Extraction of association rules based on genetic algorithm and data mining techniques

<p>Lylia Betit</p>

Extraction of association rules based on genetic algorithm and data mining techniques

Lylia Betit

University of Science and Technology Houari Boumediene, Algeria

: J Comput Eng Inf Technol

Abstract

In this project we intend to design and implement a tool dedicated to the automatic generation of association rules from a database. In order to generate the most relevant rules, we considered in this work, three different approaches: (1) extraction of rules from three data mining algorithms (Apriori, Close and CHARM); (2) enrichment of approach 1 by the application of the genetic algorithm; and (3) use of the genetic algorithm before applying one of the data mining algorithms. Moreover, we proposed two measures of relevance: weighted dominance and medium support. UML modeling was done before developing the extraction tool that supports our three approaches. Several experiments were carried out with a base related to the purchase of products. The results show that the third approach generated the most relevant rules.

Biography

Lylia Betit holds a Degree in Computer Science from USTHB: Houari Boumediene University of Science and Technology, Algeria. She is now admitted to continue her studies (Master 1 and 2) in Artificial Intelligence.

E-mail: betit.lilya@gmail.com