GIAMS: A generic approach for mining indirect association rules in data streams 1

Abstract

An indirect association refers to an infrequent itempair, each item of which is highly co-occurring with a frequent itemset called a ``mediator''. Although indirect associations have been recognized as powerful patterns revealing interesting information hidden in many applications, such as recommendation ranking, substitute items or competitive items, common web navigation paths, etc., all work conducted up to date has focused on mining indirect associations from static data; almost no work, to our knowledge, has investigated how to discover this type of pattern from streaming data. This study considers the problem of mining indirect associations from data streams. Unlike contemporary research work on stream data mining that has investigated the problem by looking at different types of streaming models, we treat the problem in a generic way. We propose a generic window model that can represent all classical streaming models and retain user flexibility in defining new models. In this context, a generic algorithm is developed, which guarantees no false positive rules and bounded support errors as long as the window model is specifiable by the proposed generic model. Comprehensive experiments on both synthetic and real datasets show the effectiveness of the proposed approach as a generic way for finding indirect association rules within streaming data.