Introduction

The DUMPERS project ran from January 2003 to August 2007. In this project we developed methods for adding adaptive navigation support for users of websites. Goal of this project was to extend existing methods with extra components like exploration of the effect of recommendation by using techniques from the field of reinforcement learning. We wused locally stored user models to provide the information about the individual users needed for personal recommendation without violating the privacy of the users. These extensions enable users to search the sites more efficiently.