THE COMPARISON OF LONG SHORT-TERM MEMORY AND BIDIRECTIONAL LONG SHORT-TERM MEMORY FOR FORECASTING COAL PRICE
Abstract
Coal remains vital for global energy despite recent demand fluctuations due to the COVID-19 pandemic and geopolitical tensions. The International Energy Agency (IEA) projected a decline in global coal demand starting in early 2024, driven by increasing renewable energy adoption. As one of the top coal exporters, Indonesia must adjust to these changes. This study aims to forecast future coal prices using historical data from Indonesia's Ministry of Energy and Mineral Resources (KESDM), applying and comparing Long Short-Term Memory (LSTM) and Bidirectional LSTM (BiLSTM) models. While BiLSTM has shown advantages in other contexts and studies, its effectiveness for coal price forecasting remains underexplored. To ensure robust predictions, we employ walk-forward validation, which divides the data into six segments and evaluates 90 hyperparameter combinations across all segments. The BiLSTM model consistently outperforms the LSTM model, achieving lower average RMSE and MAPE values. Specifically, BiLSTM records an average MAPE of 7.847 and RMSE of 10.485, compared to LSTM's 10.442 and 11.993, respectively. The Diebold-Mariano (DM) test using squared error and absolute error loss functions further corroborates these findings, with most segments showing significant improvements in favor of BiLSTM, indicated by negative DM-test statistics and p-values below 0.01 or 0.10. This superior performance continues into the testing data, where BiLSTM maintains lower error metrics and a significant result of the DM test, underscoring its reliability for forecasting. In the final stage, the forecasts from both models indicate a nearly linear downward trend in coal prices over the next 18 months, aligning with the International Energy Agency's 2023 projection of a structural decline in coal demand driven by the sustained growth of clean energy technologies.
Downloads
References
S. Makkl, “Analis Ungkap Alasan Konflik Rusia-Ukraina Bisa Terbangkan Batu Bara,” CNN Indonesia. Accessed: Mar. 12, 2024. [Online]. Available: https://www.cnnindonesia.com/ekonomi/20220307174517-85-767904/analis-ungkap-alasan-konflik-rusia-ukraina-bisa-terbangkan-batu-bara.
IEA, “Global coal demand set to remain at record levels in 2023,” International Energy Agency’s. Accessed: Aug. 21, 2024. [Online]. Available: https://www.iea.org/news/global-coal-demand-set-to-remain-at-record-levels-in-2023.
IEA, “Global coal demand expected to decline in coming years,” International Energy Agency’s. Accessed: Aug. 21, 2024. [Online]. Available: https://www.iea.org/news/global-coal-demand-expected-to-decline-in-coming-years.
ESDM, “HARGA BATUBARA ACUAN,” KEMENTERIAN ENERGI DAN SUMBER DAYA MINERAL. Accessed: Mar. 12, 2024. [Online]. Available: https://www.minerba.esdm.go.id/harga_acuan.
S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Comput, vol. 9, no. 8, pp. 1735–1780, Nov. 1997, doi: 10.1162/neco.1997.9.8.1735.
T. Gao, Y. Chai, and Y. Liu, “Applying Long Short Term Momory Neural Networks for Predicting Stock Closing Price,” in 2017 8th IEEE International Conference on Software Engineering and Service Science (ICSESS), IEEE, Nov. 2017, pp. 575–578. doi: 10.1109/ICSESS.2017.8342981.
Z. Zhang, “Comparison of LSTM and ARIMA in Price Forecasting: Evidence from Five Indexes,” 2024, pp. 40–46. doi: 10.2991/978-94-6463-268-2_6.
S. Siami-Namini, N. Tavakoli, and A. Siami Namin, “A Comparison of ARIMA and LSTM in Forecasting Time Series,” in Proceedings - 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018, Institute of Electrical and Electronics Engineers Inc., Jul. 2018, pp. 1394–1401. doi: 10.1109/ICMLA.2018.00227.
H. Wu, S. Chen, and Y. Ding, “Comparison of ARIMA and LSTM for Stock Price Prediction,” Financial Engineering and Risk Management, vol. 6, no. 1, 2023, doi: 10.23977/ferm.2023.060101.
R. L. Abduljabbar, H. Dia, and P.-W. Tsai, “Unidirectional and Bidirectional LSTM Models for Short-Term Traffic Prediction,” J Adv Transp, vol. 2021, pp. 1–16, Mar. 2021, doi: 10.1155/2021/5589075.
S. Wang, “A Stock Price Prediction Method Based on BiLSTM and Improved Transformer,” IEEE Access, vol. 11, pp. 104211–104223, 2023, doi: 10.1109/ACCESS.2023.3296308.
S. Siami-Namini, N. Tavakoli, and A. S. Namin, “The Performance of LSTM and BiLSTM in Forecasting Time Series,” in 2019 IEEE International Conference on Big Data (Big Data), IEEE, Dec. 2019, pp. 3285–3292. doi: 10.1109/BigData47090.2019.9005997.
D. G. da Silva and A. A. de M. Meneses, “Comparing Long Short-Term Memory (LSTM) and bidirectional LSTM deep neural networks for power consumption prediction,” Energy Reports, vol. 10, pp. 3315–3334, Nov. 2023, doi: 10.1016/j.egyr.2023.09.175.
