Deep LSTM with Reinforcement Learning Layer for Financial Trend Prediction in FX High Frequency Trading Systems
Source abstract
Abstract
High-frequency trading is a method of intervention on the financial markets that uses sophisticated software tools, and sometimes also hardware, with which to implement high-frequency negotiations, guided by mathematical algorithms, that act on markets for shares, options, bonds, derivative instruments, commodities, and so on. HFT strategies have reached considerable volumes of commercial traffic, so much so that it is estimated that they are responsible for most of the transaction traffic of some stock exchanges, with percentages that, in some cases, exceed 70% of the total. One of the main issues of the HFT systems is the prediction of the medium-short term trend. For this reason, many algorithms have been proposed in literature. The author proposes in this work the use of an algorithm based both on supervised Deep Learning and on a Reinforcement Learning algorithm for forecasting the short-term trend in the currency FOREX (FOReign EXchange) market to maximize the return on investment in an HFT algorithm. With an average accuracy of about 85%, the proposed algorithm is able to predict the medium-short term trend of a currency cross based on the historical trend of this and by means of correlation data with other currency crosses using techniques known in the financial field with the term arbitrage. The final part of the proposed pipeline includes a grid trading engine which, based on the aforementioned trend predictions, will perform high frequency operations in order to maximize profit and minimize drawdown. The trading system has been validated over several financial years and on the EUR/USD cross confirming the high performance in terms of Return of Investment (98.23%) in addition to a reduced drawdown (15.97 %) which confirms its financial sustainability.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Stock Market Forecasting Methods · Financial Markets and Investment Strategies · Complex Systems and Time Series Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
STMicroelectronics S.r.l.–ADG Central R&D Group, 95121 Catania, Italy
References (34)
Show source-provided references
1. Rundo, F., Trenta, F., Di Stallo, A.L., and Battiato, S. (2019). Advanced Markov-Based Machine Learning Framework for Making Adaptive Trading System. Computation, 7.10.3390/computation7010004 ↗
2. Rundo, F., Trenta, F., di Stallo, A.L., and Battiato, S. (2019). Grid Trading System Robot (GTSbot): A Novel Mathematical Algorithm for Trading FX Market. Appl. Sci., 9.10.3390/app9091796 ↗
3. Nti, I.K., Adekoya, A.F., and Weyori, B.A. (2019). A systematic review of fundamental and technical analysis of stock market predictions. Artif. Intell. Rev., 1–5.10.1007/s10462-019-09754-z ↗
4. Vlasenko, A., Vlasenko, N., Vynokurova, O., Bodyanskiy, Y., and Peleshko, D. (2019). A Novel Ensemble Neuro-Fuzzy Model for Financial Time Series Forecasting. Data, 4.10.3390/data4030126 ↗
5. Hybrid fuzzy neural network to predict price direction in the German DAX-30 index10.3846/tede.2018.6394 ↗
6. Deep Robust Reinforcement Learning for Practical Algorithmic Trading10.1109/ACCESS.2019.2932789 ↗
7. Si, W., Li, J., Ding, P., and Rao, R. (2017, January 9–10). A Multi-objective Deep Reinforcement Learning Approach for Stock Index Future’s Intraday Trading. Proceedings of the 2017 10th International Symposium on Computational Intelligence and Design (ISCID), Hangzhou, China.10.1109/ISCID.2017.210 ↗
8. Local Energy Trading Behavior Modeling With Deep Reinforcement Learning10.1109/ACCESS.2018.2876652 ↗
9. Kumar, P.H., and Patil, S.B. (2018, January 20–22). Forecasting volatility trend of INR USD currency pair with deep learning LSTM techniques. Proceedings of the 3rd International Conference on Computational Systems and Information Technology for Sustainable Solutions (CSITSS), Bengaluru, India.10.1109/CSITSS.2018.8768767 ↗
10. Ma, Y., and Han, R. (2018, January 17–20). Research on stock trading strategy based on deep neural network. Proceedings of the 18th International Conference on Control, Automation and Systems (ICCAS), PyeongChang, Korea.
