The development of accurate prediction models continues to be highly beneficial in myriad disciplines. Deep learning models
have performed well in stock price prediction and give high accuracy.
However, these models are largely affected by the vanishing gradient problem
escalated by some activation functions. This study proposes the use of the
Vanishing Gradient Resilient Optimized Gated Recurrent Unit (OGRU) model with a
scaled mean Approximation Coefficient (AC) time lag which should counter slow
convergence, vanishing gradient and large error metrics. This study employed
the Rectified Linear Unit (ReLU), Hyperbolic Tangent (Tanh), Sigmoid and
Exponential Linear Unit (ELU) activation functions. Real-life datasetsincluding the daily Apple
and 5-minute Netflix closing stock prices were used, and they were decomposed
using the Stationary Wavelet Transform (SWT). The decomposed series formed a decomposed data model
which was compared to an undecomposed data model with similar hyperparameters and different default lags. The Apple
daily dataset performed well with a Default_1 lag, using an undecomposed data model
and the ReLU, attaining 0.01312, 0.00854 and 3.67 minutes for RMSE, MAE and
runtime. The Netflix data performed best with the MeanAC_42 lag, using decomposed data model
and the ELU achieving 0.00620, 0.00487 and 3.01 minutes for the same metrics.
Ding, X., Zhang, Y., Liu, T. and Duan, J. (2014) Using Structured Events to Predict Stock Price Movement: An Empirical Investigation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, October 2014, 127-134. https://doi.org/10.3115/v1/D14-1148
[3]
Benrhmach, G., Namir, K., Namir, A. and Bouyaghroumni, J. (2020) Nonlinear Autoregressive Neural Network and Extended Kalman Filters for Prediction of Financial Time Series. Journal of Applied Mathematics, 2020, Article ID: 5057801. https://doi.org/10.1155/2020/5057801
[4]
Jegadeesh, N. and Titman, S. (1993) Returns to Buying Winners and Selling Losers: Implications for Stock Market Efficiency. The Journal of Finance, 48, 65-91. https://doi.org/10.1111/j.1540-6261.1993.tb04702.x
[5]
Nguyen, H., Baraldi, P. and Zio, E. (2021) Ensemble Empirical Mode Decomposition and Long Short-Term Memory Neural Network for Multi-Step Predictions of Time Series Signals in Nuclear Power Plants. Electronics, 283, 116-346. https://doi.org/10.1016/j.apenergy.2020.116346
[6]
Xiao, Q., Chaoqin, C. and Li, Z. (2017) Time Series Prediction Using Dynamic Bayesian Network. Optik, 135, 98-103. https://doi.org/10.1016/j.ijleo.2017.01.073
[7]
Wang, Y., Lin, K., Qi, Y., Lian, Q., Feng, S., Wu, Z. and Pan, G. (2018) Estimating Brain Connectivity with Varying-Length Time Lags Using a Recurrent Neural Network. IEEE Transactions on Biomedical Engineering, 65, 1953-1963. https://doi.org/10.1109/TBME.2018.2842769
[8]
Petneházi, G. (2019) Recurrent Neural Networks for Time Series Forecasting.
[9]
Munkhdalai, L., Li, M., Theera-Umpon, N., Auephanwiriyakul, S. and Ryu, K.H. (2020) VAR-GRU: A Hybrid Model for Multivariate Financial Time Series Prediction. Asian Conference on Intelligent Information and Database Systems, Phuket, 23-26 March 2020, 322-332. https://doi.org/10.1007/978-3-030-42058-1_27
[10]
Surakhi, O., Zaidan, M.A., Fung, P.L., Hossein, M.N., Serhan, S., AlKhanafseh, M., Ghoniem, R.M. and Hussein, T. (2021) Time-Lag Selection for Time-Series Forecasting Using Neural Network and Heuristic Algorithm. Electronics, 10, 18-25. https://doi.org/10.3390/electronics10202518
[11]
Al Wadi, S., Ismail, M.T., Altaher, A.M. and Karim, S.A.A. (2010) Forecasting Volatility Data Based on Wavelet Transforms and ARIMA Model. 2010 International Conference on Science and Social Research, Kuala Lumpur, 5-7 December 2010, 86-90. https://doi.org/10.1109/CSSR.2010.5773909
[12]
Abbasi, N.M., Aghaei, M. and Moradzadeh, F. (2015) Forecasting Stock Market Using Wavelet Transforms and Neural Networks and Arima (Case Study of Price Index of Tehran Stock Exchange). International Journal of Applied Operational Research, 5, 31-40.
