Abstract
This paper documents the development of three autonomous stock-trading agents within the framework of the Penn Exchange Simulator (PXS), a novel stock-trading simulator that takes advantage of electronic crossing networks to realistically mix agent bids with bids from the real stock market [1]. The three approaches presented take inspiration from reinforcement learning, myopic trading using regression-based price prediction, and market making. These approaches are fully implemented and tested with results reported here, including individual evaluations using a fixed opponent strategy and a comparative analysis of the strategies in a joint simulation. The market-making strategy described in this paper was the winner in the fall 2003 PLAT live competition and the runner-up in the spring 2004 live competition, exhibiting consistent profitability. The strategy’s performance in the live competitions is presented and analyzed.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Kearns, M., Ortiz, L.: The Penn-Lehman automated trading project. IEEE Intelligent Systems (to appear, 2003)
WWW: Island ECN, http://www.island.com
Chan, N., Shelton, C.R.: An electronic market maker. Technical Report 200-005, MIT Artificial Intelligence Laboratory (2001)
Das, S.: Intelligent market-making in artificial financial markets. Technical Report 2003-005, Massachusetts Institute of Technology AI Lab/CBCL (2003)
Feng, Y., Yu, R., Stone, P.: Two Stock-Trading Agents: Market Making and Technical Analysis. In: Faratin, P., Parkes, D.C., RodrĂguez-Aguilar, J.-A., Walsh, W.E. (eds.) AMEC 2003. LNCS (LNAI), vol. 3048, pp. 18–36. Springer, Heidelberg (to appear, 2004)
Yu, R., Stone, P.: Performance analysis of a counter-intuitive automated stock-trading agent. In: Proceedings of the 5th International Conference on Electronic Commerce, pp. 40–46. ACM Press, New York (2003)
WWW: Common stock-trading strategies, http://www.cis.upenn.edu/~mkearns/projects/strategies.html )
Moody, J., Saffell, M.: Learning to trade via direct reinforcement. IEEE Transactions on Newral Networks 12, 875–889 (2001)
Sutton, R., Barto, A.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)
Rummery, G.A., Niranjan, M.: On-line Q-learning using connectionist systems. Technical Report CUED/F-INFEG/TR66, Cambridge University Department (1994)
Sutton, R.S.: Generalization in reinforcement learning: Successful examples using sparse coarse coding. In: Tesauro, G., Touretzky, D., Leen, T. (eds.) Advances in Neural Information Processing Systems, vol. 8, pp. 1038–1044. MIT Press, Cambridge (1996)
Tesauro, G., Bredin, J.L.: Strategic sequential bidding in auctions using dynamic programming. In: First International Joint Conference on Autonomous Agents and Multi-Agent Systems, Bologna, Italy (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sherstov, A.A., Stone, P. (2006). Three Automated Stock-Trading Agents: A Comparative Study. In: Faratin, P., RodrĂguez-Aguilar, J.A. (eds) Agent-Mediated Electronic Commerce VI. Theories for and Engineering of Distributed Mechanisms and Systems. AMEC 2004. Lecture Notes in Computer Science(), vol 3435. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11575726_13
Download citation
DOI: https://doi.org/10.1007/11575726_13
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-29737-6
Online ISBN: 978-3-540-33166-7
eBook Packages: Computer ScienceComputer Science (R0)