Finding top-N chance patterns with KeyGraph®-based importance

Authors:
Yoshiaki Okubo;Makoto Haraguchi;Sachio Hirokawa
Affiliations:
Graduate School of Information Science and Technology, Hokkaido University, Sapporo, Japan;Graduate School of Information Science and Technology, Hokkaido University, Sapporo, Japan;Research Institute for Information Technology, Kyushu University, Fukuoka, Japan
Venue:
KES'11 Proceedings of the 15th international conference on Knowledge-based and intelligent information and engineering systems - Volume Part II
Year:
2011

Citing 9
Cited 0

Efficient mining of association rules using closed itemset lattices

Information Systems
Formal Concept Analysis: Mathematical Foundations

Formal Concept Analysis: Mathematical Foundations
Alternative Interest Measures for Mining Associations in Databases

IEEE Transactions on Knowledge and Data Engineering
Fast Algorithms for Mining Association Rules in Large Databases

VLDB '94 Proceedings of the 20th International Conference on Very Large Data Bases
Discovery of Chances Underlying Real Data

Progress in Discovery Science, Final Report of the Japanese Discovery Science Project
Discover Risky Active Faults by Indexing an Earthquake Sequence

DS '99 Proceedings of the Second International Conference on Discovery Science
Towards Rare Itemset Mining

ICTAI '07 Proceedings of the 19th IEEE International Conference on Tools with Artificial Intelligence - Volume 01
Finding Rare Patterns with Weak Correlation Constraint

ICDMW '10 Proceedings of the 2010 IEEE International Conference on Data Mining Workshops
An algorithm for extracting rare concepts with concise intents

ICFCA'10 Proceedings of the 8th international conference on Formal Concept Analysis

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, as our first proposal, we discuss a method for finding a rare pattern, called a chance pattern, which connects a pair of more frequent patterns. Particularly, our chance pattern is defined with a KeyGraph®-based importance of patterns. More concretely speaking, a chance pattern is a pattern C which often appears in a part of documents containing a frequent pattern XL as well as in those containing another pattern XR, that is, confidence values of association rules, XL ⇒ C and XR ⇒ C, are relatively high. It would be expected that such a chance pattern C revea XR. We design clique-search-based algorithms for finding chance patterns with Top-N confidence values.