Mining optimal class association rule set

Jiuyong Li, Hong Shen, Rodney Topor

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

12 Citations (Scopus)

Abstract

We define an optimal class association rule set to be the minimum rule set with the same prediction power of the complete class association rule set. Using this rule set instead of the complete class association rule set we can avoid redundant computation that would otherwise be required for mining predictive association rules and hence improve the efficiency of the mining process significantly. We present an efficient algorithm for mining the optimal class association rule set using an upward closure property of pruning weak rules before they are actually generated. We have implemented the algorithm and our experimental results show that our algorithm generates the optimal class association rule set, whose size is smaller than 1/17 of the complete class association rule set on average, in significantly less time than generating the complete class association rule set. Our proposed criterion has been shown very effiective for pruning weak rules in dense databases.

Original languageEnglish
Title of host publicationAdvances in Knowledge Discovery and Data Mining - 5th Pacific-Asia Conference, PAKDD 2001, Proceedings
EditorsDavid Cheung, Graham J. Williams, Qing Li
PublisherSpringer Verlag
Pages364-375
Number of pages12
ISBN (Print)3540419101, 9783540419105
DOIs
Publication statusPublished - 2001
Externally publishedYes
Event5th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2001 - Kowloon, Hong Kong
Duration: 16 Apr 200118 Apr 2001

Publication series

NameLecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)
Volume2035
ISSN (Print)0302-9743

Conference

Conference5th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2001
Country/TerritoryHong Kong
CityKowloon
Period16/04/0118/04/01

Fingerprint

Dive into the research topics of 'Mining optimal class association rule set'. Together they form a unique fingerprint.

Cite this