Advertisement

Revisiting Agent-Based Models of Algorithmic Trading Strategies

  • Natalia PonomarevaEmail author
  • Anisoara Calinescu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8780)

Abstract

Algorithmic trading (AT) strategies aim at executing large orders discretely, in order to minimize the order’s impact, whilst also hiding the traders’ intentions. The contribution of this paper is twofold. First we presented a method for identifying the most suitable market simulation type, based on the specific market model to be investigated. Then we proposed an extended model of the Bayesian execution strategy. We implemented and assessed this model using our tool AlTraSimBa (ALgorithmic TRAding SIMulation BAcktesting) against the standard Bayesian execution strategy and naïve execution strategies, for momentum, random and noise markets, as well as against historical data. Our results suggest that: (i) momentum market is the most suitable model for testing AT strategies, since it quickly fills the Limit Order book and produces results comparable to those of a liquid stock; (ii) the priors estimation method proposed in this paper \(-\) within the Bayesian adaptive agent model \(-\) can be advantageous in relatively stable markets, when trading patterns in consecutive days are strongly correlated, and (iii) there exists a trade-off between the frequency of decision making and more complex decision criteria, on one side, and the negative outcome of lost trading on the agents’ side due to them not participating actively in the market for some of the execution steps.

Keywords

Algorithmic trading Bayesian adaptive agents Simulation Backtesting 

Notes

Acknowledgements

Natalia Ponomareva would like to gratefully acknowledge the Hill Foundation for supporting her study for an MSc degree at the Department of Computer Science of the University of Oxford.

