ABSTRACT
Multi-objective bargaining is a challenging business model for B2C or B2B Internet applications. Our visual bargaining agent COSIMA builds on cooperative database technology like Preference SQL or Preference XPATH, which can efficiently implement \linebreak[4] multi-dimensional search engines with a Pareto-optimality semantics to find best alternative offers. COSIMA is a smart avatar with dynamically generated speech output. We have implemented several well-known bargaining strategies for a sample e-shop, where the customer can bargain on more attributes than just the price. The life-like appearance of COSIMA is supported by randomizing her bargaining tactics and by expressing visual emotions during bargaining. She can also learn and adapt dynamically to various bargaining preferences of the customers. The COSIMA prototype is carefully engineered by means of component-ware and IT-standards including SQL, XML and Java. This makes it scalable even to very large e-shop databases. Measurements show that this advanced user interface of COSIMA requires only a small overhead of a few seconds, including the bidding process. Thus real-time performance using state-of-the art software components and hardware is feasible. A preliminary user feedback has been very encouraging. COSIMA gave her debut to a large professional audience at the computer fair CeBIT 2002.
- Second International Workshop on Negotiations in electronic markets - beyond price discovery. In conjunction with the 12th International Conference on Database and Expert Systems Applications - DEXA 2001. http://www.dexa.org/dexa01/index.html.Google Scholar
- E. André and T. Rist. Adding life-like synthetic characters to the web. In Cooperative Information Agents IV, Lecture Notes of Artificial Intelligence, pages 1--13, 2000. Google ScholarDigital Library
- First International Workshop on Negotiations in electronic markets beyond price discovery. In conjunction with the 11th Int. Conf. on Database and Expert Systems Applications DEXA 2000.Google Scholar
- R. L. Keeney and H. Raiffa. Decisions with Multiple Objectives: Preferences and Value Tradeoffs. Wiley, 1976.Google Scholar
- W. Kießling. Foundations of preferences in database systems. Technical report 2001-8, October 2001.Google Scholar
- W. Kießling, S. Fischer, S. Holland, and T. Ehm. Design and implementation of COSIMA -a smart and speaking e-sales assistant. In Third International Workshop on Advanced Issues of E-Commerce and Web-Based Information Systems, pages 21--30, San Jose, California USA, June 2001. Google ScholarDigital Library
- W. Kießling, B. Hafenrichter, S. Fischer, and S. Holland. Preference XPATH: A query language for e-commerce. In 5th International Conference WirtschaftsInformatik, pages 427--440, Augsburg, Germany, September 2001.Google Scholar
- W. Kießling, S. Holland, S. Fischer, and T. Ehm. COSIMA - your smart, speaking e-salesperson. In ACM-SIGMOD International Conference Management of Data, page 600, Santa Barbara, California USA, May 2001. Google ScholarDigital Library
- W. Kießling and G. Köstler. Preference SQL - design, implementation, experiences. Technical report 2001-7, October 2001.Google Scholar
- T.-P. Liang and H.-S. Doong. Effect of bargaining in electronic commerce. In International Workshop on Advanced Issues of E-Commerce and Web-Based Information Systems, pages 174--181, Santa Clara - California, USA, April 1999. Google ScholarDigital Library
- A. B. Loyall and J. Bates. Personality-rich believable agents that use language. In W. L. Johnson and B. Hayes-Roth, editors, Proceedings of the First International Conference on Autonomous Agents (Agents'97), pages 106--113, Marina del Rey, CA, USA, 1997. ACM Press. Google ScholarDigital Library
- R. D. Luce and H. Raiffa. Games and Decisions. Harvard University Press, January 1967.Google Scholar
- N. G. Mankiw. Principles of Economics. Thomson Learning, November 2000.Google Scholar
- H. Raiffa. The Art and Science of Negotiation. Harvard University Press, July 1990.Google Scholar
- M. A. Walker, J. E. Cahn, and S. J. Whittaker. Linguistic style improvisation for lifelike computer characters. In Papers from the 1996 AAAI Workshop on Entertainment and AI/A-Life, pages 61--68, Portland, USA, 1996. AAAI Press.Google Scholar
Index Terms
- The COSIMA prototype for multi-objective bargaining
Recommendations
Leader-Based Collective Bargaining: Cooperation Mechanism and Incentive Analysis
We study leader-based collective bargaining LCB, under which a leading buyer leader and a following buyer follower form an alliance to jointly purchase a common component from a supplier. Although the leader and the follower cooperate in their component ...
A Cooperation Mechanism Among Seller Agents
JCAI '09: Proceedings of the 2009 International Joint Conference on Artificial IntelligenceThis paper proposes a cooperation mechanism among seller agents and builds a model based on multi-agent system. In the model, a manger agent has been set to watch activities of other agents. It will encourage the cooperative sellers and punish the non-...
Bargaining under Incomplete Information
This paper presents and analyzes a bargaining model of bilateral monopoly under uncertainty. Under the bargaining rule proposed, the buyer and the seller each submit sealed offers that determine whether the good in question is sold and the transfer ...
Comments