This paper provides a definition of automated negotiation within electronic commerce. It outlines two barriers to automated negotiation, the ontology issue and the strategy problem. State of the art overviews are given of automated negotiation, specifically Negotiation Support Systems, intelligent agents, the auction mechanism, and online marketspaces. Both academic research and currently functional systems are covered, and several World Wide Web addresses are given for readers who wish to investigate further on their own. 1 1 While every attempt is made to provide current URL locations, the Web changes more quickly than print media can ever capture. Hence, some of the URLs may not be current or correct by the time this article appears. We will try to keep our Negotiation Project web site, http://haas.berkeley.edu/~citm/nego-proj.html, current with respect to these addresses. 2 1.

Abstract. We describe a system for bilateral negotiations in which artificial agents are generated by an evolutionary algorithm (EA). The negotiations are governed by a finite-horizon version of the alternating-offers protocol. Several issues are negotiated simultaneously. We first analyse and validate the outcomes of the evolutionary system, using the game-theoretic subgame-perfect equilibrium as a benchmark. We then present two extensions of the negotiation model. In the first extension agents take into account the fairness of the obtained payoff. We find that when the fairness norm is consistently applied during the negotiation, agents reach symmetric outcomes which are robust and rather insensitive to the actual fairness settings. In the second extension we model a competitive market situation where agents have multiple bargaining opportunities before reaching the final agreement. Symmetric outcomes are now also obtained, even when the number of bargaining opportunities is small. We furthermore study the influence of search or negotiation costs in this game.

This paper describes our ongoing R&D effort in developing a replicable, Web-based negotiation server to conduct bargaining-type negotiations between clients (i.e., buyers and sellers) in e-commerce. Multiple copies of this server can be paired with existing Web-servers to provide negotiation capabilities. Each client can select a trusted negotiation server to represent his/her interests. Web-based GUI tools are used by clients in a build-time registration process to specify the requirements, constraints, negotiation strategic rules, and preference scoring methods related to the buying or selling of a product. The registration information is used by the negotiation servers to conduct negotiations automatically on behalf of the clients. In this paper, we present the architecture of the negotiation server and the framework for automated negotiations, and describe a number of communication primitives, which make up the negotiation protocol. We have developed a constraint satisfaction processor (CSP) to evaluate a negotiation proposal against the registered constraints. An Event-Trigger-Rule (ETR) server manages events and triggers the execution of strategic rules, which may relax constraints, notify clients, or perform other operations. Strategic rules can be added and modified at run-time to deal with the dynamic nature of negotiations. A cost-benefit analysis performs quantitative analysis of alternative negotiation conditions. We have implemented a prototype system to demonstrate automated negotiations among buyers and suppliers in a supply chain management system.

Due to the rapid growth of electronic environments (such as the Internet) much research is currently being performed on autonomous trading mechanisms. This report contains an overview of the current literature on negotiations in the fields of game theory and artificial intelligence (AI). Game theorists have successfully developed and analyzed a variety of bargaining models in the past decades. We give an extensive overview of this theoretical work. In particular, research performed in the fields of cooperative and non-cooperative bargaining, bargaining with incomplete information, and bargaining over multiple issues is evaluated. The use and shortcomings of game-theoretical concepts in practical applications is discussed. Simplifying assumptions frequently made in game-theoretical analyses, such as assumptions of perfect rationality and common knowledge, do not need to be made if the behavior of boundedly-rational negotiating agents is modeled directly, for instance using tech...

Electronic brokerage is regarded as core functionality in overcoming many current limitations of Internet Commerce. In this paper, we describe current approaches to brokerage services, both, on the Internet and for distributed object systems and analyze how brokerage influences current business models for electronic commerce. We then describe OFFER, a project that focuses on advanced models for brokerage on the Internet. We investigate a variety of brokerage services provide a high-level specification for core components of a generic brokerage service on the Internet.

Coupling of Classes (UML Class Diagram) All auctions announce their commencement and the item(s) for sale, as well as a possible reserve price and minimum bid increment. A sealed auction has a publicly announced deadline, and will make no information about the current bids available to any future bidders until the auction is over, at which time the winner(s) is (are) announced. An open auction will make information about current bids available to any future bidders until the auction is over, at which time the winner(s) is (are) announced. One can open an auction with the e-broker operation startAuction(). Currently this can be either an English, a Vickrey or a First Price Sealed Bid Auction, which are described in Table 1. Through polymorphic messaging, the operations of the appropriate type of auction are triggered afterwards. For example, different auctions, closed via stopAuction() will compute the winners in different manners. Moreover, an English Auction has additional operations...

A systematic validation of evolutionary techniques in the field of bargaining is presented. For this purpose, the dynamic and equilibrium-selecting behavior of a multi-agent system consisting of adaptive bargaining agents is investigated. The agents' bargaining strategies are updated by an evolutionary algorithm (EA), an innovative computational method to simulate collective learning in societies of boundedly-rational agents. Negotiations between the agents are governed by the well-known "alternating-offers" protocol. Using this protocol, the influence of various important factors (like the finite length of the game, time preferences, exogenous breakdown, and risk aversiveness) is investigated. We show that game theory can be used successfully to interpret the equilibrium-selecting behavior observed in computational experiments with adaptive bargaining agents. Agreement between theory and experiment is especially good when the agents experience an intermediate time pressure. D...

We believe that the Internet and related technologies will help change the role of the purchasing department, from a transaction-oriented function to a more managerial one that focuses on establishing and maintaining relationships with suppliers, third parties, and internal customers, and leveraging corporate buying power. In its new role, procurement will also manage the technological infrastructure necessary to either automate transactions fully or to empower end users to perform many transactions without the direct involvement of the purchasing personnel. These trends have major implications on procurement processes, policies, and technologies, and change management approaches. We discuss this statement by looking at the state of the art and trends in Internet-based procurement systems, and by using the results of an empirical survey that we conducted recently. Keywords: Internet; Electronic Commerce; Purchasing; Business Process Reengineering; Polls & Surveys. 1 Introduction Eme...

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

This paper describes IBIZA, a workbench for designing electronic markets for information products. IBIZA is a testbed for performing computational experiments about market-based approaches (e.g., auctions) to support negotiations between buyers and sellers. We outline the key technical and economic issues encountered in the design of IBIZA. We use examples from our work on designing a software agent-based electronic market for automated model development illustratively.