The DecisionTheoretic Video Advisor
Hien Nguyen and Peter Haddawy Decision Systems and Artificial Intelligence Lab (DSAIL) Dept. of Electrical Engineering and Computer Science University of WisconsinMilwaukee Milwaukee, WI 53201
We describe ongoing work toward development of a decisiontheoretic agent to help users choose videos based on their preferences. The DIVA (Decision Theoretic Interactive Video Advisor) system elicits user preferences using a casebased technique. Hard constraints are used to permit the user to communi cate temporary deviations from his basic preferences. If the user is not happy with the system's recommen dations, he can provide feedback, which is used to modify the represented preferences and generate a new set of recommendations. We describe the fundamen tal algorithms, the implementation, and some results from some initial experimentation.