Comparative Study of Association Rules Mining

Abstract

Association rule mining is a technique to find useful patterns and associations in transactional databases. The mining of association rules can be mapped into the problem of discovering large (frequent) itemsets where is a grouped of items which appear in a sufficient number of transaction. The discovery of interesting association relationships among huge amount of business transaction records can help in many business decision making process . There are many association rules mining algorithms. But this system is intended to make the comparative study of three association rules mining algorithms such as DHP algorithm, PHP algorithm and Hybrid Approach of Support-Ordered Tree and PHP based on same dataset. Both DHP and PHP algorithm use hash base method and pruning method to reduce database size. DHP use direct hashing technique. PHP use perfect hashing technique. The two dataset, Kyar Nyo Pan Stationary Store and Orange minimarket are used.