Fast mining and forecasting of complex time-stamped events

Given huge collections of time-evolving events such as web-click logs, which consist of multiple attributes (e.g., URL, userID, timestamp), how do we find patterns and trends? How do we go about capturing daily patterns and forecasting future events? We need two properties: (a) effectiveness, that is, the patterns should help us understand the data, discover groups, and enable forecasting, and (b) scalability, that is, the method should be linear with the data size. We introduce TriMine, which performs three-way mining for all three attributes, namely, URLs, users, and time. Specifically TriMine discovers hidden topics, groups of URLs, and groups of users, simultaneously. Thanks to its concise but effective summarization, it makes it possible to accomplish the most challenging and important task, namely, to forecast future events. Extensive experiments on real datasets demonstrate that TriMine discovers meaningful topics and makes long-range forecasts, which are notoriously difficu...

• Type: Journal
• Year: 2012
• Where: KDD
• Authors: Yasuko Matsubara, Yasushi Sakurai, Christos Faloutsos, Tomoharu Iwata, Masatoshi Yoshikawa
• Keywords: Data Mining, KDD 2012, Long Range Forecasts, Management Database, Subject Descriptors