Classification is one of major tasks in case-based reasoning (CBR) and many studies have been done for analyzing properties of case-based classification (1,14,10,15,12,9,13,7]. However, these studies only consider numerical similarity measures whereas there are other kind of similarity measure for differnet tasks. Among these measures, HYPO system [2,3] in a legal domain uses a similarity measure based on set inclusion of differences of attributes in cases.
展开▼