4 Aug 14:15: Using Collaborative Interest and Transition Models to Predict Visitor Locations in Museums

  • Lecturer: Fabian Bohnert, Ulm University
  • Time: 4 August 2008 at 14.15
  • Venue: Room B222 (Exactum building, 2nd floor), Department of Computer Science, University of Helsinki

Museums offer vast amounts of information, but a visitor's receptivity and time are typically limited. Hence, a visitor might be confronted with the challenge of selecting the personally interesting exhibits to view within the available time. Electronic handheld guides offer the opportunity to improve a visitor's experience by recommending exhibits of interest, and personalising the content delivered for these exhibits. The first step in this recommendation process is the accurate prediction of a visitor's activities and interests from non-intrusive observations of his/her behaviour. In this talk, we present two adaptive collaborative models for predicting a visitor's next locations in a museum, and an ensemble model that combines their predictions. We also discuss two alternative prediction mechanisms (set and sequence). Our experimental results from a study using a small dataset of museum visits are encouraging, with the ensemble model yielding the best performance overall.

Fabian Bohnert holds a Diplom degree in econo-mathematics (eqvl. Master in Econo-Mathematics) from Ulm University (Ulm, Germany), with majors actuarial studies and data mining. His current research towards his Ph.D. degree at Monash University (Melbourne, Australia) is based in the fields of user modelling and personalisation. He is particularly interested in adaptive statistical techniques for user modelling and recommendation in physical spaces with organised information. When undertaking his Diplom thesis and during internships in industry his research involved stochastic data modelling and data mining.

Last updated on 4 Aug 2008 by Visa Noronen - Page created on 4 Aug 2008 by Visa Noronen