The Best Way to Instil Confidence is by Being Right An Evaluation of the Effectiveness of Case-Based Explanations in providing User Confidence

Abstract

Instilling confidence in the abilities of machine learning systems in end-users is seen as critical to their success in real world problems. One way in which this can be achieved is by providing users with interpretable explanations of the system's predictions. CBR systems have long been understood to have an inherent transparency that has particular advantages for explanations compared with other machine learning techniques. However simply suppling the most similar case is often not enough. In this paper we present a framework for providing interpretable explanations of CBR systems which includes dynamically created discursive texts explaining the feature-value relationships and a measure of confidence of the CBR systems prediction being correct. We also present the results of a preliminary user evaluation we have carried out on the framework.It is clear from this evaluation that being right is important. It appears that caveats and notes of caution when the system is uncertain damage user confidence.