Construction of Decision Trees and Acyclic Decision Graphs from Decision Rule Systems

TL;DR

This paper investigates the complex process of constructing decision trees and acyclic decision graphs from rule systems, focusing on the inverse transformation and efficient computation path description.

Contribution

It explores the complexity of inverse transformations from decision rule systems to decision trees and graphs, and discusses partial construction methods for specific inputs.

Findings

Analyzes the complexity of constructing decision trees from rule systems

Discusses methods for describing computation paths without full tree construction

Provides insights into inverse transformation challenges

Abstract

Decision trees and systems of decision rules are widely used as classifiers, as a means for knowledge representation, and as algorithms. They are among the most interpretable models for data analysis. The study of the relationships between these two models can be seen as an important task of computer science. Methods for transforming decision trees into systems of decision rules are simple and well-known. In this paper, we consider the inverse transformation problem, which is not trivial. We study the complexity of constructing decision trees and acyclic decision graphs representing decision trees from decision rule systems, and we discuss the possibility of not building the entire decision tree, but describing the computation path in this tree for the given input.