An evolutionary multi-issue negotiation model

Intelligent agents are a promising development in improving the effectiveness of automated negotiations in the present complex business environments. Much research has been done that deal with a single issue, usually price, in a bilateral negotiation environment. On the other hand, in some studies on multiple issues, agents usually propose a combined offer on all the issues, or settle the negotiation issue by issue. We find that the combined offer on multiple issues is like a single-issue negotiation. Issue-by-issue settlement can be considered as a series of single-issue negotiations. Therefore a multi-issue negotiation model is proposed in this paper in which multiple issues are a part of the negotiation process, not like a single-issue settlement or combined offer on multiple issues. In the simulations, three issues, i.e. price, delivery time, and warranty, are considered, although it is possible to include more issues through the proposed system. In the simulations, a newly developed evolutionary computing technique called genetic network programming (GNP) is used and the characteristics and behaviors of agents are analyzed. To prove the effectiveness of the proposed system, the results of the proposed system are compared with those of conventional negotiation systems. (c) 2012 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.