The goal of Knowledge Discovery is to extract knowledge from a set of data. Most common techniques used in knowledge discovery are based on clustering methods whose goal is to analyze a set of objects and obtain clusters based on the similarity among these objects.

A desirable characteristic of clustering results is that these should be easily understandable by domain experts. This is mainly achieved by means of both high level descriptions of clusters and discriminant descriptions of them. In fact, these are characteristics that exhibit the results of eager learning methods (such as ID3) and lazy learning methods when used for building lazy domain theories. We propose LazyCL, a procedure using a lazy learning method to produce explanations on clusters of unlabeled cases. This procedure has been used to propose a domain theory for the classification of melanomas in situ.