Designing Templates for Mining Association Rules

Current approaches to data mining usually address specific user requests, while no general design criteria for the extraction of association rules are available for the end-user. In this paper, we propose a classification of association rule types, which provides a general framework for the design of association rule mining applications. Based on the identified association rule types, we introduce predefined templates as a means to capture the user specification of mining applications. Furthermore, we propose a general language to design templates for the extraction of arbitrary association rule types.