A Novel Approach to Rank Association Rules Using Genetic Algorithm

In this paper we propose a new technique to select the top „n‟ association rules out of a pool of „k‟ association rules based on heuristic analysis. The proposed method ranks association rules giving emphasis to a larger set of parameters than used by standard methods. The role of correlation has been emphasized in the proposed method which also tries to eliminate issues faced in incorporating correlation, support and confidence meaningfully into one single fitness function. A genetic algorithm model has been developed to establish the rank of the rules taking into consideration the extended set of parameters. The method allows us to establish the best rules in a set of “good” rules and allows for pruning of misleading rules that are often suggested by standard algorithms like the Apriori method.