Learning the Structure of Utility Graphs Used in Multi-issue Negotiation through Collaborative Filtering

Abstract

Graphical utility models represent powerful formalisms for modeling complex agent decisions involving multiple issues [2]. In the context of negotiation, it has been shown [10] that using utility graphs enables reaching Pareto-efficient agreements with a limited number of negotiation steps, even for high-dimensional negotiations involving complex complementarity/ substitutability dependencies between multiple issues. This paper considerably extends the results of [10], by proposing a method for constructing the utility graphs of buyers automatically, based on previous negotiation data. Our method is based on techniques inspired from item-based collaborative filtering, used in online recommendation algorithms. Experimental results show that our approach is able to retrieve the structure of utility graphs online, with a high degree of accuracy, even for highly non-linear settings and even if a relatively small amount of data about concluded negotiations is available.

This is a preliminary version of this work, as it resulted from a presentation at the PRIMA’05 workshop in September 2005. At the time of the publication of these post-proceedings (2009), however, a more definitive version of this work has already appeared as a book chapter in “Rational, Robust, and Secure Negotiations in Multi-Agent Systems”, Ito, T.; Hattori, H.; Zhang, M.; Matsuo, T. (Eds.), Studies in Computational Intelligence Series, vol. 89., Springer-Verlag, 2008. Interested readers may consult either version.