Result Analysis of Mining Fast Frequent Itemset Using Compacted Data

Abstract

Data mining and knowledge discovery of database is magnetizing wide array of non-trivial research arena, making easy to industrial decision support systems and continues to expand even beyond imagination in one such promising field like Artificial Intelligence and facing the real world challenges. Association rules forms an important paradigm in the field of data mining for various databases like transactional database, time-series database, spatial, object-oriented databases etc. The burgeoning amount of data in multiple heterogeneous sources coalesces with the impediment in building and preserving central vital repositories compels the need for effectual distributive mining techniques. The majority of the previous studies rely on an Apriori-like candidate set generation-and-test approach. For these applications, these forms of aged techniques are found to be quite expensive, sluggish and highly subjective in case there exists long length patterns.