Supervised Learning Techniques. Supervised learning is a type of machine learning in which the models are trained using labeled input data. The model learns the pattern to predict the output from the input data, which is “supervised” to determine the models’ accuracy when predicting the output class, comparing them with the actual true outputs. Some of the supervised learning techniques include .

Linear Regression: this models used when predicting a continuous output. It assumes the linear link of all independent variable X to an independent single variable Y.

Logistic Regression: Despite the name, this is used for classification problems and not regression. The model predicts the probability that a given instance belongs to a particular class.

Decision Trees: A tree-like model used to predict whether an instance will belong to a class or another . The decision is made based on the feature values of the model, and the tree is created to split into branches, leading to an outcome.

Random Forests: This algorithms are consist of multiple classification and regression trees during training and rigidly calculates the decision majority or mean value between the prediction of the trees. This is done by a bias variance problem.

Support Vector Machines: Used for both classification and regression to determine the hyperplane that separates the classes with the largest margin .

Naive Bayes classifiers: Naive Bayes classifiers are a family of simple probabilistic classifiers based on the Bayes Theorem.

K-Nearest Neighbors: Used for classification in a non-parametric way; a query instance is given a class by a majority vote of its K nearest neighbors .

Gradient Boosting Machines: Use an ensemble technique where multiple sequential models are built to improve prediction.

Neural Networks: A machine learning variation that applies well to regression and classification and cope with complex input relations, such as recognizing images and speech .

Typical use cases for each highly depend on what you would like to achieve and the nature of the problem and data.