Informatics and Applications
2022, Volume 16, Issue 3, pp 26-38
INCREASING FOREX TRADING PROFITABILITY WITH LSTM CANDLESTICK PATTERN RECOGNITION AND TICK VOLUME INDICATOR
- A. K. Gorshenin
- E. I. Guseynova
Abstract
The paper introduces the research of the effectiveness of using LSTM (Long-Short Term Memory) for candlestick data and a technical analysis indicator for a large number of the most common currency pairs (27 in total) over a long period in order to build automatic trading strategies. The achieved average total and annual return for 8 years of a model trading were 286% and 15.4%, respectively. It is more than 50 times higher than the values for the classic Buy & Hold trading strategy for the same period. In addition, the paper introduces a new technical indicator based on tick volumes which is an alternative trading strategy (the total and annual returns of LSTM models exceed it by an average of 7.2 and 2.3 times) as well as an additional feature to increase the profitability of the neural network strategy through the use of ensemble learning. For 37% of the analyzed currency pairs, the use of an ensemble of LSTMs allows one to increase further the total return by an average of 17.2%.
[+] References (16)
- Bholat, D., and D. Susskind. 2021. The assessment: Artificial intelligence and financial services. Oxford Rev. Econ. Pol. 37(3):417-434.
- Lin, Y., S. Liu, H. Yang, and H. Wu. 2021. Stock trend prediction using candlestick charting and ensemble machine
learning techniques with a novelty feature engineering scheme. IEEE Access 9:101433-101446.
- Lahmiri, S., and S. Bekiros. 2020. Intelligent forecasting with machine learning trading systems in chaotic intraday Bitcoin market. Chaos Soliton. Fract. 133:109641. 7 p.
- Rundo, F. 2019. Deep LSTM with reinforcement learning layer for financial trend prediction in FX high frequency trading systems. Appl. Sci. - Basel 9(20):4460. 18 p.
- Dinh, T.-A., and Y.-K. Kwon. 2018. An empirical study on importance of modeling parameters and trading volume- based features in daily stock trading using neural networks. Informatics 5(3):36. 12 p.
- Sezer, O. B., and A. M. Ozbayoglu. 2018. Algorithmic financial trading with deep convolutional neural networks: Time series to image conversion approach. Appl. Soft Comput. 70:525-538.
- Tsinaslanidis, P., and F Guijarro. 2020. What makes trading strategies based on chart recognition profitable? Expert Syst. 38(5):e12596. 17 p.
- Chen, J. H., and Y. C. Tsai. 2020. Encoding candlesticks as images for pattern classification using convolutional neural networks. Financial Innovation 6:26. 19 p.
- Hung, C.-C., and Y.-J. Chen. 2021. DPP: Deep predictor for price movement from candlestick charts. PLoS ONE 16(6):e0252404. 22 p.
- Wu, J. M.-T, Z. Li, N. Herencsar, B. Vo, and J. C.-W Lin.
2021. A graph-based CNN-LSTM stock price prediction algorithm with leading indicators. Multimedia Syst. 20 p. doi: 10.1007/s00530-021-00758-w.
- Sezer, O.B., A.M. Ozbayoglu, and E. Dogdu. 2017. A deep neural-network based stock trading system based
on evolutionary optimized technical analysis parameters. Procedia Comput. Sci. 114:473-480.
- JuHyok, U., L. PengYu, K. ChungSong, R. UnSok, and P. KyongSok. 2020. A new LSTM based reversal point prediction method using upward/downward reversal point feature sets. Chaos Soliton. Fract. 32:109559. 15 p.
- Tsantekidis, A., and A. Tefas. 2021. Transferring trading strategy knowledge to deep learning models. Knowl. Inf. Syst. 63:87-104.
- Edwards, R. D., J. Magee, and W. H. C. Bassetti. 2018. Technical analysis of stock trends. 11th ed. Boca Raton, FL: CRC Press. 685 p.
- Gorshenin, A. K., and V. Yu. Kuzmin. 2022. Statistical feature construction for forecasting accuracy increase and its applications in neural network based analysis. Mathematics 10(4):589. 21 p.
- Vilyaev, A. L., and A. K. Gorshenin. 2021. O modelirovanii torgovykh strategiy dlya valyutnykh par s ispol'zovaniem glubokikh neyronnykh setey i metoda skol'zyashchego razdeleniya smesey [On modeling trading strategies for currency pairs using deep neural networks and method of moving separation of mixtures]. Intellektual'nye sistemy. Teoriya i prilozheniya [Intelligent Systems. Theory and Applications] 25(4):92-95.
[+] About this article
Title
INCREASING FOREX TRADING PROFITABILITY WITH LSTM CANDLESTICK PATTERN RECOGNITION AND TICK VOLUME INDICATOR
Journal
Informatics and Applications
2022, Volume 16, Issue 3, pp 26-38
Cover Date
2022-10-10
DOI
10.14357/19922264220304
Print ISSN
1992-2264
Publisher
Institute of Informatics Problems, Russian Academy of Sciences
Additional Links
Key words
LSTM; ensemble learning; candlestick; technical indicator; FOREX; currency pairs
Authors
A. K. Gorshenin  and E. I. Guseynova 
Author Affiliations
Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences, 44-2 Vavilov Str., Moscow 119333, Russian Federation
M. V Lomonosov Moscow State University, 1 Leninskie Gory, GSP-1, Moscow 119991, Russian Federation
|