Supervised learning is a type of machine learning where models are trained using labeled data. That is, data where the correct output is already known for each observation. The model learns the relationship between the inputs (also called features or predictors) and the known outputs (called labels or target values), so that it can accurately predict the output for new, unseen data.
Supervised learning is called “supervised” because the training process is guided by the known answers. The model receives feedback during training about how accurate its predictions are and adjusts accordingly. This contrasts with unsupervised learning, where no labeled outcomes are provided.
There are two main types of supervised learning methods:
- Classification: The goal is to predict a category or class label (e.g., spam vs. not spam, or disease vs. no disease).
- Regression: The goal is to predict a continuous value (e.g., house price, temperature, or sales revenue).
Common supervised learning algorithms include:
- Linear regression and logistic regression
- Decision trees and random forests
- Support vector machines (SVM)
- Naive Bayes
- K-nearest neighbors (KNN)
- Neural networks, including deep learning models
- Gradient boosting methods, such as XGBoost and LightGBM
Model performance in supervised learning is typically evaluated using metrics such as classification accuracy, precision, recall, mean squared error, or R-squared, depending on whether the task is classification or regression.
Supervised learning is foundational to predictive modeling and is widely used in applications like medical diagnosis, credit scoring, fraud detection, and recommendation systems.
« Back to Glossary Index