Publication Type

Conference Proceeding Article

Version

submittedVersion

Publication Date

11-2007

Abstract

In this paper, we propose to design a market game that (a) can be used in modeling and studying commodity trading scenarios, and (b) can be used in capturing human traders' behaviors. Specifically, we demonstrate the usefulness of this commodity trading game in a single-commodity futures trading scenario. A pilot experiment was run with a mixture of human traders and an autonomous agent that emulates the aggregatedmarket condition, with the assumption that this autonomous agent would hint each of its action through a public announcement. We show that the information collected from this simulation can be used to extract the pattern of successful human traders. Finally, we elaborate on the potential of this market game in studying autonomous commodity trading.

Discipline

Artificial Intelligence and Robotics | Business | Operations Research, Systems Engineering and Industrial Engineering

Publication

IEEE/WIC/ACM International Conference on Intelligent Agent Technology, 2007: IAT '07: 2-5 November 2007, Fremont, CA: Proceedings

First Page

445

Last Page

449

ISBN

9780769530277

Identifier

10.1109/IAT.2007.42

Publisher

IEEE Computer Society

City or Country

Los Alamitos, CA

Additional URL

http://dx.doi.org/10.1109/IAT.2007.42

Share

COinS