Transactions on Data Analysis in Social Science

Transactions on Data Analysis in Social Science

A Review of Deep Learning Methods for Financial Market Prediction

Document Type : Original Article

Authors
A. Karimi Dastgerdi
F. Zamani Boroujeni
Department of Computer Engineering, Isfahan (Khorasgan) Branch, Islamic Azad University, Isfahan, Iran
10.47176/TDASS.2020.164
Abstract
Financial market prediction plays a crucial role for investors and financial institutions aiming to optimize returns and minimize risks. Over the past decades, considerable research has focused on developing effective and accurate methods for forecasting financial market trends. Traditional statistical models often face limitations in capturing the nonlinear and complex dynamics of financial time series. In contrast, deep learning techniques provide advanced analytical and predictive frameworks capable of uncovering latent structures and intricate patterns within large-scale financial datasets. This study systematically reviews recent deep learning approaches applied to the prediction of financial time series, including recurrent neural networks (RNNs), long short-term memory networks (LSTMs), convolutional neural networks (CNNs), and hybrid models. We evaluate these methods based on their architecture, data representation, and predictive performance, highlighting their respective strengths and weaknesses. Our analysis demonstrates that deep learning algorithms exhibit superior capabilities in modeling nonlinear dependencies and temporal correlations in financial data, enabling accurate forecasting of stock prices, indices, and other market indicators. Furthermore, while individual network architectures perform effectively, combining recurrent and convolutional layers often enhances prediction accuracy and robustness. The findings underscore the potential of deep learning as a powerful tool for financial decision-making, offering valuable insights for both researchers and practitioners in the field of computational finance.
Keywords
Deep Learning
Financial Markets
Time Series Prediction
Stock Price
Stock Exchange
[1]      Pinches, G. E. (1970). The random walk hypothesis and technical analysis. Financial Analysts Journal, 26(2), 104–110. https://doi.org/10.2469/faj.v26.n2.104
[2]      Weiss, G. (1992). Chaos hits Wall Street the theory that is! Business Week, 2, 138–140.
[3]      Hrasko, R., Pacheco, A. G., & Krohling, R. A. (2015). Time series prediction using restricted Boltzmann machines and backpropagation. Procedia Computer Science, 55, 990–999. https://doi.org/10.1016/j.procs.2015.07.104
[4]      Ying, C., Yang, M.-L., & Jun, L. (2015). Multiclass classification based on a deep convolutional neural network. Frontiers of Information Technology & Electronic Engineering, 16(11), 930–939. https://doi.org/10.1631/FITEE.1500125
[5]      Liu, W., Wang, Z., Liu, X., Zeng, N., Liu, Y., & Alsaadi, F. E. (2017). A survey of deep neural network architectures and their applications. Neurocomputing, 234, 11–26. https://doi.org/10.1016/j.neucom.2016.12.038
[6]      White, H. (1988). Economic prediction using neural networks: The case of IBM daily stock returns. In Proceedings of the IEEE International Conference on Neural Networks (pp. 451–458). IEEE. https://doi.org/10.1109/ICNN.1988.23959
[7]      Kim, K.-J., & Han, I. (2000). Genetic algorithms approach to feature discretization in artificial neural networks for the prediction of stock price index. Expert Systems with Applications, 19(2), 125–132. https://doi.org/10.1016/S0957-4174(00)00027-0
[8]      Garliauskas, A. (1999). Neural network chaos and computational algorithms of forecast in finance. In Proceedings of the 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No. 99CH37028) (Vol. 2, pp. 638–643). IEEE. https://doi.org/10.1109/ICSMC.1999.825335
[9]      Chong, E., Han, C., & Park, F. C. (2017). Deep learning networks for stock market analysis and prediction: Methodology, data representations, and case studies. Expert Systems with Applications, 83, 187–205. https://doi.org/10.1016/j.eswa.2017.04.030
[10]   Bengio, Y., Simard, P., & Frasconi, P. (1994). Learning long-term dependencies with gradient descent is difficult. IEEE Transactions on Neural Networks, 5(2), 157–166. https://doi.org/10.1109/72.279181
[11]   Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
[12]   Graves, A., Mohamed, A.-R., & Hinton, G. (2013). Speech recognition with deep recurrent neural networks. In 2013 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 6645–6649). IEEE. https://doi.org/10.1109/ICASSP.2013.6638947
[13]   Bao, W., Yue, J., & Rao, Y. (2017). A deep learning framework for financial time series using stacked autoencoders and long short-term memory. PLOS ONE, 12(7), e0180944. https://doi.org/10.1371/journal.pone.0180944
[14]   Chung, H., & Shin, K.-S. (2018). Genetic algorithm-optimized long short-term memory network for stock market prediction. Sustainability, 10(10), 3765. https://doi.org/10.3390/su10103765
[15]   Sang, C., & Di Pierro, M. (2019). Improving trading technical analysis with TensorFlow long short-term memory (LSTM) neural network. The Journal of Finance and Data Science, 5(1), 1–11. https://doi.org/10.1016/j.jfds.2018.10.003
[16]   Fischer, T., & Krauss, C. (2018). Deep learning with long short-term memory networks for financial market predictions. European Journal of Operational Research, 270(2), 654–669. https://doi.org/10.1016/j.ejor.2017.11.054
[17]   Kim, P. (2017). Matlab deep learning: With machine learning, neural networks and artificial intelligence. Springer.
[18]   Selvin, S., Vinayakumar, R., Gopalakrishnan, E., Menon, V. K., & Soman, K. (2017). Stock price prediction using LSTM, RNN and CNN-sliding window model. In 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI) (pp. 1643–1647). IEEE. https://doi.org/10.1109/ICACCI.2017.8126078
[19]   Tsantekidis, A., Passalis, N., Tefas, A., Kanniainen, J., Gabbouj, M., & Iosifidis, A. (2017). Forecasting stock prices from the limit order book using convolutional neural networks. In 2017 IEEE 19th Conference on Business Informatics (CBI) (Vol. 1, pp. 7–12). IEEE. https://doi.org/10.1109/CBI.2017.23
[20]   Hiransha, M., Gopalakrishnan, E., Menon, V. K., & Soman, K. (2018). NSE stock market prediction using deep-learning models. Procedia Computer Science, 132, 1351–1362. https://doi.org/10.1016/j.procs.2018.05.050
[21]   Sim, H. S., Kim, H. I., & Ahn, J. J. (2019). Is deep learning for image recognition applicable to stock market prediction? Complexity, 2019, Article 4324878. https://doi.org/10.1155/2019/4324878
[22]   Long, W., Lu, Z., & Cui, L. (2019). Deep learning-based feature engineering for stock price movement prediction. Knowledge-Based Systems, 164, 163–173. https://doi.org/10.1016/j.knosys.2018.10.034
[23]   Zhou, X., Pan, Z., Hu, G., Tang, S., & Zhao, C. (2018). Stock market prediction on high-frequency data using generative adversarial nets. Mathematical Problems in Engineering, 2018, Article 4907423. https://doi.org/10.1155/2018/4907423
Transactions on Data Analysis in Social Science
Volume 2, Issue 3
Summer 2020
Pages 164-172

  • Receive Date 04 June 2020
  • Revise Date 18 August 2020
  • Accept Date 20 September 2020