Abstract
Trading strategies are constantly being employed in the financial markets in order to increase consistency, reduce human errors of judgment and boost the probability of taking profitable market positions. In this work, we attempt to transfer the knowledge of several different types of trading strategies to deep learning models. The trading strategies are applied on price data of foreign exchange trading pairs and are actual strategies used in production trading environments. Along with our approach to transfer the strategy knowledge, we introduce a preprocessing method of the original price candles making it suitable for use with Neural Networks. Our results suggest that the deep models that are tested perform better than simpler models and they can accurately learn a variety of trading strategies.
Similar content being viewed by others
References
Chen CH, Lu CY, Lin CB (2019) An intelligence approach for group stock portfolio optimization with a trading mechanism. Knowl Inf Syst 62:1–30. https://doi.org/10.1007/s10115-019-01353-2
Deng Y, Bao F, Kong Y, Ren Z, Dai Q (2017) Deep direct reinforcement learning for financial signal representation and trading. IEEE Trans Neural Netw Learn Syst 28(3):653–664
Frankel JA, Froot KA (1990) Chartists, fundamentalists, and trading in the foreign exchange market. Am Econ Rev 80(2):181–185
Froot KA, Scharfstein DS, Stein JC (1992) Herd on the street: informational inefficiencies in a market with short-term speculation. J Finance 47(4):1461–1484
Goumatianos N, Christou IT, Lindgren P, Prasad R (2017) An algorithmic framework for frequent intraday pattern recognition and exploitation in forex market. Knowl Inf Syst 53(3):767–804
He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE international conference on computer vision, pp 1026–1034
Hirshleifer D, Subrahmanyam A, Titman S (1994) Security analysis and trading patterns when some investors receive information before others. J Finance 49(5):1665–1698
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780
Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv:1502.03167
Jegadeesh N, Titman S (1993) Returns to buying winners and selling losers: implications for stock market efficiency. J Finance 48(1):65–91
Krishnamoorthy S (2018) Sentiment analysis of financial news articles using performance indicators. Knowl Inf Syst 56(2):373–394
Malkiel BG, Fama EF (1970) Efficient capital markets: a review of theory and empirical work. J Finance 25(2):383–417
Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529
Murphy JJ (1999) Technical analysis of the financial markets: a comprehensive guide to trading methods and applications. Penguin, Westminster
Neely C, Weller P, Dittmar R (1997) Is technical analysis in the foreign exchange market profitable? a genetic programming approach. J Financ Quant Anal 32(4):405–426
Nison S (2001) Japanese candlestick charting techniques: a contemporary guide to the ancient investment techniques of the Far East. Penguin, Westminster
Ozorhan MO, Toroslu IH, Sehitoglu OT (2018) Short-term trend prediction in financial time series data. Knowl Inf Syst 61:1–33. https://doi.org/10.1007/s10115-018-1303-xs
Pai PF, Lin CS (2005) A hybrid arima and support vector machines model in stock price forecasting. Omega 33(6):497–505
Petropoulos A, Chatzis SP, Siakoulis V, Vlachogiannakis N (2017) A stacked generalization system for automated forex portfolio trading. Expert Syst Appl 90:290–302
Shiller RJ (1987) Investor behavior in the October 1987 stock market crash: survey evidenc. NBER Working Paper No. w2446, Available at SSRN: https://ssrn.com/abstract=227115
Shiller RJ, Fischer S (1984) Stock prices and social dynamics. Brook Pap Econ Act 2:457–510
Silver D, Huang A, Maddison CJ, Guez A, Sifre L, van den Driessche G, Schrittwieser J, Antonoglou I, Panneershelvam V, Lanctot M et al (2016) Mastering the game of go with deep neural networks and tree search. Nature 529(7587):484
Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958
Taylor MP, Allen H (1992) The use of technical analysis in the foreign exchange market. J Int Money Finance 11(3):304–314
Tieleman T, Hinton G (2012) Lecture 6.5-rmsprop: divide the gradient by a running average of its recent magnitude. COURSERA Neural Netw Mach Learn 4(2):26–31
Tsantekidis A, Passalis N, Tefas A, Kanniainen J, Gabbouj M, Iosifidis A (2017a) Forecasting stock prices from the limit order book using convolutional neural networks. In: 2017 IEEE 19th conference on business informatics (CBI), vol 1. IEEE, pp 7–12
Tsantekidis A, Passalis N, Tefas A, Kanniainen J, Gabbouj M, Iosifidis A (2017b) Using deep learning to detect price change indications in financial markets. In: 2017 25th European signal processing conference (EUSIPCO). IEEE, pp 2511–2515
Tsantekidis A, Passalis N, Tefas A, Kanniainen J, Gabbouj M, Iosifidis A (2018) Using deep learning for price prediction by exploiting stationary limit order book features. arXiv:1810.09965
Van den Oord A, Dieleman S, Zen H, Simonyan K, Vinyals O, Graves A, Kalchbrenner N, Senior AW, Kavukcuoglu K (2016) Wavenet: a generative model for raw audio. In: SSW, p 125
Wang J, Zhou S, Guan J (2012) Detecting potential collusive cliques in futures markets based on trading behaviors from real data. Neurocomputing 92:44–53
Werbos PJ (1990) Backpropagation through time: what it does and how to do it. Proc IEEE 78(10):1550–1560
Zhang X, Li Y, Wang S, Fang B, Philip SY (2019) Enhancing stock market prediction with extended coupled hidden markov model over multi-sourced data. Knowl Inf Syst 61(2):1071–1090
Acknowledgements
We kindly thank SpeedLab AG for providing their expertise on the matter of FOREX trading and the comprehensive dataset of FOREX currency pairs. This research has been co-financed by the European Union and Greek national funds through the Operational Program Competitiveness, Entrepreneurship and Innovation, under the call RESEARCH - CREATE - INNOVATE (Project code: T2EDK-02094). Avraam Tsantekidis was solely funded by a scholarship from the State Scholarship Foundation (IKY) according to the “Strengthening Human Research Resources through the Pursuit of Doctoral Research” act, with resources from the “Human Resources Development, Education and Lifelong Learning 2014–2020” program.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Tsantekidis, A., Tefas, A. Transferring trading strategy knowledge to deep learning models. Knowl Inf Syst 63, 87–104 (2021). https://doi.org/10.1007/s10115-020-01510-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10115-020-01510-y