11. Chen, C.T., Chen, A., and Huang, S. (2018, January 28–31). Cloning Strategies from Trading Records using Agent-based Reinforcement Learning Algorithm. Proceedings of the IEEE International Conference on Agents (ICA), Singapore.10.1109/AGENTS.2018.8460078 ↗
12. Korczak, J., and Hemes, M. (2017, January 3–6). Deep learning for financial time series forecasting in A-Trader system. Proceedings of the Federated Conference on Computer Science and Information Systems (FedCSIS), Prague, Czech Republic.10.15439/2017F449 ↗
13. Wang, J., Sun, T., Liu, B., Cao, Y., and Wang, D. (2018, January 17–20). Financial Markets Prediction with Deep Learning. Proceedings of the 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), Orlando, FL, USA.10.1109/ICMLA.2018.00022 ↗
14. Lee, R.S.T. (2019). Chaotic Type-2 Transient-Fuzzy Deep Neuro-Oscillatory Network (CT2TFDNN) for Worldwide Financial Prediction. IEEE Trans. Fuzzy Syst. May.10.1007/978-981-32-9796-8_12 ↗
15. Zarkias, K.S., Passalis, N., Tsantekidis, A., and Tefas, A. (2019, January 12–17). Deep Reinforcement Learning for Financial Trading Using Price Trailing. Proceedings of the ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK.10.1109/ICASSP.2019.8683161 ↗
16. The limits of arbitrage10.1111/j.1540-6261.1997.tb03807.x ↗
17. Conoci, S., Rundo, F., Petralta, S., and Battiato, S. (2018, January 4–6). Advanced skin lesion discrimination pipeline for early melanoma cancer diagnosis towards PoC devices. Proceedings of the IEEE 2017 European Conference on Circuit Theory and Design (ECCTD), Catania, Italy.10.1109/ECCTD.2017.8093310 ↗
18. Bio-Inspired Feed-Forward System for Skin Lesion Analysis, Screening and Follow-Up
19. Evaluation of Levenberg–Marquardt neural networks and stacked autoencoders clustering for skin lesion analysis, screening and follow-up10.1049/iet-cvi.2018.5195 ↗
20. Adaptive Compression of Stereoscopic Images
21. Oral metronomic vinorelbine in advanced non-small cell lung cancer patients unfit for chemotherapy10.21873/anticanres.12647 ↗
22. LSTM recurrent networks learn simple context-free and context-sensitive languages10.1109/72.963769 ↗
23. Learning precise timing with LSTM recurrent networks
24. Long short-term memory10.1162/neco.1997.9.8.1735 ↗
25. Jithesh, V., Sagayaraj, M.J., and Srinivasa, K.G. (2017, January 9–10). LSTM recurrent neural networks for high resolution range profile based radar target classification. Proceedings of the 3rd International Conference on Computational Intelligence & Communication Technology (CICT), Ghaziabad, India.10.1109/CIACT.2017.7977298 ↗
26. Balouji, E., Gu, I.Y.H., Bollen, M.H.J., Bagheri, A., and Nazari, M. (2018, January 13–16). A LSTM-based deep learning method with application to voltage dip classification. Proceedings of the 18th International Conference on Harmonics and Quality of Power (ICHQP), Ljubljana, Slovenia.10.1109/ICHQP.2018.8378893 ↗
27. A nonlinear pattern recognition pipeline for PPG/ECG medical assessments10.1007/978-3-030-04324-7_57 ↗
28. Rundo, F., Ortis, A., Battiato, S., and Conoci, S. (2018). Advanced Bio-Inspired System for Noninvasive Cuff-Less Blood Pressure Estimation from Physiological Signal Analysis. Computation, 6.10.3390/computation6030046 ↗
29. Characterization of sipms with nir long-pass interferential and plastic filters10.1109/JPHOT.2018.2834738 ↗
30. PPG/ECG multisite combo system based on SiPM technology10.1007/978-3-030-04324-7_44 ↗
31. Rundo, F., Banna, G.L., and Conoci, S. (2019). Bio-Inspired Deep-CNN Pipeline for Skin Cancer Early Diagnosis. Computation, 7.10.3390/computation7030044 ↗
32. Self Organizing Motor Maps for Color-Mapped Image Re-Indexing10.1109/TIP.2007.909415 ↗
33. (2019, September 12). Tickstory—Historical Data & Resources for Traders. Available online: https://tickstory.com/.
34. (2019, September 12). STM32 Platform. Available online: https://www.st.com/content/st_com/en/about/innovation---technology/artificial-intelligence.html.