Finding association rules that trade support optimally against confidence

Article type: Research Article

Authors: Scheffer, Tobias

Affiliations: Humboldt-Universität zu Berlin, Department of Computer Science, Unter den Linden 6, 10099 Berlin, Germany. E-mail: scheffer@informatik.hu-berlin.de

Abstract: When evaluating association rules, rules that differ in both support and confidence have to be compared; a larger support has to be traded against a higher confidence. The solution which we propose for this problem is to maximize the expected accuracy that the association rule will have for future data. In a Bayesian framework, we determine the contributions of confidence and support to the expected accuracy on future data. We present a fast algorithm that finds the n best rules which maximize the resulting criterion. The algorithm dynamically prunes redundant rules and parts of the hypothesis space that cannot contain better solutions than the best ones found so far. We evaluate the performance of the algorithm relative to the Apriori algorithm.

DOI: 10.3233/IDA-2005-9405

Journal: Intelligent Data Analysis, vol. 9, no. 4, pp. 381-395, 2005