Negotiation modeling and e-shopping agents

Abstract

Negotiation is a key component of e-business. Like business in the real world, negotiation often occurs between two parties or among parties. Considering how to settle on the terms of a transaction, negotiation varies in duration and complexity depending on the market. In general, people are directly engaged in a negotiation process with common knowledge, their experience, and certain learning or reasoning strategies. The human involved negotiations accrue transaction costs that may be too high for either consumers or merchants. Software agent technologies can be used to automate several of the most time-consuming stages and help human combat information overload and expedite specific stages of the business process. The agent-mediated e-business systems are creating new markets (low-cost consumer-to-consumer goods) and beginning to reduce transaction cost in variety of business processes. With a rational negotiation model, software agents should be able to negotiate in an intelligent way on behalf of the real-world parties they represent. However, one of the challenging problems here is negotiation modeling. How to precisely reflect human's negotiation process on different levels is a crucial point. This paper presents our studies on negotiation modeling and demonstrates the negotiation model based e-shopping agents.