Glossary term
Glossary term
Foundations
Informally, a model that generates a numerical prediction. (In contrast, a classification model generates a class prediction.) For example, the following are all regression models:
A model that predicts a certain house's value in Euros, such as 423,000.
A model that predicts a certain tree's life expectancy in years, such as 23.2.
A model that predicts the amount of rain in inches that will fall in a certain city over the next six hours, such as 0.18.
Two common types of regression models are:
Linear regression, which finds the line that best fits label values to features.
Logistic regression, which generates a probability between 0.0 and 1.0 that a system typically then maps to a class prediction.
Not every model that outputs numerical predictions is a regression model. In some cases, a numeric prediction is really just a classification model that happens to have numeric class names. For example, a model that predicts a numeric postal code is a classification model, not a regression model.
Created for this library
A retail forecasting team uses a regression model to predict next-week sales by SKU.
A real estate firm uses a regression model on property features to estimate market value.
A logistics team uses a regression model to predict delivery time given route and historical traffic.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License