Advertisement

Designing, Implementing and Testing an Automated Trading Strategy Based on Dynamic Bayesian Networks, the Limit Order Book Information, and the Random Entry Protocol

  • Javier Sandoval
  • Germán Hernández
Chapter
Part of the Studies in Computational Intelligence book series (SCI, volume 647)

Abstract

This paper evaluates, using the Random Entry Protocol technique, a high-frequency trading strategy based on a Dynamic Bayesian Network (DBN) that can identify predictive trend patterns in foreign exchange orden-driven markets. The proposed DNB allows simultaneously to represent expert knowledge of skilled traders in a model structure and to learn computationally from data information that reflects relevant market sentiment dynamics. The DBN is derived from a Hierarchical Hidden Markov Model (HHMM) that incorporates expert knowledge in its design and learns the trend patterns present in the market data. The wavelet representation is used to produce compact representations of the LOB liquidity dynamics that simultaneously reduces the time complexity of the computational learning and improves its precision. In previous works, this trading strategy has been shown to be competitive when compared with conventional techniques. However, these works failed to control for unwanted dependencies in the return series used for training and testing that may have skewed performance results to the positive side. This paper constructs key trading strategy estimators based on the Random Entry Protocol over the USD-COP data. This technique eliminates unwanted dependencies on returns and order flow while keeps the natural autocorrelation structure of the Limit Order Book (LOB). It is still concluded that the HHMM-based model results are competitive with a positive, statistically significant P/L and a well-understood risk profile. Buy-and-Hold results calculated over the testing period are provided for comparison reasons.

Keywords

Trading Strategy Dynamic Bayesian Network Transaction Price Order Book Volume Block 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Notes

Acknowledgments

We thank Bolsa de Valores de Colombia (BVC) for providing the dataset. This work was partially supported by Colciencias.

References

  1. 1.
    Murphy, K.: Dynamic Bayesian networks: representation, inference, and learning. Ph.D. thesis, University of California, Berkeley (2002)Google Scholar
  2. 2.
    Bengtsson, H.: Bayesian networks—A self-contained introduction with implementation remarks. Ph.D. thesis, Mathematical Statistics, Lund Institute of Technology (1999)Google Scholar
  3. 3.
    Sandoval, J., Hernández, G.: Procedia Comput. Sci. 51(1593) (2015) (International Conference On Computational Science, ICCS Computational Science at the Gates of Nature). doi: 10.1016/j.procs.2015.05.290. http://www.sciencedirect.com/science/article/pii/S1877050915010984
  4. 4.
    Sandoval, J., Hernandez, G.: Science and Information Conference (SAI), pp. 435–442 (2015). doi: 10.1109/SAI.2015.7237178
  5. 5.
    Sandoval, J., Hernández, G.: Machine Learning and Data Mining in Pattern Recognition. In: Perner (ed.) Lecture Notes in Computer Science, vol. 8556. Springer International Publishing, pp. 408–421 (2014). doi: 10.1007/978-3-319-08979-9_30
  6. 6.
    Covrig, V., Ng, L.: J. Bank. Finan. 28(9), 2155 (2004)CrossRefGoogle Scholar
  7. 7.
    Politis, D.N., Romano, J.P.: J. Am. Stat. Assoc. 89(428), 1303 (1994). http://www.jstor.org/stable/2290993
  8. 8.
    Efron, B.: The Jackknife, the Bootstrap and Other Resampling Plans. Society for Industrial and Applied Mathematics (1982). doi: 10.1137/1.9781611970319, http://epubs.siam.org/doi/abs/10.1137/1.9781611970319
  9. 9.
    Schmidt, A.B.: J. Trading 4, 62 (2009). doi: 10.3905/JOT.2009.4.4.062 CrossRefGoogle Scholar
  10. 10.
    Murphy, K.P., Paskin, M.A.: Proceedings of Neural Information Processing Systems (2001)Google Scholar
  11. 11.
    Bouchaud, J.P., Farmer, J.D., Lillo, F.: How markets slowly digest changes in supply and demand. Quantitative Finance Papers 0809.0822. arXiv.org (2008). http://ideas.repec.org/p/arx/papers/0809.0822.html
  12. 12.
    Dorogovtsev, S., Mendes, J., Oliveira, J.: Phys. A: Stat. Mech. Appl. 360(2), 548 (2006). doi: 10.1016/j.physa.2005.06.064, http://www.sciencedirect.com/science/article/B6TVG-4GNTCF9-2/2/d9efa60dec0417dacaf9f01a5b4bcc40
  13. 13.
    Eisler, Z., Kertesz, J., Lillo, F.: The limit order book on different time scales. Quantitative Finance Papers 0705.4023, arXiv.org (2007). http://ideas.repec.org/p/arx/papers/0705.4023.html
  14. 14.
    Gu, G.F., Chen, W., Zhou, W.X.: Physica 387(21), 5182 (2008)CrossRefGoogle Scholar
  15. 15.
    Tian, G. Guo, M.: Rev. Quant. Finan. Acc. 28(3), 287 (2007). http://ideas.repec.org/a/kap/rqfnac/v28y2007i3p287-306.html
  16. 16.
    Weber, P., Rosenow, B.: Quant. Finan. 5(4), 357 (2005)CrossRefGoogle Scholar
  17. 17.
    Hassan, M.R., Nath, B., Kirley, M.: Expert Syst. Appl. 33(1), 171 (2007). doi: 10.1016/j.eswa.2006.04.007, http://www.sciencedirect.com/science/article/pii/S0957417406001291
  18. 18.
    Ortega, L., Khashanah, K.: J. Forecast. 33(2), 134 (2014). doi: 10.1002/for.2270, http://dx.doi.org/10.1002/for.2270

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.UNAL UExternadoBogotáColombia
  2. 2.UNALBogotáColombia

Personalised recommendations