CART (Classification And Regression Tree)

Information

• CART (Classification And Regression Tree) is a decision tree algorithm used for both classification and regression analysis.
• It involves recursively splitting the dataset into smaller subsets by identifying the best predictor variables and splitting rules that minimize the variance or impurity within each subset.
• The algorithm builds a binary tree with the target variable at the root and splits the tree into branches based on the input features until it reaches the terminal nodes (leaves) containing the predicted values.
• For classification problems, CART uses Gini impurity or entropy measures to quantify the impurity of a node, while for regression problems, it minimizes the sum of squared residuals (SSR) between the predicted and actual values.
• CART can handle both categorical and numerical data, and is easy to interpret and visualize. However, it is prone to overfitting and can be sensitive to small variations in the data.