A Machine Learning Approach for Mechanism Selection in Complex Negotiations

Publication Type:

Conference Paper

Source:

Modern Approaches to Agent-based Complex Automated Negotiation, Springer Japan (2016)

URL:

sites/default/files/ACANegoMechanism2015Proceeding.pdf

Abstract:

<div>
<div>
<div>
<p>Automated negotiation mechanisms can be helpful in con- texts where users want to reach mutually satisfactory agreements about issues of shared interest, especially for complex problems with many interdependent issues. A variety of automated negotiation mechanisms have been proposed in the literature. The effectiveness of those mech- anisms, however, may depend on the characteristics of the underlying negotiation problem (e.g. on the complexity of participant’s utility func- tions, as well as the degree of conflict between participants). While one mechanism may be a good choice for a negotiation problem, it may be a poor choice for another. In this paper, we pursue the problem of select- ing the effective negotiation mechanism by (1) defining a set of scenario metrics to capture the relevant features of negotiation problems, (2) eval- uating the performance of a range of negotiation mechanisms on a diverse test suite of negotiation scenarios, (3) applying machine learning tech- niques to identify which mechanisms work best with which scenarios, and (4) demonstrating that using these classification rules for mecha- nism selection enables significantly better negotiation performance than any single mechanism alone.</p>
</div>
</div>
</div>