Algorithms for discovering potentially interesting patterns. (1st January 2011)

• Record Type: Journal Article
• Authors: Singh, Raj; Johnsten, Tom; Raghavan, Vijay V.; Xie, Ying
• Is Part Of: International journal of granular computing, rough sets and intelligent systems. Volume 2:Number 2(2011)
• Page Start: 107
• Page End: 122
• Publication Date: 2011-01-01
• Subjects: data mining -- potential interesting patterns -- positive patterns -- negative patterns -- association rules -- closed frequent itemsets; Intelligent agents (Computer science) -- Periodicals; 006.3
• DOI: 10.1504/IJGCRSIS.2011.043366
• Languages: English
• ISSNs: 1757-2703

Abstract

A pattern discovered from a collection of data is usually considered potentially interesting if its information content can assist the user in their decision making process. To that end, we have defined the concept of potential interestingness of a pattern based on whether it provides statistical knowledge that is able to affect one's belief system. In this paper, we introduce two algorithms, referred to as All-Confidence based Discovery of Potentially Interesting Patterns (ACDPIP) and ACDPIP-Closed, to discover patterns that qualify as potentially interesting. We show that the ACDPIP algorithm represents an efficient alternative to an algorithm introduced in our earlier work, referred to as Discovery of Potentially Interesting Patterns (DAPIP). However, results of experimental investigations also show that the application of ACDPIP is limited to sparse datasets. In response, we propose the algorithm ACDPIP-Closed designed to effectively discover potentially interesting patterns from dense datasets.