ESWCA:An Efficient Algorithm for Mining Frequent Itemsets

The most significant tasks in data mining are the process of mining frequent itemsets over data streams. It should support the flexible trade-off between processing time and mining accuracy. The objective was to propose an effective algorithm which generates frequent itemsets in a very less time by avoiding multiple scans. In this paper, we present an improved algorithm ESWCA for mining frequent itemsets using sliding window model. The ESWCA algorithm processes on an on-line transactional data stream. In this approach, we handle continues transaction slides in a segment-based manner which produces the improved runtime and memory consumption. Also, by revising the fair-cutter in the novel algorithm, multiple scans of the entire datasets will be avoided. Our experiments show that our algorithm not only achieved effectively consumes less memory, but also runs in an efficient manner.