Multi-objective rule mining using genetic algorithms

  • Authors:
  • Ashish Ghosh;Bhabesh Nath

  • Affiliations:
  • Machine Intelligence Unit, Indian Statistical Institute, 203 B.T. Road, Kolkata 700 108, India;Department of Computer Science, Tezpur University, Tezpur, India

  • Venue:
  • Information Sciences: an International Journal - Special issue: Soft computing data mining
  • Year:
  • 2004

Quantified Score

Hi-index 0.01

Visualization

Abstract

Association rule mining problems can be considered as a multi-objective problem rather than as a single objective one. Measures like support count, comprehensibility and interestingness, used for evaluating a rule can be thought of as different objectives of association rule mining problem. Support count is the number of records, which satisfies all the conditions present in the rule. This objective gives the accuracy of the rules extracted from the database. Comprehensibility, is measured by the number of attributes involved in the rule and tries to quantify the understandability of the rule. Interestingness measures how much interesting the rule is.Using these three measures as the objectives of rule mining problem, this article uses a Pareto based genetic algorithm to extract some useful and interesting rules from any market-basket type database. Based on experimentation, the algorithm has been found suitable for large databases.