Classification and Regression Trees: Advanced Methods (with C4.5 algorithm)

In a previous post on CART Algorithm, we saw what decision trees (aka Classification and Regression Trees, or CARTs) are. We explored a classification problem and solved it using the CART algorithm while also learning about information theory.

In this post, we show the popular C4.5 algorithm on the same classification problem and look into advanced techniques to improve our trees: such as random forests and pruning.

C4.5 Algorithm for Classification

The classification problem discussed in the p...