An Automated Multi-Issue Negotiation Mechanism Based on Intelligent Agents in E- Commerce

This paper presents an agent-based automated negotiation mechanism for multi-issue negotiation in ecommerce. To avoid a deadlock in which both agents are unwilling to concede or refuse to disclose more information may arise in the traditional alternating-offer pattern, the information of both agents is considered completely private. In our model, the issues are divided into two categories (i.e., continuous issues and discrete issues). To accelerate the negotiation process, we allow concurrent negotiation threads for different combination value of discrete issue. The seller agent and the buyer agent can only respond by varying the price in each thread. The mechanism can discourage counter-speculation and effectively control fraud and misrepresentation in a certain extent. Through a case study, the capabilities of the proposed method are illustrated and the mechanism could be well suited for practical applications.