Mining Fuzzy Frequent Item Set using Compact Frequent Pattern (CFP) Tree Algorithm

Abstract

The problem of mining quantitative data from large transaction database is considered to be an important critical task. Researchers have proposed efficient algorithms for mining of frequent itemsets based on Frequent Pattern (FP) tree like structure which outperforms Apriori like algorithms by its compact structure and less generation of candidate itemsets mostly for binary data items from huge transaction database. Fuzzy logic softens the effect of sharp boundary intervals and solves the problem of uncertainty present in data relationships. This proposed approach integrates the fuzzy logic in the newly invented tree-based algorithm by constructing a compact sub-tree for a fuzzy frequent item significantly efficient than other algorithms in terms of execution times, memory usages and reducing the search space resulting in the discovery of fuzzy frequent itemsets.