Abstract
This paper presents the use of Deep Belief Networks (DBN) for direction forecasting on financial time series, particularly those associated to the High Frequency Domain. The paper introduces some of the key concepts of the DBN, presents the methodology, results and its discussion. DBNs achieves better performance for particular configurations and training times were acceptable, however if they want to be pursued in real applications, windows sizes should be evaluated.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
It means five sell intentions and five buy intentions, recorded every five seconds. If something changed in the LOB within the 5 s interval it is not registered.
- 2.
Candlestick is an ancient representation from rice Japanese traders in the 1700’s. Widely used by technical traders to analyze price formations (Luca, 2000).
- 3.
Traded quantity of Facebook stock for each 15-seconds interval.
- 4.
References
Bank for International Settlements, Settlement Systems Technical Committee of the International Organization of Securities Commissions Principles for financial market infrastructures, Basel, Switzerland, March 2011
Darskuviene, V.: “Finanical Markets.” Leonardo Da Vinci Transfer of Innovation Program, pp. 1–140 (2010)
Sandoval, J.: High Frequency Exchange rate prediction using dynamic bayesian networks over the limit order book information. Universidad Nacional de Colombia (2015)
Arévalo, A., Niño, J., Hernández, G., Sandoval, J.: High-frequency trading strategy based on deep neural networks. In: Huang, D., Han, K., Hussain, A. (eds.) ICIC 2016. LNCS, vol. 9773, pp. 424–436. Springer, Heidelberg (2016). doi:10.1007/978-3-319-42297-8_40
ESMA, “High-frequency trading activity in EU equity markets” (2014)
UK’s Gov Office, “The Future of Computer Trading in Financial Markets An International Perspective” (2012)
Sandoval, J., Nino, G., Hernandez, G., Cruz, A.: Detecting informative patterns in financial market trends based on visual analysis. Procedia Comput. Sci. 80, 752–761 (2016)
Ohlsson, S.: Stellan Ohlsson: deep learning: how the mind overrides experience. Sci. Educ. 21, 1381–1392 (2012). Cambridge University Press, New York
Tay, F.E.H., Cao, L.: Application of support vector machines in financial time series forecasting. Omega 29, 309–317 (2001)
Ortega, L.F.: A neuro-wavelet method for the forecasting of financial time series. In: Proceedings of the World Congress on Engineering and Computer Science, vol. I (2012)
Schmidhuber, J.: Deep Learning in Neural Networks: An Overview, vol. 61, pp. 1–66. arXiv Preprint arXiv1404.7828 (2014)
Hinton, G.E., Osindero, S., Teh, Y.-W.: Communicated by Yann Le Cun a fast learning algorithm for deep belief nets. Neural Comput. 18, 1527–1554 (2006)
Hinton, G.: A practical guide to training restricted Boltzmann machines. Comput. (Long Beach Calif.) 9, 1 (2010)
Zhu, C., Yin, J., Li, Q.: A stock decision support system based on DBNs⋆. J. Comput. Inf. Syst. 2, 883–893 (2014)
Längkvist, M., Karlsson, L., Loutfi, A.: A review of unsupervised feature learning and deep learning for time-series modelling. Pattern Recogn. Lett. 42(1), 11–24 (2014)
Kuremoto, T., Kimura, S., Kobayashi, K., Obayashi, M.: Time series forecasting using a deep belief network with restricted Boltzmann machines. Neurocomputing 137, 47–56 (2014)
Dalto, M.: Deep neural networks for time series prediction with applications in ultra-short-term wind forecasting (2015)
Lai, A., Li, M.K., Pong, F.W.: Forecasting Trade Direction and Size of Future Contracts Using Deep Belief Network (2012)
Salakhutdinov, R., Hinton, G.: Deep Boltzmann machines. In: Artificial Intelligence and Statistics, vol. 5, no. 3, pp. 448–455 (2009)
Bengio, Y.: Learning deep architectures for AI. Found. Trends Mach. Learn. 2(1), 1–127 (2009)
Fawcett, T.: An introduction to ROC analysis. Pattern Recogn. Lett. 27(8), 861–874 (2006)
Powers, D.: Evaluation: from precision, recall and F-measure to ROC, informedness, markedness & correlation. J. Mach. Learn. Technol. 2(1), 37–63 (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Niño-Peña, J.H., Hernández-Pérez, G.J. (2016). Price Direction Prediction on High Frequency Data Using Deep Belief Networks. In: Figueroa-García, J., López-Santana, E., Ferro-Escobar, R. (eds) Applied Computer Sciences in Engineering. WEA 2016. Communications in Computer and Information Science, vol 657. Springer, Cham. https://doi.org/10.1007/978-3-319-50880-1_7
Download citation
DOI: https://doi.org/10.1007/978-3-319-50880-1_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-50879-5
Online ISBN: 978-3-319-50880-1
eBook Packages: Computer ScienceComputer Science (R0)