Chapter 2.3 - Data mining and decision trees

Abstract

This chapter presents briefly data mining, an interdisciplinary field at the intersection of artificial intelligence, machine learning, statistics, and database systems, and discusses decision trees, one of the most common data mining tools used for classification. The processes in creating a decision tree are described, basic terms are explained, and the strengths and weaknesses of this technique compared with more traditional statistics are outlined. The random forest method used to increase the predictive performance of decision trees is presented in more detail. Finally an example of the use of decision trees in sex estimation is implemented in a step-by-step manner in R.