Applying hybrid case-based reasoning in agent-based negotiations for supply chain management

Abstract

In recent years, enormous research effort has been spent on the development of multi-agent systems to automate buyer–seller negotiations in supply chain management (SCM) applications. In many of these agent-based negotiation systems, the negotiation process is restricted to the stage when agents interact to exchange bargaining offers; activities in the pre-bargaining and post-bargaining stages are ignored. With a more comprehensive perspective, the negotiation lifecycle comprises a number of phases including the pre- and post-bargaining phases, in addition to the phase when participants interact to bargain. In this paper, a hybrid case-based reasoning approach is applied in the pre- and post-negotiation phases to support adaptive negotiation strategy for buyer–seller negotiations in SCM applications. When a new negotiation problem arrives, a similar previous negotiation case is retrieved from the case database and its solutions are recommended for inferring the negotiation parameters. The recommended parameters have to be adjusted to suit the new negotiation problem. Subsequent to negotiation completion, negotiation parameters and the negotiation outcome are analyzed and evaluated. After the evaluation, the new negotiation case, including the problem descriptions and solutions, is retained in the case database for future applications.