Advertisement

Behavioural Investigations of Financial Trading Agents Using Exchange Portal (ExPo)

  • Steve Stotter
  • John Cartlidge
  • Dave Cliff
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8790)

Abstract

Some major financial markets are currently reporting that 50 % or more of all transactions are now executed by automated trading systems (ATS). To understand the impact of ATS proliferation on the global financial markets, academic studies often use standard reference strategies, such as “AA” and “ZIP”, to model the behaviour of real trading systems. Disturbingly, we show that the reference algorithms presented in the literature are ambiguous, thus reducing the validity of strict comparative studies. As a remedy, we suggest disambiguated standard implementations of AA and ZIP. Using Exchange Portal (ExPo), an open-source financial exchange simulation platform designed for real-time behavioural economic experiments involving human traders and/or trader-agents, we study the effects of disambiguating AA and ZIP, before introducing a novel method of assignment-adaptation (ASAD). Experiments show that introducing ASAD agents into a market with shocks can produce counter-intuitive market dynamics.

Keywords

Software agents Auctions Agent-based computational economics ACE Agent-based modelling ABM Automated trading Computational finance ExPo Exchange portal Assignment adaptation 

Notes

Acknowledgments

The authors would like to thank Tomas Gražys for significant development of the ExPo platform. John Cartlidge is supported by EPSRC grant, number EP/H042644/1; primary financial support for Dave Cliff’s research comes from EPSRC grant, number EP/F001096/1.

