Validation of Case-Based Reasoning Systems

We present an approach to systematically describing case-based reasoning systems by different kinds of criteria. One main requirement was the practical relevance of these criteria and their usability for real-life applications. We report on the results we achieved from a case study carried out in the INRECA 1 Esprit project. To avoid terminological conflicts with views/definitions of validation known from literature (Abel, 1996; O'Keefe & O'Leary, 1993) we classify our approach as evaluation of CBR systems as we already did in the past (e.g., Althoff, 1996). However, we believe that the results achieved in the INRECA case study and its further impacts will contribute to define the process of validating CBR systems more precisely. Thus, the title of this paper is meant as a goal that is to achieve and should motivate the reader to contribute to its discussion (as well as to its achievement).