Scalable APRIORI-based frequent pattern discovery

Date

2009-04-28T17:44:31Z

Authors

Chester, Sean

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

Frequent itemset mining, the task of finding sets of items that frequently occur to- gether in a dataset, has been at the core of the field of data mining for the past sixteen years. In that time, the size of datasets has grown much faster than has the ability of existing algorithms to handle those datasets. Consequentely, improvements are needed. In this thesis, we take the classic algorithm for the problem, A Priori, and improve it quite significantly by introducing what we call a vertical sort. We then use the benchmark large dataset, webdocs, from the FIMI 2004 conference to contrast our performance against several state-of-the-art implementations and demonstrate not only equal efficiency with lower memory usage at all support thresholds, but also the ability to mine support thresholds as yet unattempted in literature. We also indicate how we believe this work can be extended to achieve yet more impressive results.

Description

Keywords

data mining, apriori, frequent itemset mining, machine learning

Citation