ECML PKDD 2008

A Visualization-Based Exploratory Technique for Classifier Comparison with respect to Multiple Metrics and Multiple Domains

Classifier performance evaluation typically gives rise to a multitude of results that are difficult to interpret. On the one hand, a variety of different metrics can be applied, each adding a little bit more information about the classifiers than the others; and on the other hand, evaluation must be conducted on multiple domains to get a clear view of the classifier's general behaviour. In this demo, we present a visualization tool that allows a user to study the different classifiers with respect to both a variety of metrics and domains. We take the view that classifier evaluation should be done on an exploratory basis. In particular, we suggest mining the results of the study to draw valid and relevant knowledge about the behaviour of our algorithms. The tool presented in this demo will enable such a process.