Kovid-19 Pandemi Süreci Altında Brent Ham Petrol Fiyatlarının Öngörülmesi: Koşullu Lstm Modeli
Özet
Yenilenemez güç kaynaklarından biri olan ham petrol, çağdaş endüstrinin can damarıdır. Sanayi, ulaşım, otomobil, kozmetik, enerji, kimya, ilaç gibi birçok sektörde kullanılan ham petrol, dünya ekonomisinde çok önemli yere sahiptir ve bu nedenle “siyah altın” olarak kabul edilmektedir. Bu çalışmada, Brent petrol fiyatları ARIMA, LSTM ve koşullu LSTM modelleri ile tahmin edilmiş ve 60 günlük öngörü değerleri elde edilmiştir. Tüm modellerde Brent petrol fiyatları, avro/dolar endeksi, doğalgaz fiyatı, ABD dolar endeksi, kovid-19 kukla değişkeni girdi olarak kullanılmıştır. Bu çalışmanın literatüre katkısı koşullu LSTM modeli kullanarak kovid-19 etkisinin eğitim setine dahil edilmeksizin yardımcı bir özellik olarak ele alınmasıdır.
Referanslar
Altan, A., & Karasu, S. (2022). Crude oil time series prediction model based on LSTM network with chaotic Henry gas solubility optimization. Energy, 242, 122964. https://doi.org/10.1016/j.energy.2021.122964
Bildirici, M., Bayazit, N. G., & Ucan, Y. (2020). Analyzing crude oil prices under the impact of COVID-19 by using LSTARGARCHLSTM. Energies, 13, 1–18. https://doi.org/10.3390/en13112980
Box, G. E. P., & Jenkins, G. M. (1970). Time series analysis: Forecasting and control. San Francisco, CA: Holden-Day.
Bristone, M., Prasad, R., & Abubakar, A. A. (2020). CPPCNDL: Crude oil price prediction using complex network and deep learning algorithms. Petroleum, 6, 353–361. https://doi.org/10.1016/j.petlm.2019.11.009
Cen, Z., & Wang, J. (2019). Crude oil price prediction model with long short term memory deep learning based on prior knowledge data transfer. Energy, 169, 160–171. https://doi.org/10.1016/j.energy.2018.12.016
Chen, Y., He, K., & Tso, G. K. F. (2017). Forecasting Crude Oil Prices: A Deep Learning based Model. Procedia Computer Science, 122, 300–307. https://doi.org/10.1016/j.procs.2017.11.373
Daneshvar, A., Ebrahimi, M., Salahi, F., Rahmaty, M., & Homayounfar, M. (2022). Brent Crude Oil Price Forecast Utilizing Deep Neural Network Architectures. Computational Intelligence and Neuroscience, 2022, 6140796. https://doi.org/10.1155/2022/6140796
Firouzjaee, J. T., & Khaliliyan, P. (2022). Considering interpretability of the LSTM Architecture for Oil Stocks Prices Prediction (Statistical Finance). http://arxiv.org/abs/2201.00350
Guo, J. (2019). Oil price forecast using deep learning and ARIMA. 2019 International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI), 241–247. https://doi.org/10.1109/MLBDBI48998.2019.00054
Heravi, M. M. L., Khorrampanah, M., & Houshmand, M. (2022). Forecasting Crude Oil Prices Using Improved Deep Belief Network (IDBN) and Long-Term Short-Term Memory Network (LSTM). 30th International Conference on Electrical Engineering (ICEE), 823–826. https://doi.org/10.1109/ICEE55646.2022.9827452
Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9, 1735–1780. https://doi.org/doi:10.1162/neco.1997.9.8.1735
Jiang, H., Hu, W., Xiao, L., & Dong, Y. (2022). A decomposition ensemble based deep learning approach for crude oil price forecasting. Resources Policy, 78, 102855. https://doi.org/10.1016/j.resourpol.2022.102855
Jiao, X., Song, Y., Kong, Y., & Tang, X. (2022). Volatility forecasting for crude oil based on text information and deep learning PSO-LSTM model. Journal of Forecasting, 41, 933–944. https://doi.org/10.1002/for.2839
Kim, J. M., Han, H. H., & Kim, S. (2022). Forecasting Crude Oil Prices with Major S&P 500 Stock Prices: Deep Learning, Gaussian Process, and Vine Copula. Axioms, 11, 375. https://doi.org/10.3390/axioms11080375
Li, X., Shang, W., & Wang, S. (2019). Text-based crude oil price forecasting: A deep learning approach. International Journal of Forecasting, 35, 1548–1560. https://doi.org/10.1016/j.ijforecast.2018.07.006
Makala, D., & Li, Z. (2019). Economic Forecasting With Deep Learning: Crude Oil. MATTER: International Journal of Science and Technology, 5(2), 213–228. https://doi.org/10.20319/mijst.2019.52.213228
Manowska, A., & Bluszcz, A. (2022). Forecasting Crude Oil Consumption in Poland Based on LSTM Recurrent Neural Network. Energies, 15, 4885. https://doi.org/10.3390/en15134885
Nasir, J., Aamir, M., Haq, Z. U., Khan, S., Amin, M. Y., & Naeem, M. (2023). A new approach for forecasting crude oil prices based on stochastic and deterministic influences of LMD Using ARIMA and LSTM Models. IEEE Access, 11, 14322–14339. https://doi.org/10.1109/ACCESS.2023.3243232
Niu, T., Wang, J., Lu, H., Yang, W., & Du, P. (2021). A Learning System Integrating Temporal Convolution and Deep Learning for Predictive Modeling of Crude Oil Price. IEEE Transactions on Industrial Informatics, 17(7), 4602–4612. https://doi.org/10.1109/TII.2020.3016594
