Association rule mining is one of the most important and well-researched techniques of data mining, that aims to induce associations among sets of items in transaction databases or other data repositories. Currently Apriori algorithms play a major role in identifying frequent item set and deriving rule sets out of it. However there are few shortfalls in conventional Apriori Algorithm. They are i) candidate items generation consumes lot of time in the case of large datasets ii) It supports majorly the conjunctive nature of association rules iii) The single minimum support factor to generate the effective rules. However points ii) and iii) have been addressed effectively in the earlier work [10] with reference to Apriori Algorithm. But this paper majorly worked on the above point i). In the proposed algorithm, FP growth algorithm has been taken for a reference in generating frequent item set without candidate generation. There are appreciable amount of modification and enhancements have been worked out in line with the earlier work. Besides this work also taken care the integration issues while fitting it suitably with the earlier worked out algorithm [10]. This packaged Algorithm is named as E-Rules (Effective Rules). After incorporating the modified FP Growth Algorithm, it has been observed that there is a prominent difference in time taken and performance as it does not involve candidate generations. Hence 'E-Rules' addressing the faster generation of frequent item sets, so that to offer interesting/useful rules in an effective and optimized manner with the help of Genetic Algorithm.

FP Growth Algorithm Genetic Algorithm Lift ratio Multiple Minimum Support Disjunctive Rules