Associative classification with prediction confidence

Do, T. D., Hui, S. C. and Fong, A. C.M. (2006) Associative classification with prediction confidence. In: Advances in Machine Learning and Cybernetics. Series: Lecture notes in computer science (3930). Springer: Berlin ; Heidelberg, pp. 199-208. ISBN 9783540335849 (doi: 10.1007/11739685_21)

Abstract

Associative classification which uses association rules for classification has achieved high accuracy in comparison with other classification approaches. However, the confidence measure which is conventionally used for selecting association rules for classification may not conform to the prediction accuracy of the rules. In this paper, we propose a measure called prediction confidence to measure the prediction accuracy of association rules. In addition, a probabilistic-based approach for estimating prediction confidence of association rules is given and its performance is evaluated. The use of prediction confidence helps improve the performance of associative classifiers.

• Item Type: Book Sections
• Additional Information: <br>4th International Conference, ICMLC 2005, Guangzhou, China, August 18-21, 2005, Revised Selected Papers.</br> <br>Online ISBN: 9783540335856</br>
• Status: Published
• Glasgow Author(s) Enlighten ID: Fong, Dr Alvis Cheuk Min
• Authors: Do, T. D., Hui, S. C., and Fong, A. C.M.
• College/School: College of Science and Engineering > School of Computing Science
• Publisher: Springer
• ISSN: 0302-9743
• ISBN: 9783540335849