Utility elicitation is an important component of many applications, such as decision support systems and recommender systems. Such systems query the users about their preferences and give recommendations based on the system’s belief about the utility function. Critical to these applications is the acquisition of prior distribution about the utility parameters and the possibility of real time Bayesian inference. In this paper we consider Monte Carlo methods for these problems.
Lecture Notes in Computer Science: 6th International Conference, Lion 6, Paris, France, January 16-20, 2012, Revised Selected Papers, 2012, p. 503-508