Decision Tree Induction Based on Efficient Tree Restructuring

  • Authors:
  • Paul E. Utgoff;Neil C. Berkman;Jeffery A. Clouse

  • Affiliations:
  • Department of Computer Science, University of Massachusetts, Amherst, MA 01003. E-mail: utgoff@cs.umass.edu;Corvid Corp., 779 West St., Carlisle, MA 01741. E-mail: neil@corvid.com;Department of Computer Science, North Carolina A&T State University, Greensboro, NC 27411. E-mail: clouse@ncat.edu

  • Venue:
  • Machine Learning
  • Year:
  • 1997

Quantified Score

Hi-index 0.00

Visualization

Abstract

The ability to restructure a decision tree efficiently enables avariety of approaches to decision tree induction that would otherwisebe prohibitively expensive. Two such approaches are described here,one being incremental tree induction (ITI), and the other beingnon-incremental tree induction using a measure of tree qualityinstead of test quality (DMTI). These approaches and severalvariants offer new computational and classifier characteristics thatlend themselves to particular applications.