The potential of Associative Classifiers

Assoc. Prof. O. Zaiane

Dept of Computer Science, University of Alberta, Canada

Mon Nov 14 14:00:00 NZDT 2005 in Room 031, MSCS

Abstract

There are countless paradigms and strategies for devising a classifier. Associative classifiers use association rules as a model and are a very new approach to rule-based classification. While they are still less accurate than other approaches, they have many advantages and certainly potential in many applications. We will briefly introduce associative classifiers, discuss their main three phases: rule generation, rule pruning and rule selection, and highlight the differences between the suggested strategies. We will also present our current research work targeting theses individual three phases to improve the effectiveness of such classifiers.

Bio can be found at: http://www.cs.ualberta.ca/~zaiane/htmldocs/bio.html