'Classification And Regression Trees', also sometimes called 'decision trees'. CART is a popular machine learning technique, and it forms the basis for techniques like random forests and common implementations of gradient boosting machines.
CART stands for Classification And Regression Trees. This is a technique for developing a tree model (T) to predict categories (C) and/or continuous values (R) by recursive partitioning. It does not make restrictive parametric assumptions.
(Note that "CART" is a synecdoche for the general data mining technique of using decision trees to predict outcomes. Strictly speaking, "CART" refers to a specific algorithm for forming trees that was popularized by the work of Leo Breiman. However, CART is commonly used to refer to any predictive tree algorithm, and the tag may be used similarly on Cross Validated.)
