Résumé
With the rapid development of information technology, many applications have to deal with potentially infinite data streams. In such a dynamic context, storing the whole data stream history is unfeasible and providing a high-quality summary is required for decision makers. A practical and consistent summarization method is the extraction of the frequent itemsets over temporal windows. Nevertheless, this method suffers from a critical drawback: results pile up quickly making the analysis either uncomfortable or impossible for users. In this paper, we propose to unify these results thanks to a synthesis method for multidimensional frequent itemsets based on a graph structure and taking advantage of the data hierarchies. We overcome a major drawback of the Tilted Time Window (TTW) standard framework by taking into account the data distribution. Experiments conducted on both synthetic and real datasets show that our approach can be applied to data streams.