Volume 2, Issue 4 (11-2020)                   sjamao 2020, 2(4): 1-11 | Back to browse issues page


XML Persian Abstract Print


Faculty of Industry Engineering, Department of Socio-Economic Systems, Sharif University of Technology, Iran.
Abstract:   (1845 Views)
In this study, it is presented a new hybrid model based on deep neural networks to predict the direction and magnitude of the Forex market movement in the short term. The overall model presented is based on the scalping strategy and is provided for high frequency transactions. The proposed hybrid model is based on a combination of three models based on deep neural networks. The first model is a deep neural network with a multi-input structure consisting of a combination of Long Short Term Memory layers. The second model is a deep neural network with a multi-input structure made of a combination of one-dimensional Convolutional Neural network layers. The third model has a simpler structure and is a multi-input model of the Multi-Layer Perceptron layers. The overall model was also a model based on the majority vote of three top models. This study showed that models based on Long Short-Term Memory layers provided better results than the other models and even hybrid models with more than 70% accurate.
Full-Text [PDF 455 kb]   (1507 Downloads)    
Type of Study: Research | Subject: Mathematical and Quantitative Methods
Received: 2020/09/15 | Revised: 2020/10/24 | Accepted: 2020/10/30 | Published: 2020/11/25

References
1. Zhang G, Eddy Patuwo B, Hu MY. Forecasting with artificial neural networks: The state of the art. Int J Forecast. 1998; 14(1): 35-62. [DOI:10.1016/S0169-2070(97)00044-7]
2. Lawrence R. Using neural networks to forecast stock market prices. 1997; 1-21.
3. Tsibouris G, Zeidenberg M. Testing the efficient markets hypothesis with gradient descent algorithms. Neural Net Cap Market. 1995; 127-136.
4. Tsai CF, Hsiao YC. Combining multiple feature selection methods for stock prediction: :union:, intersection, and multi-intersection approaches. Decis Support Syst. 2010; 50(1): 258-269. [DOI:10.1016/j.dss.2010.08.028]
5. Hadavandi E, Shavandi H, Ghanbari A. Integration of genetic fuzzy systems and artificial neural networks for stock price forecasting. Knowl Base Syst. 2010; 23(8): 800-808. [DOI:10.1016/j.knosys.2010.05.004]
6. Barak S, Arjmand A, Ortobelli S. Fusion of multiple diverse predictors in stock market. Inf Fusion. 2017; 36: 90-102. [DOI:10.1016/j.inffus.2016.11.006]
7. Ballings M, Van Den Poel D, Hespeels N, Gryp R. Expert systems with applications evaluating multiple classifiers for stock price direction prediction. Expert Syst Appl. 2015; May. [DOI:10.1016/j.eswa.2015.05.013]
8. Sowmya R, Suneetha KR. Data mining with big data. Proccidings of the 11th International Conference Intelligent Systems Control. ISCO 2017; 26(1): 246-250. [DOI:10.1109/ISCO.2017.7855990]
9. Tsai C-F, Wang S-P. Stock price forecasting by hybrid machine learning. Proccidings of the International Multiconference Engineering and Computer Science. 2009; I: 2210.
10. Rather AM, Agarwal A, Sastry VN. Recurrent neural network and a hybrid model for prediction of stock returns. Expert Syst Appl. 2015; 42(6): 3234-3241. [DOI:10.1016/j.eswa.2014.12.003]
11. Norris E. Scalping: small quick profits can add up. Investopedia. 2019; https://www.investopedia.com/articles/trading/05/scalping.asp

Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.