Optimization and analysis of decision trees and rules: Dynamic programming approach

Handle URI:
http://hdl.handle.net/10754/564783
Title:
Optimization and analysis of decision trees and rules: Dynamic programming approach
Authors:
Alkhalid, Abdulaziz; Amin, Talha ( 0000-0003-3035-8612 ) ; Chikalov, Igor; Hussain, Shahid ( 0000-0002-1698-2809 ) ; Moshkov, Mikhail ( 0000-0003-0085-9483 ) ; Zielosko, Beata
Abstract:
This paper is devoted to the consideration of software system Dagger created in KAUST. This system is based on extensions of dynamic programming. It allows sequential optimization of decision trees and rules relative to different cost functions, derivation of relationships between two cost functions (in particular, between number of misclassifications and depth of decision trees), and between cost and uncertainty of decision trees. We describe features of Dagger and consider examples of this systems work on decision tables from UCI Machine Learning Repository. We also use Dagger to compare 16 different greedy algorithms for decision tree construction. © 2013 Taylor and Francis Group, LLC.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Applied Mathematics and Computational Science Program; Extensions of Dynamic Programming, Machine Learning and Discrete Optimization Research Group; Computer Science Program
Publisher:
Informa UK Limited
Journal:
International Journal of General Systems
Issue Date:
Aug-2013
DOI:
10.1080/03081079.2013.798902
Type:
Article
ISSN:
03081079
Appears in Collections:
Articles; Applied Mathematics and Computational Science Program; Computer Science Program; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorAlkhalid, Abdulazizen
dc.contributor.authorAmin, Talhaen
dc.contributor.authorChikalov, Igoren
dc.contributor.authorHussain, Shahiden
dc.contributor.authorMoshkov, Mikhailen
dc.contributor.authorZielosko, Beataen
dc.date.accessioned2015-08-04T07:15:47Zen
dc.date.available2015-08-04T07:15:47Zen
dc.date.issued2013-08en
dc.identifier.issn03081079en
dc.identifier.doi10.1080/03081079.2013.798902en
dc.identifier.urihttp://hdl.handle.net/10754/564783en
dc.description.abstractThis paper is devoted to the consideration of software system Dagger created in KAUST. This system is based on extensions of dynamic programming. It allows sequential optimization of decision trees and rules relative to different cost functions, derivation of relationships between two cost functions (in particular, between number of misclassifications and depth of decision trees), and between cost and uncertainty of decision trees. We describe features of Dagger and consider examples of this systems work on decision tables from UCI Machine Learning Repository. We also use Dagger to compare 16 different greedy algorithms for decision tree construction. © 2013 Taylor and Francis Group, LLC.en
dc.publisherInforma UK Limiteden
dc.subjectdecision rulesen
dc.subjectdecision treesen
dc.subjectdynamic programmingen
dc.subjectoptimizationen
dc.titleOptimization and analysis of decision trees and rules: Dynamic programming approachen
dc.typeArticleen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentApplied Mathematics and Computational Science Programen
dc.contributor.departmentExtensions of Dynamic Programming, Machine Learning and Discrete Optimization Research Groupen
dc.contributor.departmentComputer Science Programen
dc.identifier.journalInternational Journal of General Systemsen
dc.contributor.institutionDepartment of Systems and Computer Engineering, Carleton University, Ottawa, ON, Canadaen
dc.contributor.institutionInstitute of Computer Science, University of Silesia, Sosnowiec, Polanden
kaust.authorChikalov, Igoren
kaust.authorHussain, Shahiden
kaust.authorMoshkov, Mikhailen
kaust.authorZielosko, Beataen
kaust.authorAmin, Talhaen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.