‘Forgetting functions’ in the context of data streams for the benefit of decision-making

With development of new technologies, many applications generate large volumes of data that all need to be collected and processed instantly. Flowing as streams, these data are usually continuous, voluminous and cannot be stored integrally as persistent data. In this context, new systems called Data Stream Management Systems (DSMS) have emerged for processing data streams on the fly. However, in some applications, we can analyse expired data. Treating a data stream is performed according to a well defined temporal window. Beyond this window, data are discarded or lost forever. Some applications need to keep track of expired data. Thus, it is necessary to retain a compact structure (synopsis or summary) of streams in order to answer a wide range of needs. In this paper, we are interested in developing a generic summary structure for expired data. In order to preserve the possibility of performing future analysis, we suggest to establish specifications on these expired data. These specifications called forgetting functions define summaries (by aggregation) to be retained among the data to `forget'. We apply our approach to a real dataset for building summaries. A data cube is set up to answer a variety of needs.