A novel approach of finding frequent itemsets in high speed data streams

Abstract

The paper proposes a novel methodology of finding frequent itemsets in data stream. Fuzzification of support of closed frequent itemsets in conjunction with jumping window has been used for finding frequent itemsets. Fuzzification of support of closed frequent itemsets helps in preserving information regarding the frequent itemsets at different point in time in the data stream. Use of jumping window over the high speed data stream improves the speed of the proposed algorithm. Effectiveness of the proposed algorithm is shown by comparing its performance with the widely known MOMENT algorithm on both IBM synthetic datasets and benchmark datasets taken from UCI Machine Learning Repository.