Genetic algorithms based optimization of membership functions for fuzzy weighted association rules mining

Finding the most appropriate fuzzy sets becomes complicated when items are not considered to have equal importance and the support and confidence parameters needed in the mining process are specified as linguistic terms. Existing clustering based automated methods are not satisfactory because they do not consider the optimization of the discovered membership functions. To tackle this problem, we propose genetic algorithms (GAs) based clustering method, which dynamically adjusts the fuzzy sets to provide maximum profit based on minimum support and confidence specified as linguistic terms. This is achieved by tuning the base values of the membership functions for each quantitative attribute in a way that maximizes the number of large itemsets. To the best of our knowledge, this is the first effort in this direction. Experimental results on 100 K transactions taken from the adult database of US census in year 2000 demonstrate that the proposed clustering method exhibits good performance in terms of the number of produced large itemsets and interesting association rules.