An Efficient Approach to Mine Frequent Itemsets Using the Variant of Classic Apriori and FP-Tree

Abstract

As with the advancement of the information technologies, the amount of accumulated data is also increasing. It has resulted in large amount of data stored in databases, warehouses and other repositories. Thus the Data mining comes into picture to explore and analyse the databases to extract the interesting and previously unknown patterns and rules known as association rule mining. In data mining, association rule mining becomes one of the important tasks of descriptive technique which can be defined as discovering meaningful patterns from large collection of data. Mining frequent itemset is very fundamental part of association rule mining. Many algorithms have been proposed from last many decades including horizontal layout based techniques, vertical layout based techniques, and projected layout based techniques. But most of the techniques suffer from repeated database scan, Candidate generation (Apriori Algorithms), memory consumption problem (FP-tree Algorithms) and many more for mining frequent patterns. As in retailer industry many transactional databases contain same set of transactions many times, to apply this thought, in this paper we present a new technique which is combination of present Apriori (improved Apriori) and FP-tree techniques that guarantee the better performance in terms of time and memory than classical aprioi algorithm.