A Contribution to the Study of Classification and Regression Trees Using Multivalued Array Algebra

Abstract

Classification and regression trees are machine-learning methods that construct prediction models from data. The models are obtained by recursively partitioning the data and fitting a simple prediction model within each partition. As a result, the partitioning can be represented graphically as a decision tree. Classification trees are designed for dependent variables that take a finite number of unordered values. Whereas, regression trees are for dependent variables that take continuous or ordered discrete values.This paper presents an approach for classification and regression trees by considering the Array Algebra. The data’s descriptive knowledge is expressed by means of an array expression written in terms of a multivalued language. The Array Algebra allows for classification in a simple manner.