In data mining, regression is a statistical modeling technique that involves predicting a continuous quantity for new observations by using the knowledge gained from the previous data.
In simple words, if the target variable or outcome the variable is a continuous variable then it is a regression problem and if the target variable is discrete, it is a classification problem.
Example for regression problem: Predicting the prices of houses from the features of houses like the number of rooms, the size of a house, location of the house, etc.
Some of the most used regression algorithms in Data Mining:
- Linear regression
- Lasso regression
- Polynomial regression
- Ridge regression
- Decision trees
- Random forest regression
- K-Nearest neighbors
If you wish to learn more about regression and implementation, you can enroll in this Data Science Training course by Intellipaat.
Also, watch this video on Data Mining:
Back