An Agent-based Platform for Online Auctions
Abstract
This paper proposes a web-based agent platform for E-commercewhich allows humans and software agents to perform automatic auctions over the Internet. Internet-basedauction is a profitable, exciting and dynamic part of E-commerce. However, the lack of standardonnegotiation protocol between agents and an auctioneer makes full automation of E-commerceinfeasible. Hence, we design a complete architecture and a set of negotiation protocols based on advanced agent technologies. Moreover, we evaluatedthenegotiation protocol using a Markov chain model. Our experimental results show that (1) the Markov chain can model independently simulatedbidder's behaviour accurately, (2) a wider range of bidder 's behaviour can be simulatedwith agents having partial knowledge of other bidders' willingness to bid and the closing time. In summary, our agent-based platform can incorporate realistic scenarios for simulation in online auction and other E-commerce applications. Keywords: software agent, E-commerce, negotiation protocol, Markovchain 1
Authors: Anson Lee, Michael Rung-Tsong Lyu, Irwin King