Machine Learning: What is the difference between regression and classification algorithms?
First of all, both regression and classification algorithms can be classified as supervised learning algorithms. Although they solve different problems, the basic principle is the same for both: algorithms learn a function f(x) based on a "labeled" data set, which assigns an output y to each input x. The goal is to determine the function f(x) as precisely as possible in order to use it as a basis for the most precise classification. The goal is to determine the function f(x) as accurately as possible in order to use it to make predictions for new inputs that are as precise as possible.
The fundamental difference between regression and classification algorithms is that the output of a regression algorithm is numerical, while the output in a classification algorithm is categorical.
An example of a regression problem is the prediction of house prices based on different characteristics such as the size, the number of rooms and the location. In this case, one would use a regression algorithm and train it with a data set containing the respective characteristics and prices of different houses. Then, the algorithm is able to predict the price of a house based on the three characteristics of size, number of rooms, and location.
Commonly used regression algorithms are linear regression, support vector regression, and regression trees.
An example of a classification problem is a spam filter, which is used in almost every e-mail program. The goal of the classification algorithm is to assign e-mails to either the inbox or the spam folder based on various characteristics. The training of the algorithm works similar to a regression algorithm.
Commonly used classification algorithms include logistic regression, k-nearest-neighbors, and decision trees.
Source (translated): Medium
Damage good. All good.
