Closed Frequent Itemset Mining Using Directed Acyclic Graph Based on MapReduce

Abstract In various industries, the set of frequently occurring items is required for taking important decisions. There are few algorithms which are used to extract frequently occurring item sets from the given database. The basic problem with these algorithms is the generation of candidate item sets before producing frequent item set. This causes waste of time and space. FP Growth is the most efficient and scalable approach among the existing techniques. But it still generates a massive number of conditional FP trees. So we propose an improvement for FP tree based technique which does not use conditional FP trees. It generates FP trees using Directed Acyclic Graph (DAG) structure. For this we propose an algorithm that scans the database and generates FP trees as DAG so that we can generate frequent patterns directly using DAG without generating conditional FP trees. Also the paper discusses the system with respect to parallel mining using MapReduce concept. This proves to be better in terms of time and space compared to single machine environment.