An Efficient Automated Negotiation System Using Multi-attributes in the Online Environment

In this paper we propose an efficient negotiation agent system that guarantees the reciprocity of the attendants in a bilateral negotiation on the ecommerce. The proposed negotiation agent system exploits incremental learning based on artificial neural networks to generate counter-offers and is trained by the previous offers that have been rejected by the other party. During a negotiation, the software agents on behalf of the buyer and the seller negotiate each other by considering the multi-attributes of a product. The experimental results show that the proposed negotiation system achieves better agreements than other negotiation agent systems that can be operable under the realistic and practical environment. Furthermore, the proposed system carries out negotiations about twenty times faster than other negotiation systems on the average.