Abstract
For more than a decade Vytelingum’s Adaptive-Aggressive (AA) algorithm has been recognized as the best-performing automated auction-market trading-agent strategy currently known in the AI/Agents literature; in this paper, we demonstrate that it is in fact routinely outperformed by another algorithm when exhaustively tested across a sufficiently wide range of market scenarios. The novel step taken here is to use large-scale compute facilities to brute-force exhaustively evaluate AA in a variety of market environments based on those used for testing it in the original publications. Our results show that even in these simple environments AA is consistently outperformed by IBM’s GDX algorithm, first published in 2002. We summarize here results from more than one million market simulation experiments, orders of magnitude more testing than was reported in the original publications that first introduced AA. A 2019 ICAART paper by Cliff claimed that AA’s failings were revealed by testing it in more realistic experiments, with conditions closer to those found in real financial markets, but here we demonstrate that even in the simple experiment conditions that were used in the original AA papers, exhaustive testing shows AA to be outperformed by GDX. We close this paper with a discussion of the methodological implications of our work: any results from previous papers where any one trading algorithm is claimed to be superior to others on the basis of only a few thousand trials are probably best treated with some suspicion now. The rise of cloud computing means that the compute-power necessary to subject trading algorithms to millions of trials over a wide range of conditions is readily available at reasonable cost: we should make use of this; exhaustive testing such as is shown here should be the norm in future evaluations and comparisons of new trading algorithms.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Independently, and via a wholly different line of attack, Gjerstad and Shachat [13] also demolished the argument that Gode and Sunder's [14] ZIC results indicate that the efficiency or intelligence in the market system lies solely within the CDA mechanism. Nevertheless, Gode and Sunder's results continue to be cited uncritically by various authors in the economics literature: we can only assume that such authors prefer a nice fairy story, rather than hard facts.
- 2.
At least two of those papers were co-authored by one of us, Dave Cliff. So this present paper is offered as something of a mea culpa from Cliff.
References
BSE: Bristol Stock Exchange. GitHub public source-code repository (2012). https://github.com/davecliff/BristolStockExchange
Cartea, Á., Jaimungal, S., Penalva, J.: Algorithmic and High-Frequency Trading. Cambridge University Press, Cambridge (2015)
Cliff, D.: Minimal-intelligence agents for bargaining behaviours in market-based environments. Hewlett-packard labs technical report HPL-97-91 (1997)
Cliff, D., Preist, C.: Days without end: on the stability of experimental single-period continuous double auction markets. Hewlett-packard labs technical report HPL-2001-325 (2001)
Cliff, D.: An open-source limit-order-book exchange for teaching and research. In: Proceedings of the IEEE Symposium on Computational Intelligence in Financial Engineering (CIFEr), Bengaluru, India, vol. SS-1296, pp. 1853–1860 (2018)
Cliff, D.: Exhaustive testing of trader-agents in realistically dynamic continuous double auction markets: AA does not dominate. In: Proceedings ICAART (2019)
Das, R., Hanson, J., Kephart, J., Tesauro, G.: Agent-human interactions in the continuous double auction. In: Proceedings IJCAI-2001, pp. 1169–1176 (2001)
De Luca, M., Cliff, D.: Agent-human interactions in the CDA, Redux. In: Proceedings ICAART 2011 (2011a)
De Luca, M., Cliff, D.: Human-agent auction interactions: adaptive-aggressive agents dominate. In: Proceedings IJCAI-2011, pp. 178–185 (2011b)
De Luca, M.: Adaptive algorithmic trading systems. Ph.D. thesis, University of Bristol, UK (2015)
Gjerstad, S., Dickhaut, J.: Price formation in double auctions. Games Econ. Behav. 22(1), 1–29 (1997)
Gjerstad, S.: The impact of pace in double auction bargaining. Working Paper, Department of Economics, University of Arizona (2003)
Gjerstad, S., Shachat, J.: Individual rationality and market efficiency. Working Paper, Department of Economics, Purdue University (2007)
Gode, D., Sunder, S.: Allocative efficiency of markets with zero-intelligence traders. J. Polit. Econ. 101(1), 119–137 (1993)
le Calvez, A., Cliff, D.: Deep learning can replicate adaptive traders in a LOB financial market. In: Proceedings of the IEEE Symposium on Computational Intelligence in Financial Engineering (CIFEr), vol. S1070, pp. 1876–1883 (2018)
Rodgers, K.: Why Aren’t they Shouting? A Banker’s Tale of Change, Computers, and Perpetual Crisis. RH Business Books/Cornerstone Digital, New York (2016)
Rust, J., Miller, J., Palmer, R.: Behavior of trading automata in a computerized double auction market. In: Friedman, D., Rust, J. (eds.) The Double Auction Market: Institutions, Theories, & Evidence, pp. 155–198. Addison-Wesley, Boston (1992)
Smith, V.: An experimental study of competitive market behavior. J. Polit. Econ. 70(2), 111–137 (1962)
Snashall, D.: An exhaustive comparison of algorithmic trading strategies: AA does not dominate. Master’s thesis, Department of Computer Science, University of Bristol (2019)
Stoikov, S.: The micro-price: a high-frequency estimator of future prices (2017). https://papers.ssrn.com/sol3/papers.cfm?abstract_id=2970694
Stotter, S., Cartlidge, J., Cliff, D.: Exploring assignment-adaptive (ASAD) trading agents in financial market experiments. In: Proceedings ICAART, vol. 1, pp. 77–88 (2013)
Stotter, S., Cartlidge, J., Cliff, D.: Behavioural investigations of financial trading agents using exchange portal (ExPo). In: Nguyen, N.T., Kowalczyk, R., Fred, A., Joaquim, F. (eds.) Transactions on Computational Collective Intelligence XVII. LNCS, vol. 8790, pp. 22–45. Springer, Heidelberg (2014). https://doi.org/10.1007/978-3-662-44994-3_2
Tesauro, G., Das, R.: High-performance bidding agents for the continuous double auction. In: Proceedings of the 3rd ACM Conference on Electronic Commerce, pp. 206–209 (2001)
Tesauro, G., Bredin, J.: Sequential strategic bidding in auctions using dynamic programming. In: Proceedings AAMAS 2002 (2002)
Vach, D.: Comparison of double auction bidding strategies for automated trading agents. MSc thesis, Charles University in Prague (2015)
Vytelingum, P.: The structure and behaviour of the continuous double auction. Ph.D. thesis, School of Electronics and Computer Science, University of Southampton, UK (2006)
Vytelingum, P., Cliff, D., Jennings, N.: Strategic Bidding in CDAs. Artif. Intell. 172(14), 1700–1729 (2008)
Wellman, M., Greenwald, A., Stone, P.: Autonomous Bidding Agents: Strategies and Lessons from the Trading Agent Competition. MIT Press, Cambridge (2007)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Snashall, D., Cliff, D. (2019). Adaptive-Aggressive Traders Don’t Dominate. In: van den Herik, J., Rocha, A., Steels, L. (eds) Agents and Artificial Intelligence. ICAART 2019. Lecture Notes in Computer Science(), vol 11978. Springer, Cham. https://doi.org/10.1007/978-3-030-37494-5_13
Download citation
DOI: https://doi.org/10.1007/978-3-030-37494-5_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-37493-8
Online ISBN: 978-3-030-37494-5
eBook Packages: Computer ScienceComputer Science (R0)