Binary Decision Trees

A Binary Decision Tree is a structure based on a sequential decision process. Starting from the root, a feature is evaluated and one of the two branches is selected. This procedure is repeated until a final leaf is reached, which normally represents the classification target we're looking for. One of the first formulations of Decision Trees is called Iterative Dichotomizer 3 (ID3), and it required categorical features. This condition restricted its use and led to the development of C4.5, which could also manage continuous (but binned and discretized) values. Moreover, C4.5 was also known because of its ability to transform a tree into a sequence of conditional expressions (if <condition> then <...> else <...>). In this book, we are going to address the most recent development, which is called Classification and Regression Trees (CART...