References

  1. 1.
  2. 2.
    Cboe historical stock volatilities. http://www.cboe.com/data/historicalvolatility.aspx
  3. 3.
  4. 4.
    JASA - Java Auction Simulator API. http://www.essex.ac.uk/ccfea/research/software/jasa/
  5. 5.
    Online tick-level dataset Dukascopy. http://freeserv.dukascopy.com/exp/
  6. 6.
    A resource for agent- and individual-based modellers, and the home page of Swarm. http://www.swarm.org/index.php/Main_Page
  7. 7.
    Almgren, R., Lorenz, J.: Bayesian adaptive trading with a daily cycle. J. Trading 1(4), 38–46 (2006)CrossRefGoogle Scholar
  8. 8.
    Andersen, T.G., Bollerslev, T., Diebold, F.X., Ebens, H.: The distribution of realized stock return volatility. J. Financ. Econ. 61, 43–76 (2001)CrossRefGoogle Scholar
  9. 9.
    Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, Heidelberg (2006)zbMATHGoogle Scholar
  10. 10.
    Bonabeau, E.: Agent-based modeling: methods and techniques for simulating human systems. PNAS 99(3), 7280–7287 (2002)CrossRefGoogle Scholar
  11. 11.
    Chung, K.H., Kim, Y.: Volatility, market structure, and the bid-ask spread. Asia-Pac. J. Financ. Stud. 38(1), 67–107 (2009)CrossRefGoogle Scholar
  12. 12.
    Cui, W., Brabazon, A., O’Neill, M.: Efficient trade execution using a genetic algorithm in an order book based artificial stock market. In: Conference Companion on Genetic and Evolutionary Computation, pp. 2023–2028 (2009)Google Scholar
  13. 13.
    Cui, W., Brabazon, A., O’Neill, M.: Evolving dynamic trade execution strategies using grammatical evolution. In: Di Chio, C., et al. (eds.) EvoApplications 2010, Part II. LNCS, vol. 6025, pp. 192–201. Springer, Heidelberg (2010) CrossRefGoogle Scholar
  14. 14.
    Daniel, G.: Asynchronous simulations of a limit order book. Ph.D. thesis, University of Manchester (2007)Google Scholar
  15. 15.
    Domowitz, I., Yegerman, H.: The cost of algorithmic trading: a first look at comparative performance. J. Trading 1, 33–42 (2006)CrossRefGoogle Scholar
  16. 16.
    Ederington, L.H., Guan, W.: Measuring historical volatility. J. Appl. Financ. 16, 5–14 (2006)Google Scholar
  17. 17.
    Engle, R., Patton, A.: What good is a volatility model? Quant. Financ. 1, 237–245 (2001)CrossRefGoogle Scholar
  18. 18.
    Farmer, J.D., Patelli, P., Zovko, I.I.: The predictive power of zero intelligence in financial markets. SSRN eLibrary (2004)Google Scholar
  19. 19.
    Gsell, M.: Assessing the impact of algorithmic trading on markets: a simulation approach. In: 16th European Conference on Information Systems, pp. 587–598 (2008)Google Scholar
  20. 20.
    Hendershott, T., Jones, C., Menkveld, A.: Does algorithmic trading improve liquidity? J. Financ. 66, 1–33 (2011)CrossRefGoogle Scholar
  21. 21.
    Izumi, K., Toriumi, F., Matsui, H.: Evaluation of automated-trading strategies using an artificial market. Neurocomputing 72, 3469–3476 (2009)CrossRefGoogle Scholar
  22. 22.
    Jiang, C.X., Kim, J.-C., Wood, R.A.: A comparison of volatility and bidask spread for NASDAQ and NYSE after decimalization. Appl. Econ. 43(10), 1227–1239 (2011)CrossRefGoogle Scholar
  23. 23.
    Kakade, S.M., Kearns, M., Mansour, Y., Ortiz, L.E.: Competitive algorithms for VWAP and limit order trading. In: Proceedings of the 5th ACM Conference on Electronic Commerce, pp. 189–198 (2004)Google Scholar
  24. 24.
    Lebaron, B.: Agent-based computational finance. In: Handbook of Computational Economics, Agent-based Computational Economics, pp. 166–209 (2006)Google Scholar
  25. 25.
    Nevmyvaka, Y., Feng, Y., Kearns, M.: Reinforcement learning for optimized trade execution. In: Proceedings of the 23rd International Conference on Machine Learning, pp. 673–680 (2006)Google Scholar
  26. 26.
    Nevmyvaka, Y., Kearns, M.S., Papandreou, A., Sycara, K.P.: Electronic trading in order-driven markets: efficient execution. In: CEC’05, pp. 190–197 (2005)Google Scholar
  27. 27.
    Ponomareva, N.: Using agent-based modelling and backtest to evaluate algorithmic trading strategies. Master’s thesis, Department of Computer Science, University of Oxford (2011)Google Scholar
  28. 28.
    Raghavendra, S., Paraschiv, D., Vasiliu, L.: A framework for testing algorithmic trading strategies. Working Paper No. 0139 (2008). http://hdl.handle.net/10379/325
  29. 29.
    Rashid, A.: Using a service oriented architecture for simulating algorithmic trading strategies. In: Proceedings of the 12th International Conference on Information Integration and Web-based Applications & #38; Services, iiWAS ’10, France, Paris, pp. 925–929 (2010)Google Scholar
  30. 30.
    Roll, R.: A simple implicit measure of the effective bid-ask spread in an efficient market. J. Financ. 39, 1127–1139 (1984)CrossRefGoogle Scholar
  31. 31.
    Sharpe, W., Alexander, G.J., Bailey, J.W.: Investments, 6th edn. Prentice Hall, New York (1998)Google Scholar
  32. 32.
    Wang, F., Dong, K., Deng, X.: Algorithmic trading system: design and applications. Front. Comput. Sci. China 3, 235–246 (2009)CrossRefGoogle Scholar
  33. 33.
    Wurman, P.R., Walsh, W.E., Wellman, M.P.: Flexible double auctions for electronic commerce: theory and implementation. Decis. Support Syst. 24(1), 17–27 (1998)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  1. 1.Department of Computer ScienceUniversity of OxfordOxfordUK

Personalised recommendations