Finding interesting patterns using user expectations

One of the major problems in the field of knowledge discovery (or data mini ng) is the interestingness problem. Past research and applications have fou nd that, in practice, it is all too easy to discover a huge number of patte rns in a database. Most of these patterns are actually useless or uninteres ting to the user. But due to the huge number of patterns, it is difficult f or the user to comprehend them and to identify those interesting to him/her . To prevent the user from being overwhelmed by the large number of pattern s, techniques are needed to rank them according to their interestingness. I n this paper, we propose such a technique, called the user-expectation meth od. In this technique, the user is first asked to provide his/her expected patterns according to his/her past knowledge or intuitive feelings. Given t hese expectations, the system uses a fuzzy matching technique to match the discovered patterns against the user's expectations, and then rank the disc overed patterns according to the matching results. A variety of rankings ca n be performed for different purposes, such as to confirm the user's knowle dge and to identify unexpected patterns, which are by definition interestin g. The proposed technique is general and interactive.