[13]
Skehin, T., Crane, M. and Bezbradica, M. (2018) Day ahead Forecasting of FAANG Stocks Using ARIMA, LSTM Networks and Wavelets. CEUR Workshop Proceedings: Day Ahead Forecasting of FAANG Stocks Using ARIMA, LSTM Networks and Wavelets, Dublin, 6-7 December 2018, 334-340.
[14]
Lahmiri, S. (2014) Wavelet Low- and High-Frequency Components as Features for Predicting Stock Prices with Backpropagation Neural Networks. Journal of King Saud University—Computer and Information Sciences, 26, 218-227. https://doi.org/10.1016/j.jksuci.2013.12.001
[15]
Chandar, S.K., Sumathi, M. and Sivanandam, S.N. (2016) Prediction of Stock Market Price Using Hybrid of Wavelet Transform and Artificial Neural Network. Indian Journal of Science and Technology, 9, 1-5. https://doi.org/10.17485/ijst/2016/v9i8/87905
[16]
Kulaglic, A. and üstündağ, B.B. (2018) Stock Price Forecast Using Wavelet Transformations in Multiple Time Windows and Neural Networks. 2018 3rd International Conference on Computer Science and Engineering (UBMK), Sarajevo, 20-23 September 2018, 518-521. https://doi.org/10.1109/UBMK.2018.8566614
[17]
Jarrah, M. and Salim, N. (2019) A Recurrent Neural Network and a Discrete Wavelet Transform to Predict the Saudi Stock Price Trends. International Journal of Advanced Computer Science and Applications, 10, 155-162. https://doi.org/10.14569/IJACSA.2019.0100418
[18]
Štifanić, D., Musulin, J., Miočević, A., Baressi Šegota, S., Šubić, R. and Car, Z. (2020) Impact of COVID-19 on Forecasting Stock Prices: An Integration of Stationary Wavelet Transform and Bidirectional Long Short-Term Memory. Complexity, 2020, Article ID: 1846926. https://doi.org/10.1155/2020/1846926
[19]
Qiu, J., Wang, B. and Zhou, C. (2020) Forecasting Stock Prices with Long-Short Term Memory Neural Network Based on Attention Mechanism. PLOS ONE, 15, 222-227. https://doi.org/10.1371/journal.pone.0227222
[20]
Althelaya, K.A., Mohammed, S.A. and El-Alfy, E.M. (2021) Combining Deep Learning and Multiresolution Analysis for Stock Market Forecasting. IEEE Access, 9, 13099-13111. https://doi.org/10.1109/ACCESS.2021.3051872
[21]
Biazon, V. and Bianchi, R. (2020) Gated Recurrent Unit Networks and Discrete Wavelet Transforms Applied to Forecasting and Trading in the Stock Market. Anais do XVII Encontro Nacional de Inteligência Artificial e Computacional, 68, 650-661. https://doi.org/10.5753/eniac.2020.12167
[22]
Arévalo, A., Nino, J., León, D., Hernandez, G. and Sandoval, J. (2018) Deep Learning and Wavelets for High-Frequency Price Forecasting. International Conference on Computational Science, Wuxi, 11-13 June 2018, 385-399. https://doi.org/10.1007/978-3-319-93701-4_29
[23]
Wang, X., Xu, J., Shi, W. and Liu, J. (2019) OGRU: An Optimized Gated Recurrent Unit Neural Network. Journal of Physics: Conference Series, 1325, 12-89. https://iopscience.iop.org/article/10.1088/1742-6596/1325/1/012089 https://doi.org/10.1088/1742-6596/1325/1/012089
[24]
Ardila, D. and Sornette, D. (2016) Dating the Financial Cycle with Uncertainty Estimates: A Wavelet Proposition. Finance Research Letters, 19, 298-304. https://doi.org/10.1016/j.frl.2016.09.004
[25]
Miao, Y. (2019) A Deep Learning Approach for Stock Market Prediction. Computer Science Department, Stanford University, Stanford. http://cs230.stanford.edu/projects_fall_2020/reports/55614857.pdf
[26]
Adhinata, F.D. and Rakhmadani, D.P. (2021) Prediction of Covid-19 Daily Case in Indonesia Using Long Short Term Memory Method. Teknika, 10, 62-67. https://doi.org/10.34148/teknika.v10i1.328
[27]
Khalil, E.A.H., El Houby, E.M.F. and Mohamed, H.K. (2021) Deep Learning for Emotion Analysis in Arabic Tweets. Journal of Big Data, 8, 1-15. https://doi.org/10.1186/s40537-021-00523-w