An implementation for dynamic combination of frequent items in HCFPMINETREE

Abstract

Modern digital databases are immersed with massive collection of data. The proliferation, ubiquity and increasing power of computer technology have increased data collection and storage. As datasets have grown in size and complexity, direct hands-on data analysis has increasingly been augmented in-direct, automatic data processing. There are so many existing algorithms to find frequent itemsets in Association Rule Mining. In this paper, we have modified FPtree algorithm as HCFPMine frequency of tree (Horizontal Compact Frequent Pattern Mining) combines all the maximum occurrence of frequent itemsets before converting into the tree structure. We have also used median value for finding same frequency of items and inserted it as node in the tree structure. We have explained it with an algorithm and illustrated with examples and also depicted the runtime and memory space for the construction of the tree structure.