An Experimental Comparison of Old and New Decision Tree Algorithms

2019/11/08 by Zharmagambetov, Arman, Hada, Suryabhan Singh, Carreira-Perpiñán, Miguel Á. +1
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.1911.03054

Abstract

This paper presents a detailed comparison of a recently proposed algorithm for optimizing decision trees, tree alternating optimization (TAO), with other popular, established algorithms. We compare their performance on a number of classification and regression datasets of various complexity, different size and dimensionality, across different performance factors: accuracy and tree size (in terms of the number of leaves or the depth of the tree). We find that TAO achieves higher accuracy in nearly all datasets, often by a large margin.

Related

• Search Strategies for Optimal Classification and Regression Trees
• Optimal or Greedy Decision Trees? Revisiting their Objectives, Tuning, and Performance
• On the Optimality of Trees Generated by ID3
• Can a Single Tree Outperform an Entire Forest?
• Harnessing the Power of Choices in Decision Tree Learning