ACTIVATION FUNCTION IN LSTM FOR IMPROVED FORECASTING OF CLOSING NATURAL GAS STOCK PRICES
Abstract
The closing price of natural gas stocks greatly influences investment decisions and the energy industry. Predicting prices correctly can greatly help investors, market participants, and all parties involved, as it allows for making better decisions and optimizing investment portfolios. By using deep learning methods to role model various LSTM activation functions, such as Sigmoid, ReLU, and Tanh, this exploration will hopefully help understand complex patterns in time series data. By finding an appropriate forecasting method, all parties involved can reduce the environmental impact. The experimental results show that the model with ReLU activation function has the highest R2 value of 0.960 in both the training and test sets, and the model with Tanh activation function is also successful, with R2 values of 0.950 in the training set and 0.949 in the test set, and an MSE of 0.002. The model with the sigmoid activation function was slightly lower, with R2 values of 0.931 in the training set and 0.943 in the test set, and an MSE of 0.003. These findings indicate that the LSTM model with the ReLU activation function is considered better for predicting the closing price of natural gas stocks. These findings may help investors, stakeholders, and market participants choose the most accurate model to predict the closing price of natural gas stocks.
Downloads
References
L. Zhan and Z. Tang, ‘Natural Gas Price Forecasting by a New Hybrid Model Combining Quadratic Decomposition Technology and LSTM Model’, Mathematical Problems in Engineering, vol. 2022, no. 1, p. 5488053, 2022, doi: 10.1155/2022/5488053.
A. Manowska, A. Rybak, A. Dylong, and J. Pielot, ‘Forecasting of Natural Gas Consumption in Poland Based on ARIMA-LSTM Hybrid Model’, Energies, vol. 14, no. 24, Art. no. 24, Jan. 2021, doi: 10.3390/en14248597.
J. Liu, S. Wang, N. Wei, X. Chen, H. Xie, and J. Wang, ‘Natural gas consumption forecasting: A discussion on forecasting history and future challenges’, Journal of Natural Gas Science and Engineering, vol. 90, p. 103930, Jun. 2021, doi: 10.1016/j.jngse.2021.103930.
S. Devi, S. Warasniasih, and P. Masdiantini, ‘The Impact of COVID-19 Pandemic on the Financial Performance of Firms on the Indonesia Stock Exchange’, Journal of Economics, Business, & Accountancy Ventura, vol. 23, Nov. 2020, doi: 10.14414/jebav.v23i2.2313.
I. E. Livieris, E. Pintelas, N. Kiriakidou, and S. Stavroyiannis, ‘An Advanced Deep Learning Model for Short-Term Forecasting U.S. Natural Gas Price and Movement’, in Artificial Intelligence Applications and Innovations. AIAI 2020 IFIP WG 12.5 International Workshops, I. Maglogiannis, L. Iliadis, and E. Pimenidis, Eds., Cham: Springer International Publishing, 2020, pp. 165–176. doi: 10.1007/978-3-030-49190-1_15.
W. Qiao, W. Liu, and E. Liu, ‘A combination model based on wavelet transform for predicting the difference between monthly natural gas production and consumption of U.S.’, Energy, vol. 235, p. 121216, Nov. 2021, doi: 10.1016/j.energy.2021.121216.
R. Guan, A. Wang, Y. Liang, J. Fu, and X. Han, ‘International Natural Gas Price Trends Prediction with Historical Prices and Related News’, Energies, vol. 15, no. 10, Art. no. 10, Jan. 2022, doi: 10.3390/en15103573.
S. Karasu and A. Altan, ‘Crude oil time series prediction model based on LSTM network with chaotic Henry gas solubility optimization’, Energy, vol. 242, p. 122964, Mar. 2022, doi: 10.1016/j.energy.2021.122964.
D. Li, Y. Zhang, D. Gong, L. Pan, and Y. Zhao, ‘Gas Data Prediction Based on LSTM Neural Network’, IOP Conf. Ser.: Mater. Sci. Eng., vol. 750, no. 1, p. 012175, Feb. 2020, doi: 10.1088/1757-899X/750/1/012175.
B. Liu, J. Chen, H. Wang, and Q. Wang, ‘Renewable Energy and Material Supply Risks: a Predictive Analysis Based on An LSTM Model’, Frontiers in Energy Research, vol. 8, 2020, Accessed: Jan. 17, 2024. [Online]. Available: https://www.frontiersin.org/articles/10.3389/fenrg.2020.00163
J. Berrisch and F. Ziel, ‘Distributional modeling and forecasting of natural gas prices’, Journal of Forecasting, vol. 41, no. 6, pp. 1065–1086, 2022, doi: 10.1002/for.2853.
S. Kiliçarslan and M. Celik, ‘RSigELU: A nonlinear activation function for deep neural networks’, Expert Systems with Applications, vol. 174, p. 114805, Jul. 2021, doi: 10.1016/j.eswa.2021.114805.
M. H. Essai Ali, A. B. Abdel-Raman, and E. A. Badry, ‘Developing Novel Activation Functions Based Deep Learning LSTM for Classification’, IEEE Access, vol. 10, pp. 97259–97275, 2022, doi: 10.1109/ACCESS.2022.3205774.
K. Biswas, S. Kumar, S. Banerjee, and A. K. Pandey, ‘TanhSoft—Dynamic Trainable Activation Functions for Faster Learning and Better Performance’, IEEE Access, vol. 9, pp. 120613–120623, 2021, doi: 10.1109/ACCESS.2021.3105355.
N. Alamsyah, T. P. Yoga, and B. Budiman, ‘Improving Traffic Density Prediction Using Lstm With Parametric Relu (PRELU) Activation’, JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer), vol. 9, no. 2, Art. no. 2, Feb. 2024, doi: 10.33480/jitk.v9i2.5046.
S. Mastromichalakis, ‘ALReLU: A different approach on Leaky ReLU activation function to improve Neural Networks Performance’, arXiv preprint arXiv:2012.07564, 2020, doi: 10.48550/arXiv.2012.07564
L. Fernando Santos, M. Gattass, A. Correa Silva, F. Miranda, C. Siedschlag, and R. Ribeiro, ‘Natural gas detection in onshore data using transfer learning from a LSTM pre-trained with offshore data’, in SEG Technical Program Expanded Abstracts 2020, in SEG Technical Program Expanded Abstracts. , Society of Exploration Geophysicists, 2020, pp. 1190–1195. doi: 10.1190/segam2020-3426303.1.
‘Oil, Gas & Other Fuels Futures Data’. Accessed: Jun. 26, 2024. [Online]. Available: https://www.kaggle.com/datasets/guillemservera/fuels-futures-data?resource=download
Copyright (c) 2024 budimann budiman, Nur Alamsyah, R. Yadi Rakhman Alamsyah
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
-a.jpg)
-b.jpg)
