Mining traditional association rules using frequent itemsets lattice

Abstract

There are many methods which have been developed for improvement of time inmining frequent itemsets. However, the methods which deal with the time ofmining association rules were not put in deep research. In reality, in case ofdatabase which contains many frequent itemsets (from ten thousands up tomillions), the time of mining association rules is much larger than that neededfor mining frequent itemsets. In this paper, we present an application oflattice in mining traditional association rules which will reduce greatly thetime for mining rules-our method includes two phases: (1) building frequentitemsets lattice and (2) mining association rules from lattice. We based on theparent-child relationships in lattice to fast discover the association rules.The experiments show that the mining rules from lattice is more effective thanthe direct mining from frequent itemsets using hash table. © 2009 IEEE.