Mining informative rule set for prediction

Li, Jiuyong and Shen, Hong and Topor, Rodney (2004) Mining informative rule set for prediction. Journal of Intelligent Information Systems, 22 (2). pp. 155-174. ISSN 0925-9902

[img]
Preview
PDF (Author's version)
Li_Shen_Topor_Author's_version.pdf

Download (199Kb)

Abstract

[Abstract]: Mining transaction databases for association rules usually generates a large number of rules, most of which are unnecessary when used for subsequent prediction. In this paper we define a rule set for a given transaction database that is much smaller than the association rule set but makes the same predictions as the association rule set by the confidence priority. We call this rule set informative rule set. The informative rule set is not constrained to particular target items; and it is smaller than the non-redundant association rule set. We characterise relationships between the informative rule set and non-redundant association rule set. We present an algorithm to directly generate the informative rule set without generating all frequent itemsets first that accesses the database less frequently than other direct methods. We show experimentally that the informative rule set is much smaller and can be generated more efficiently than both the association rule set and non-redundant association rule set.


Statistics for USQ ePrint 3547
Statistics for this ePrint Item
Item Type: Article (Commonwealth Reporting Category C)
Refereed: Yes
Item Status: Live Archive
Additional Information: Author's version deposited in accordance with the copyright policy of the publisher.
Depositing User: epEditor USQ
Faculty / Department / School: Historic - Faculty of Sciences - Department of Maths and Computing
Date Deposited: 19 Nov 2007 23:35
Last Modified: 02 Jul 2013 22:54
Uncontrolled Keywords: association rule mining; data mining; prediction; information rule set
Fields of Research (FOR2008): 08 Information and Computing Sciences > 0801 Artificial Intelligence and Image Processing > 080109 Pattern Recognition and Data Mining
Identification Number or DOI: doi: 10.1023/B:JIIS.0000012468.25883.a5
URI: http://eprints.usq.edu.au/id/eprint/3547

Actions (login required)

View Item Archive Repository Staff Only