Home > Archive > 2011 > Volume 1 Number 4 (Oct. 2011) >
IJMLC 2011 Vol.1(4): 325-331 ISSN: 2010-3700
DOI: 10.7763/IJMLC.2011.V1.48

Robust and Cost-Effective Approach for Discovering Action Rules

Nasrin Kalanat, Pirooz Shamsinejad, and Mohamad Saraee

Abstract—The main goal of Knowledge Discovery in Databases is to find interesting and usable patterns, meaningful in their domain. Actionable Knowledge Discovery came to existence as a direct respond to the need of finding more usable patterns called actionable patterns. Traditional data mining and algorithms are often confined to deliver frequent patterns and come short for suggesting how to make these patterns actionable. In this scenario the users are expected to act. However, the users are not advised about what to do with delivered patterns in order to make them usable. In this paper, we present an automated approach to focus on not only creating rules but also making the discovered rules actionable. Up to now few works have been reported in this field which lacking incomprehensibility to the user, overlooking the cost and not providing rule generality. Here we attempt to present a method to resolving these issues. In this paper CEARDM method is proposed to discover cost-effective action rules from data. These rules offer some cost-effective changes to transferring low profitable instances to higher profitable ones. We also propose an idea for improving in CEARDM method.

Index Terms—actionable knowledge discovery, cost-effective action rules, profit mining.

Nasrin Kalanat and Pirooz Shamsinejadbabaki are with Electrical and Computer Engineering Department of Isfahan University of Technology, Isfahan, Iran. (e-mail: n.kalanat@ec.iut.ac.ir; p_shamsinejad@ec.iut.ac.ir). Mohammad Saraee is the founder and Director of the Intelligent Databases, Data Mining and Bioinformatics Research Centre.


Cite: Nasrin Kalanat, Pirooz Shamsinejad and Mohamad Saraee, "Robust and Cost-Effective Approach for Discovering Action Rules," International Journal of Machine Learning and Computing vol. 1, no. 4, pp.325-331, 2011.

General Information

  • ISSN: 2010-3700 (Online)
  • Abbreviated Title: Int. J. Mach. Learn. Comput.
  • Frequency: Bimonthly
  • DOI: 10.18178/IJMLC
  • Editor-in-Chief: Dr. Lin Huang
  • Executive Editor:  Ms. Cherry L. Chen
  • Abstracing/Indexing: Inspec (IET), Google Scholar, Crossref, ProQuest, Electronic Journals Library.
  • E-mail: ijmlc@ejournal.net

Article Metrics