Implementing frequent itemset mining by advanced distributed approach using matrix-based pruning

Abstract

Mining of frequent itemsets is a very crucial process in the mining of associate rules. Significant challenges are being encountered in this era where big data has drawn its own circle by shaping around space and time factors. A distributed procedure for the job is what that best be defined. So we increment our previous version with an enhanced version by the implementing a distributed approach which is better that FP growth. Differentiating of the existing and proposed algorithm is done using the practical valuable data that is available.