Reduction of Negative and Positive Association Rule Mining and Maintain Superiority of Rule Using Modified Genetic Algorithm

Association rule mining play important rule in market data analysis and also in medical diagnosis of correlated problem. For the generation of association rule mining various technique are used such as Apriori algorithm, FP-growth and tree based algorithm. Some algorithms are wonder performance but generate negative association rule and also suffered from Superiority measure problem. In this paper we proposed a multi-objective association rule mining based on genetic algorithm and Euclidean distance formula. In this method we find the near distance of rule set using Euclidean distance formula and generate two class higher class and lower class .the validate of class check by distance weight vector. Basically distance weight vector maintain a threshold value of rule itemsets. In whole process we used genetic algorithm for optimization of rule set. Here we set population size is 1000 and selection process validate by distance weight vector. Our proposed algorithm distance weight optimization of association rule mining with genetic algorithm compared with multi-objective association rule optimization using genetic algorithm. Our proposed algorithm is better rule set generation instead of MORA method.