T. Handhayani, I. Lewenusa, D. E. Herwindiati, and J. Hendryli, “A Comparison of LSTM and BiLSTM for Forecasting the Air Pollution Index and Meteorological Conditions in Jakarta,” in 2022 5th International Seminar on Research of Information Technology and Intelligent Systems (ISRITI), IEEE, Dec. 2022, pp. 334–339. doi: 10.1109/ISRITI56927.2022.10053078.
S. P. Prahesti, I. D. Sulvianti, and Y. Angraini, “PERAMALAN HARGA BATU BARA ACUAN MENGGUNAKAN METODE AUTOREGRESSIVE INTEGRATED MOVING AVERAGE DAN FUNGSI TRANSFER,” Xplore: Journal of Statistics, vol. 12, no. 1, pp. 1–11, Jan. 2023, doi: 10.29244/xplore.v12i1.1100.
Y. Zheng, K. Yuan, and L. Dai, “Research on Coal Price Forecast based on ARIMA and SVM combination Model,” in E3S Web of Conferences, EDP Sciences, May 2021. doi: 10.1051/e3sconf/202125702008.
X. Liu, “Research on the forecast of coal price based on LSTM with improved Adam optimizer,” J Phys Conf Ser, vol. 1941, no. 1, p. 012069, Jun. 2021, doi: 10.1088/1742-6596/1941/1/012069.
X. Xu and Y. Zhang, “Thermal coal price forecasting via the neural network,” Intelligent Systems with Applications, vol. 14, p. 84, 2022, doi: 10.1016/j.iswa.2022.20.
Z. Alameer, A. Fathalla, K. Li, H. Ye, and Z. Jianhua, “Multistep-ahead forecasting of coal prices using a hybrid deep learning model,” Resources Policy, vol. 65, p. 101588, Mar. 2020, doi: 10.1016/j.resourpol.2020.101588.
S. Pan, “Coal Price Prediction based on LSTM,” Journal of Physics: Conference Series, vol. 1802, no. 4, p. 042055, Mar. 2021, doi: 10.1088/1742-6596/1802/4/042055.
F.X. Diebold and R.S. Mariano, “Comparing predictive accuracy,” JBES, vol. 13, pp. 253-263, Jul 1995.
S. Panigrahi and H. S. Behera,” Effect of Normalization Techniques on Univariate Time Series Forecasting using Evolutionary Higher Order Neural Network,” IJEAT, vol.3, Dec 2013.
D. Singh and B. Singh, “Investigating the impact of data normalization on classification performance,” Appl Soft Comput, vol.97, 2020, doi: 10.1016/j.asoc.2019.105524.
J. N. Van Rijn and F. Hutter,”Hyperparameter importance across datasets,” in Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery, Jul. 2018, pp. 2367–2376. doi: 10.1145/3219819.3220058.
A. García-Medina and E. Aguayo-Moreno, “LSTM–GARCH Hybrid Model for the Prediction of Volatility in Cryptocurrency Portfolios,” Comput Econ, vol. 63, no. 4, pp. 1511–1542, Apr. 2024, doi: 10.1007/s10614-023-10373-8.
L. Mualifah, K. A. Notodipuro, and A. M. Soleh, “A comparative study of GARCH, LSTM, and HYBRID GARCH– LSTM models for analyzing the dynamical pattern of stock price volatility,” M.S thesis, IPB University, Bogor, 2022.
D. A. Dzulhijjah, Kusrini, and K. A. Yuana, “IMPLEMENTASI ALGORITMA BI-LSTM DALAM MENDETEKSI ENTITAS WAKTU DAN LOKASI KEBAKARAN HUTAN,” 2023.
R. Pardo, “The Evaluation and Optimization of Trading Strategies Second Edition,” 2007.
R. Hyndman and G. Athanasopoulos, Forecasting: Principles and Practice, 3rd ed. Melbourne: OTexts, 2021.
C.D. Lewis, Industrial and business forecasting methods: A practical guide to exponential smoothing and curve fitting, London; Boston: Butterworth Scientific, 1982.
P. Nimmani, S. Vodithala, and V. Polepally, “Neural Network Based Integrated Model for Information Retrieval,” in 2021 5th International Conference on Intelligent Computing and Control Systems (ICICCS), IEEE, May 2021, pp. 1286–1289. doi: 10.1109/ICICCS51141.2021.9432241.
D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” Dec. 2014, [Online]. Available: http://arxiv.org/abs/1412.6980.
X. Glorot, A. Bordes, and Y. Bengio, “Deep Sparse Rectifier Neural Networks,” 2011.
Copyright (c) 2025 Indra Rivaldi Siregar, Adhiyatma Nugraha, Khairil Anwar Notodiputro, Yenni Angraini, Laily Nissa Atul Mualifah
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this Journal agree to the following terms:
- Author retain copyright and grant the journal right of first publication with the work simultaneously licensed under a creative commons attribution license that allow others to share the work within an acknowledgement of the work’s authorship and initial publication of this journal.
- Authors are able to enter into separate, additional contractual arrangement for the non-exclusive distribution of the journal’s published version of the work (e.g. acknowledgement of its initial publication in this journal).
- Authors are permitted and encouraged to post their work online (e.g. in institutional repositories or on their websites) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published works.
1.gif)