References

  1. 1.
    Cartlidge, J., Ait-Boudaoud, D.: Autonomous virulence adaptation improves coevolutionary optimisation. IEEE Trans. Evol. Comput. 15(2), 215–229 (2011)CrossRefGoogle Scholar
  2. 2.
    Cartlidge, J.: Trading experiments using financial agents in a simulated cloud computing commodity market. In: Duval, B., van den Herik, J., Loiseau, S., Filipe, J. (eds.) 6th International Conference on Agents and Artificial Intelligent, Agents (ICAART-2014), vol. 2, pp. 311–317. SciTePress, March 2014Google Scholar
  3. 3.
    Cartlidge, J., Bullock, S.: Caring versus sharing: how to maintain engagement and diversity in coevolving populations. In: Banzhaf, W., Ziegler, J., Christaller, T., Dittrich, P., Kim, J.T. (eds.) ECAL 2003. LNCS (LNAI), vol. 2801, pp. 299–308. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  4. 4.
    Cartlidge, J., Bullock, S.: Unpicking tartan CIAO plots: understanding irregular coevolutionary cycling. Adapt. Behav. 12(2), 69–92 (2004)CrossRefGoogle Scholar
  5. 5.
    Cartlidge, J., Cliff, D.: Exploring the “robot phase transition” in experimental human-algorithmic markets. The Future of Computer Trading in Financial Markets-Foresight Driver Review-DR25, Crown Copyright, Oct 2012. http://bitly.com/SvqohP
  6. 6.
    Cartlidge, J., Cliff, D.: Evidencing the “robot phase transition” in experimental human-algorithmic markets. In: Filipe, J., Fred, A. (eds.) 5th International Conference on Agents and Artificial Intelligent, Agents (ICAART-2013), vol. 1, pp. 345–352. SciTePress, Feb 2013Google Scholar
  7. 7.
    Cartlidge, J., Szostek, C., De Luca, M., Cliff, D.: Too fast too furious: faster financial-market trading agents can give less efficient markets. In: Filipe, J., Fred, A. (eds.) 4th International Conference on Agents and Artificial Intelligent, Agents (ICAART-2012), vol. 2, pp. 126–135. SciTePress, Feb 2012Google Scholar
  8. 8.
    Cliff, D.: Minimal-intelligence agents for bargaining behaviors in market-based environments. Technical report, HPL-97-91, Hewlett-Packard Labs, Aug 1997. http://bit.ly/18uC9vM
  9. 9.
    Das, R., Hanson, J., Kephart, J., Tesauro, G.: Agent-human interactions in the continuous double auction. In: Nebel, B. (ed.) 17th International Joint Conference on Artificial Intelligent (IJCAI-01), pp. 1169–1176. Morgan Kaufmann, Aug 2001Google Scholar
  10. 10.
    De Luca, M., Cliff, D.: Agent-human interactions in the continuous double auction, redux: using the OpEx lab-in-a-box to explore ZIP and GDX. In: Filipe, J., Fred, A. (eds.) 3rd International Conference on Agents and Artificial Intelligent (ICAART-2011), pp. 351–358. SciTePress, Jan 2011Google Scholar
  11. 11.
    De Luca, M., Cliff, D.: Human-agent auction interactions: adaptive-aggressive agents dominate. In: Walsh, T. (ed.) 22nd International Joint Conference on Artificial Intelligent (IJCAI-11), pp. 178–185. AAAI Press, Jul 2011Google Scholar
  12. 12.
    De Luca, M., Szostek, C., Cartlidge, J., Cliff, D.: Studies of interactions between human traders and algorithmic trading systems. The Future of Computer Trading in Financial Markets-Foresight Driver Review-DR13, Crown Copyright, Sep 2011. http://bitly.com/RoifIu
  13. 13.
    ExPo: The Exchange Portal, Mar 2012. http://sourceforge.net/projects/exchangeportal/
  14. 14.
    Feltovich, N.: Nonparametric tests of differences in medians: comparison of the wilcoxon-mann-whitney and robust rank-order tests. Exp. Econ. 6, 273–297 (2003)CrossRefzbMATHGoogle Scholar
  15. 15.
    Feltovich, N.: Critical values for the robust rank-order test. Commun. Stat. Simul. Comput. 34(3), 525–547 (2005)CrossRefzbMATHMathSciNetGoogle Scholar
  16. 16.
    Gjerstad, S., Dickhaut, J.: Price formation in double auctions. Games Econ. Behav. 22(1), 1–29 (1998)CrossRefzbMATHMathSciNetGoogle Scholar
  17. 17.
    Gode, D., Sunder, S.: Allocative efficiency of markets with zero-intelligence traders: markets as a partial substitute for individual rationality. J. Polit. Econ. 101(1), 119–137 (1993)CrossRefGoogle Scholar
  18. 18.
    OpEx: Open Exchange software, Mar 2012. https://sourceforge.net/projects/open-exchange/
  19. 19.
    Preist, C., van Tol, M.: Adaptive agents in a persistent shout double auction. In: 1st International Conference on Information and Computation Economies, pp. 11–18. ACM Press (1998)Google Scholar
  20. 20.
    Smith, V.: An experimental study of comparative market behavior. J. Polit. Econ. 70, 111–137 (1962)CrossRefGoogle Scholar
  21. 21.
    Stock, J.H., Watson, M.M.: Introduction to Econometrics, Chap. 4, 3rd edn. Pearson, Upper Saddle River (2012)Google Scholar
  22. 22.
    Stotter, S.: Improving the strategies of algorithmic traders and investigating further realism in their market environment. Master’s thesis, Department of Computer Science: University of Bristol, UK, July 2012Google Scholar
  23. 23.
    Stotter, S., Cartlidge, J., Cliff, D.: Exploring assignment-adaptive (ASAD) trading agents in financial market experiments. In: Filipe, J., Fred, A.L.N. (eds.) 5th International Conference on Agents and Artificial Intelligent, Agents (ICAART-2013), vol. 1, pp. 77–88. SciTePress, Feb 2013Google Scholar
  24. 24.
    Tesauro, G., Das, R.: High-performance bidding agents for the continuous double auction. In: ACM Conference on Electronic Commerce, pp. 206–209. ACM Press (2001)Google Scholar
  25. 25.
    van Montfort, G.P.R., Bruten, J., Rothkrantz, L.: Arbitrageurs in segmented markets. Technical report, HPL-97-120, Hewlett-Packard Labs, Oct 1997. http://www.hpl.hp.com/techreports/97/HPL-97-120.pdf
  26. 26.
    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)Google Scholar
  27. 27.
    Vytelingum, P., Dash, R.K., David, E., Jennings, N.R.: A risk-based bidding strategy for continuous double auctions. In: López de Mánataras, R., Saitta, L. (eds.) 16th European Conference on Artificial Intelligence (ECAI-2004), pp. 79–83. IOS Press (2004)Google Scholar
  28. 28.
    Widrow, B., Hoff, Jr., M.E.: Adaptive switching circuits. In: Institute of Radio Engineers, Western Electron, Show and Convention (IRE WESCON), Convention Record, Part 4, pp. 96–104, Aug 1960Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  1. 1.Department of Computer ScienceUniversity of Bristol Merchant Venturers BuildingBristolUK

Personalised recommendations