A New Approach of Eliminating Redundant Association Rules

Abstract

AbstractTwo important constraints of association rule mining algorithm are support and confidence. However, such constraints-based algorithms generally produce a large number of redundant rules. In many cases, if not all, number of redundant rules is larger than number of essential rules, consequently the novel intention behind association rule mining becomes vague. To retain the goal of association rule mining, we present several methods to eliminate redundant rules and to produce small number of rules from any given frequent or frequent closed itemsets generated. The experimental evaluation shows that the proposed methods eliminate significant number of redundant rules.KeywordsAssociation RuleFrequent ItemsetsAssociation Rule MiningSupport ThresholdConfidence ThresholdThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.