DocumentCode :
3205845
Title :
Adaptive Agents for Sequential English Auctions with a Fixed Deadline
Author :
Ma, Huiye ; Leung, Ho-fung
Author_Institution :
Center for Math. & Compute Sci., Amsterdam
fYear :
2007
fDate :
23-26 July 2007
Firstpage :
29
Lastpage :
38
Abstract :
In this paper, we consider sequential English auctions with a fixed deadline. The protocol allows the specification of a deadline since in real world trading, it is often essential to conclude a transaction among agents under a fixed deadline. Although there are a lot of differences between continuous double auctions (CDAs) and the sequential English auction, it is possible to modify the agents designed for continuous double auctions and apply them to the sequential English auctions with a fixed deadline. We describe how to revise these adaptive agents, including ZI-C, ZIP, GD, and AA. The performance of these agents is evaluated by two sets of experiments. In the first set of experiments, it turns out that when it is very difficult for all the buyer agents to buy their goods, agents adopting the dominant strategy outperform the revised adaptive bidding strategies. In order to test whether the dominant strategy is always the best choice for difficult buying, we add AA strategy into the experiments. The experimental results demonstrate that AA agents perform better than the agents using the dominant strategy and other adaptive bidding strategies in general.
Keywords :
adaptive systems; commerce; adaptive agents; adaptive bidding strategy; continuous double auctions; fixed deadline; sequential English auctions; Computer science; Cost accounting; Electronic commerce; Internet; Mathematics; Protocols; Testing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
E-Commerce Technology and the 4th IEEE International Conference on Enterprise Computing, E-Commerce, and E-Services, 2007. CEC/EEE 2007. The 9th IEEE International Conference on
Conference_Location :
Tokyo
Print_ISBN :
0-7695-2913-5
Type :
conf
DOI :
10.1109/CEC-EEE.2007.17
Filename :
4285196
Link To Document :
بازگشت