Decision tree methods: applications for classification and prediction

TLDR

Decision tree methodology is a widely used non‑parametric data‑mining technique that builds classification or prediction models by recursively partitioning data into branch‑like segments without imposing a parametric structure. This paper introduces commonly used decision‑tree algorithms (CART, C4.5, CHAID, QUEST) and describes how to visualize tree structures using SPSS and SAS. The authors split large datasets into training and validation sets, build a decision‑tree model on the training data, and use the validation data to select the optimal tree size.

Abstract

Decision tree methodology is a commonly used data mining method for establishing classification systems based on multiple covariates or for developing prediction algorithms for a target variable. This method classifies a population into branch-like segments that construct an inverted tree with a root node, internal nodes, and leaf nodes. The algorithm is non-parametric and can efficiently deal with large, complicated datasets without imposing a complicated parametric structure. When the sample size is large enough, study data can be divided into training and validation datasets. Using the training dataset to build a decision tree model and a validation dataset to decide on the appropriate tree size needed to achieve the optimal final model. This paper introduces frequently used algorithms used to develop decision trees(including CART, C4.5, CHAID, and QUEST) and describes the SPSS and SAS programs that can be used to visualize tree structure.