Experiments with an Innovative Tree Pruning Algorithm

M. Zhong, M. Georgiopoulos, and G.C. Anagnostopoulos (USA)

Keywords

decision tree, classification, 2norm, pruning, CART, C4.5

Abstract

The pruning phase is one of the necessary steps in deci sion tree induction. Existing pruning algorithms tend to have some or all of the following difficulties: 1) lack of theoretical support; 2) high computational complexity; 3) dependence on validation; 4) complicated implementation. The 2-norm pruning algorithm proposed here addresses all of the above difficulties. This paper demonstrates the ex perimental results of the comparison among the 2-norm pruning algorithm and two classical pruning algorithms, the Minimal Cost-Complexity algorithm (used in CART) and the Error-based pruning algorithm (used in C4.5), and confirms that the 2-norm pruning algorithm is superior in accuracy and speed.

Important Links:



Go Back