Linear regression is a supervised learning method that uses a linear model to predict a continuous numerical value. It estimates the relationship between input features and a floating-point output, usually by minimizing a loss such as mean squared error. It differs from classification methods, which predict categories rather than continuous values.
A type of machine learning model in which both of the following are true: - The model is a linear model. - The prediction is a floating-point value. (This is the regression part of linear regression.) Contrast linear regression with logistic regression. Also, contrast regression with classification. See Linear regression in Machine Learning Crash Course for more information.