Enhancing Itemset Tree Rules and Performance
Jay B. Lewis, Ryan Benton, David M. Bourrie, Jennifer Lavergne · 2019
Association mining is the process of discovering relationships between items in a data set, where a group of items forms an itemset. A problem with the typical association mining approach is a large number of the generated frequent itemsets typically do not contain any items of interest to the user. Targeted association mining solves this by only deriving itemsets that include the items specified within a user's query. A popular targeted approach is the Itemset Tree, which consists of an index tree structure and algorithms for search and rule generation. Numerous enhancements to improve the Itemset Tree efficiency or extend its capability have been proposed. However, two major problems exist. First, the itemset generation process utilized by the Itemset Tree does not leverage the Apriori Principle, resulting in the unnecessary and costly generation of infrequent itemsets. Second, the Itemset Tree rule generation process has restrictions that prevent some rules containing the user query from being generated; as a result, the user misses useful information. In this paper, we offer a redesigned generation process resulting in faster itemset generation (milliseconds versus minutes) and expanded rulesets.