An Evaluation Framework for Consumer Decision Making in Future Energy Markets
Thu. 27 Oct. 2011
Mandeville Building T09-67
|A myriad of personalization and recommendation techniques have been proposed for supporting users in making their decisions in Web environments. However, most techniques are only evaluated and compared to each other based on offline experimentation with datasets. In future energy domains personalization mechanisms and recommendation approaches are deemed particularly useful in order to foster consumer decision making due to the variety of different tariffs or dynamic pricing mechanisms. Therefore, the talk will present an evaluation framework on top of the Power Trading Agent Competition (Power TAC) infrastructure to assess different decision support strategies in the context of such a mixed-initiative human-system interaction. It will consequently explore different user support and recommendation scenarios that include explanations of recommendations and conversational interaction strategies.
|Markus Zanker is an Associate Professor in the Department for Applied Informatics and the director of the study program Information Management at Alpen-Adria-Universität Klagenfurt, Austria. He is also cofounder and director of ConfigWorks GmbH, a provider of interactive selling technology. His research interests focus on knowledge-based systems, particularly in the fields of interactive sales applications, such as product configuration and recommendation. He also works on knowledge acquisition and user modeling for personalization. He is an associate editor of the International Journal of Human-Computer Studies and he was co-chairing the program committee of the 4th ACM Conference on Recommender Systems in 2010. He is a co-author of the first introductory book on Recommender Systems that is published by Cambridge University Press.|
This research seminar is organised by the Learning Agents Research Group at Erasmus (LARGE).