Why Robots Failed - Demonstrating the Superiority of Multiple-order Trading Agents in Experimental Human-agent Financial Markets

Marco De Luca

Abstract

In the past decade there has been a rapid growth of the use of adaptive automated trading systems, commonly referred to in the finance industry as ``robot traders'': AI applications replacing highly-paid human traders in the global financial markets. The academic roots of this industry-changing deployment of AI technologies can be traced back to research published by a team of researchers at IBM at IJCAI 2001, which was subsequently replicated and extended by De Luca and Cliff at IJCAI 2011 and ICAART 2011. Here, we focus on the order management policy enforced by Open Exchange (OpEx), the open source algorithmic trading system designed by De Luca, for both human and robot traders: while humans are allowed to manage multiple orders simultaneously, robots only deal with one order at the time. We hypothesise that such unbalance may have strongly influenced the victory of human traders over robot traders, reported in past studies by De Luca et al., and by Cartlidge and Cliff. We employed OpEx to implement a multiple-order policy for robots as well as humans, and ran several human vs. robot trading experiments. Using aggregated market metrics and time analysis, we reached two important conclusions. First, we demonstrated that, in mixed human-robot markets, robots dealing multiple simultaneous orders consistently outperform robots dealing one order at a time. And second, we showed that while human traders outperform single-order robot traders under specific circumstances, multiple-order robot traders are never outperformed by human traders. We thus conclude that the performance of robot traders in a human-robot mixed market is strongly influenced by the order management policy they employ.

References

  1. Cartlidge, J. and Cliff, D. (2012). Foresight project, Driver Review DR25. Exploring the “robot phase transition” in experimental human-algorithmic markets. Technical report, UK Government's Office for Science.
  2. Cartlidge, J. and Cliff, D. (2013). Evidencing the “robot phase transition” in human-agent experimental financial markets. In Proceedings of ICAART 2013.
  3. Cartlidge, J., Szostek, C., De Luca, M., and Cliff, D. (2012). Too fast too furious. Faster Financial-Market Trading Agents Can Give Less Efficient Markets. In Proceedings of ICAART 2012.
  4. Cliff, D. (1996). Minimal-intelligence agents for bargaining behaviors in market-based environments. Technical report, Hewlett Packard Laboratories.
  5. Cliff, D. and Preist, C. (2001). Days without end: On the stability of experimental single-period continuous double auction markets. Technical report, Hewlett Packard Laboratories.
  6. Das, R., Hanson, J., Kephart, J., and Tesauro, G. (2001). Agent-human interactions in the continuous double auction. In Proceedings of IJCAI 2001.
  7. De Luca, M. (2012). Open Exchange (OpEx) - The open source Algorithmic Trading System, SourceForge.
  8. De Luca, M. and Cliff, D. (2011a). Agent-Human Interactions in the Continuous Double Auction, Redux. Using the OpEx Lab-in-a-Box to explore ZIP and GDX. In Proceedings of ICAART 2011.
  9. De Luca, M. and Cliff, D. (2011b). Human-agent auction interactions: Adaptive-aggressive agents dominate. In Proceedings of IJCAI 2011.
  10. De Luca, M., Szostek, C., Cartlidge, J., and Cliff, D. (2011). Foresight project, Driver Review DR13. Studies on interactions between human traders and Algorithmic Trading Systems. Technical report, UK Government's Office for Science.
  11. Feltovich, N. (2003). Nonparametric tests of differences in medians: comparison of the Wilcoxon-MannWhitney and robust rank-order tests. Experimental Economics.
  12. Fligner, M. and Pollicello, G. (1981). Robust Rank Procedures for the Behrens-Fisher Problem. Journal of the American Statistical Association, (76):162-168.
  13. Smith, V. (1962). An experimental study of comparative market behavior. Journal of Political Economics, 70:111-137.
  14. Tesauro, G. and Bredin, J. (2002). Strategic sequential bidding in auctions using dynamic programming. In Proceedings of AAMAS 2002.
  15. Vytelingum, P. (2006). The Structure and Behaviour of the Continuous Double Auction. PhD thesis.
  16. Vytelingum, P., Cliff, D., and Jennings, N. (2008). Strategic bidding in continuous double auctions. Artificial Intelligence, 172(14):1700-1729.
Download


Paper Citation


in Harvard Style

De Luca M. (2015). Why Robots Failed - Demonstrating the Superiority of Multiple-order Trading Agents in Experimental Human-agent Financial Markets . In Proceedings of the International Conference on Agents and Artificial Intelligence - Volume 1: ICAART, ISBN 978-989-758-073-4, pages 44-53. DOI: 10.5220/0005203100440053


in Bibtex Style

@conference{icaart15,
author={Marco De Luca},
title={Why Robots Failed - Demonstrating the Superiority of Multiple-order Trading Agents in Experimental Human-agent Financial Markets},
booktitle={Proceedings of the International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,},
year={2015},
pages={44-53},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005203100440053},
isbn={978-989-758-073-4},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Agents and Artificial Intelligence - Volume 1: ICAART,
TI - Why Robots Failed - Demonstrating the Superiority of Multiple-order Trading Agents in Experimental Human-agent Financial Markets
SN - 978-989-758-073-4
AU - De Luca M.
PY - 2015
SP - 44
EP - 53
DO - 10.5220/0005203100440053