Toward market-driven agents for electronic auction
- 1 November 2001
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans
- Vol. 31 (6), 474-484
- https://doi.org/10.1109/3468.983399
Abstract
While there are several existing agent-based systems addressing the crucial and difficult issues of automated negotiation and auction, this research has designed and engineered a society of trading agents with two distinguishing features: 1) a market-driven negotiation strategy and 2) a deal optimizing auction protocol. Unlike some of the existing systems where users manually select predefined trading strategies, in the market-driven approach, trading agents automatically select the appropriate strategies by examining the changing market situations. Results from a series of experiments suggest that the market-driven approach generally achieved more favorable outcomes as compared to the fixed strategy approach. Furthermore, it provides a more intuitive simulation of trading because trading agents are able to respond to different market situations with appropriate strategies. By augmenting the auction protocol with a deal optimization stage, trading agents can be programmed to optimize transaction deals by delaying the finalization of deals in search of better deals. Experimental results showed that by having a deal optimization stage, the auction protocol produced generally optimistic outcomes.Keywords
This publication has 3 references indexed in Scilit:
- Agent behaviors in virtual negotiation environmentsIEEE Transactions on Systems, Man and Cybernetics, Part C (Applications and Reviews), 1999
- Agent-mediated electronic commerce: a surveyThe Knowledge Engineering Review, 1998
- The Michigan Internet AuctionBotPublished by Association for Computing Machinery (ACM) ,1998