A new approach for evaluating internal cluster validation indices

A vast number of different methods are available for unsupervised classification. Since no algorithm and parameter setting performs best in all types of data, there is a need for cluster validation to select the actually best-performing algorithm. Several indices were proposed for this purpose without using any additional (external) information. These internal validation indices can be evaluated by applying them to classifications of datasets with a known cluster structure. Evaluation approaches differ in how they use the information on the ground-truth classification. This paper reviews these approaches, considering their advantages and disadvantages, and then suggests a new approach.