Digital Library
Close Browse articles from a journal
 
<< previous    next >>
     Journal description
       All volumes of the corresponding journal
         All issues of the corresponding volume
           All articles of the corresponding issues
                                       Details for article 4 of 8 found articles
 
 
  New probabilistic interest measures for association rules
 
 
Title: New probabilistic interest measures for association rules
Author: Hahsler, Michael
Hornik, Kurt
Appeared in: Intelligent data analysis
Paging: Volume 11 (2007) nr. 5 pages 437-455
Year: 2007-10-16
Contents: Mining association rules is an important technique for discovering meaningful patterns in transaction databases. Many different measures of interestingness have been proposed for association rules. However, these measures fail to take the probabilistic properties of the mined data into account. We start this paper with presenting a simple probabilistic framework for transaction data which can be used to simulate transaction data when no associations are present. We use such data and a real-world database from a grocery outlet to explore the behavior of confidence and lift, two popular interest measures used for rule mining. The results show that confidence is systematically influenced by the frequency of the items in the left hand side of rules and that lift performs poorly to filter random noise in transaction data. Based on the probabilistic framework we develop two new interest measures, hyper-lift and hyper-confidence, which can be used to filter or order mined association rules. The new measures show significantly better performance than lift for applications where spurious rules are problematic.
Publisher: IOS Press
Source file: Elektronische Wetenschappelijke Tijdschriften
 
 

                             Details for article 4 of 8 found articles
 
<< previous    next >>
 
 Koninklijke Bibliotheek - National Library of the Netherlands