Efficient algorithms for hierarchical online rule mining

Abstract

Association rule Mining, as one of the technologies equipped with Data Mining, deals with the challenge of mining the informative associations from the fast accumulating data. From the past decade, the research community has been busy progressing day by day towards the task of rule mining. Hierarchical Online rule mining opens a new trend to achieve an online approach in real sense. In this thesis, we further develop the theory of Hierarchical Association Rules. Notably, we propose a new algorithm that further improves the efficiency of the previously proposed works in three aspects. In phase 1 of the rule-mining problem, we introduce Hierarchy Aware Counting and Transaction Reduction concepts that reduce the computational complexity by a considerable factor. We also propose Redundancy Check while generating rules in phase 2 of the problem. We propose a modified version of a Synthetic Data Generator that deals with Hierarchical data and evaluate the performance of the proposed new algorithm. We finally discuss the issues that can form the future perspectives of the proposed new approach.