This item is available under a Creative Commons License for non-commercial use only
Case-based approaches to classiﬁcation, as instance-based learning techniques, have a particular reliance on training examples that other supervised learning techniques do not have. In this paper we present the RDCL case proﬁling technique that categorises each case in a case-base based on its classiﬁcation by the case-base, the beneﬁt it has and/or the damage it causes by its inclusion in the case-base. We show how these case proﬁles can identify the cases that should be removed from a case-base in order to improve generalisation accuracy and we show what aspects of existing noise reduction algorithms contribute to good performance and what do not.
Delany, S. (2009) The Good, the Bad and the Incorrectly Classified: Profiling Cases for Case-Base Editing. L.McGinty & D. Wilson (eds) International Conference on Case Based Reasoning (ICCBR 2009), LNCS 5650 p.135-149 Springer Verlag. doi:10.1007/978-3-642-02998-1_11