters, image classification, price prediction, medical screening. Understanding it clarifies the central role that labelled data plays in building useful AI.
Related terms
- Unsupervised Learning — learning from data with no labels.
- Training Data — the labelled examples used.
- Reinforcement Learning — a third approach, learning from rewards.
Frequently asked questions
What is supervised learning?
It is training a model on labelled examples — inputs paired with correct outputs — so it learns to predict the output for new inputs.
What are examples of supervised learning?
Spam detection, image classification, price prediction, and sentiment analysis are all supervised tasks that learn from labelled data.
