A Database-Independent Approach of Mining Association Rules with Genetic Algorithm

Abstract

Apriori-like algorithms for association rules mining rely upon the minimum support and the minimum confidence. Users often feel hard to give these thresholds. On the other hand, genetic algorithm is effective for global searching, especially when the searching space is so large that it is hardly possible to use deterministic searching method. We try to apply genetic algorithm to the association rules mining and propose an evolutionary method. Computations are conducted, showing that our ARMGA model can be used for the automation of the association rule mining systems, and the ideas given in this paper are effective.