Learning fuzzy decision trees using integer programming

J.S. Rhuggenaath, Y. Zhang, A. Akcay, U. Kaymak, Sicco E. Verwer

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

9 Citations (Scopus)
1128 Downloads (Pure)

Abstract

A popular method in machine learning for supervised classification is a decision tree. In this work we propose a new framework to learn fuzzy decision trees using mathematical programming. More specifically, we encode the problem of constructing fuzzy decision trees using a Mixed Integer Linear Programming (MIP) model, which can be solved by any optimization solver. We compare the performance of our method with the performance of off-the-shelf decision tree algorithm CART and Fuzzy Inference Systems (FIS) using benchmark data-sets. Our initial results are promising and show the advantages of using non-crisp boundaries for improving classification accuracy on testing data.
Original languageEnglish
Title of host publication2018 IEEE International Conference on Fuzzy Systems, FUZZ 2018 - Proceedings
Place of PublicationPiscataway
PublisherInstitute of Electrical and Electronics Engineers
Pages312-319
Number of pages8
ISBN (Electronic)978-1-5090-6020-7
DOIs
Publication statusPublished - 12 Oct 2018
Event2018 IEEE International Conference on Fuzzy Systems, FUZZ 2018 - Rio de Janeiro, Brazil
Duration: 8 Jul 201813 Jul 2018

Conference

Conference2018 IEEE International Conference on Fuzzy Systems, FUZZ 2018
Abbreviated titleFUZZ 2018
Country/TerritoryBrazil
CityRio de Janeiro
Period8/07/1813/07/18

Keywords

  • Fuzzy logic
  • Fuzzy systems
  • Machine learning
  • Mathematical programming
  • Optimization

Fingerprint

Dive into the research topics of 'Learning fuzzy decision trees using integer programming'. Together they form a unique fingerprint.

Cite this