Petra Perner
Institute of Computer Vision and applied Computer Sciences, IBaI, Leipzig
Title: New Ways to present the Results of a Data Mining Process to an Expert
Biography
Biography: Petra Perner
Abstract
Data Mining methods can easily work on applications with many features and come up with decision rules, relations or patterns for the application. The results should be reported in such a way that an expert can overlook them. Often it is forgotten that the quality of the presentation depends on the kind of attributes you are using and for e.g. the decision tree induction method. Therefore, attribute construction or summarization in a way that many attributes represent a feature is necessary. We show on different applications how this can be done and what quality of representation can be achieved. We also show what kind of representation binary and n-ary decision tree induction methods can bring out.