Improved Implementation and Performance Analysis of Association Rule Mining in Large Databases

Abstract

Data mining is the process of extracting interesting and previously unknown patterns and correlations from data stored in Data Base Management Systems (DBMSs). Association Rule Mining is the process of discovering items, which tend to occur together in transactions. Efficient algorithms to mine frequent patterns are crucial to many tasks in data mining. The task of mining association rules consists of two main steps. The first involves finding the set of all frequent itemsets. The second step involves testing and generating all high confidence rules among itemsets. Our paper deals with obtaining both the frequent itemsets as well as generating association rules among them.In this paper we implement the FORC (Fully Organized Candidate Generation) algorithm, which is a constituent of the Viper algorithm for generating our candidates and subsequently our frequent itemsets. Our implementation is an improvement over Apriori, the most common algorithm used for frequent item set mining.KeywordsAssociation RuleFrequent ItemsetsAssociation Rule MiningFrequent ItemApriori AlgorithmThese 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.