Olah, C. (2015). Understanging LSTM Networks. GitHub Repository. http://colah.github.io/posts/2015-08-Understanding-LSTMs/
Remy, P. (2020). Conditional RNN for Keras. GitHub Repository. https://github.com/philipperemy/cond_rnn
Safi, S., Aliyu, S., Ibrahim, K. S., & Sanusi, O. I. (2022). Can Oil Price Predict Exchange Rate? Empirical Evidence from Deep Learning. International Journal of Energy Economics and Policy, 12(4), 482–493. https://doi.org/10.32479/ijeep.13200
Sajadi, S. M. A., Khodaee, P., Hajizadeh, E., Farhadi, S., Dastgoshade, S., & Du, B. (2022). Deep Learning-Based Methods for Forecasting Brent Crude Oil Return Considering COVID-19 Pandemic Effect. Energies, 15, 8124. https://doi.org/10.3390/en15218124
Salamai, A. A. (2023). Deep learning framework for predictive modeling of crude oil price for sustainable management in oil markets. Expert Systems with Applications, 211, 118658. https://doi.org/10.1016/j.eswa.2022.118658
Santoso, A., Wijaya, F. D., Setiawan, N. A., & Waluyo, J. (2022). Data Mining Algorithms for Operating Pressure Forecasting of Crude Oil Distribution Pipelines to Identify Potential Blockages. Machine Learning and Knowledge Extraction, 4, 700–714. https://doi.org/10.3390/make4030033
Yahoo Finance. (n.d.). Retrieved February 14, 2022, from https://finance.yahoo.com/
Yiğit, T., Aksoy, B., Ersoy, M., Şenol, R., & Salman, O. K. M. (2021). Petrol fiyatlarının zaman serileri ve LSTM modeli kullanılarak tahminlenmesi. Uluslararası Teknolojik Bilimler Dergisi, 13(1), 34–38.
Zhang, K., & Hong, M. (2022). Forecasting crude oil price using LSTM neural networks. Data Science in Finance and Economics, 2(3), 163–180. https://doi.org/10.3934/dsfe.2022008
Zhao, Y., Li, J., & Yu, L. (2017). A deep learning ensemble approach for crude oil price forecasting. Energy Economics, 66, 9–16. https://doi.org/10.1016/j.eneco.2017.05.023
Referanslar
Altan, A., & Karasu, S. (2022). Crude oil time series prediction model based on LSTM network with chaotic Henry gas solubility optimization. Energy, 242, 122964. https://doi.org/10.1016/j.energy.2021.122964
Bildirici, M., Bayazit, N. G., & Ucan, Y. (2020). Analyzing crude oil prices under the impact of COVID-19 by using LSTARGARCHLSTM. Energies, 13, 1–18. https://doi.org/10.3390/en13112980
Box, G. E. P., & Jenkins, G. M. (1970). Time series analysis: Forecasting and control. San Francisco, CA: Holden-Day.
Bristone, M., Prasad, R., & Abubakar, A. A. (2020). CPPCNDL: Crude oil price prediction using complex network and deep learning algorithms. Petroleum, 6, 353–361. https://doi.org/10.1016/j.petlm.2019.11.009
Cen, Z., & Wang, J. (2019). Crude oil price prediction model with long short term memory deep learning based on prior knowledge data transfer. Energy, 169, 160–171. https://doi.org/10.1016/j.energy.2018.12.016
Chen, Y., He, K., & Tso, G. K. F. (2017). Forecasting Crude Oil Prices: A Deep Learning based Model. Procedia Computer Science, 122, 300–307. https://doi.org/10.1016/j.procs.2017.11.373
Daneshvar, A., Ebrahimi, M., Salahi, F., Rahmaty, M., & Homayounfar, M. (2022). Brent Crude Oil Price Forecast Utilizing Deep Neural Network Architectures. Computational Intelligence and Neuroscience, 2022, 6140796. https://doi.org/10.1155/2022/6140796
Firouzjaee, J. T., & Khaliliyan, P. (2022). Considering interpretability of the LSTM Architecture for Oil Stocks Prices Prediction (Statistical Finance). http://arxiv.org/abs/2201.00350
Guo, J. (2019). Oil price forecast using deep learning and ARIMA. 2019 International Conference on Machine Learning, Big Data and Business Intelligence (MLBDBI), 241–247. https://doi.org/10.1109/MLBDBI48998.2019.00054
Heravi, M. M. L., Khorrampanah, M., & Houshmand, M. (2022). Forecasting Crude Oil Prices Using Improved Deep Belief Network (IDBN) and Long-Term Short-Term Memory Network (LSTM). 30th International Conference on Electrical Engineering (ICEE), 823–826. https://doi.org/10.1109/ICEE55646.2022.9827452
Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9, 1735–1780. https://doi.org/doi:10.1162/neco.1997.9.8.1735
Jiang, H., Hu, W., Xiao, L., & Dong, Y. (2022). A decomposition ensemble based deep learning approach for crude oil price forecasting. Resources Policy, 78, 102855. https://doi.org/10.1016/j.resourpol.2022.102855
Jiao, X., Song, Y., Kong, Y., & Tang, X. (2022). Volatility forecasting for crude oil based on text information and deep learning PSO-LSTM model. Journal of Forecasting, 41, 933–944. https://doi.org/10.1002/for.2839
Kim, J. M., Han, H. H., & Kim, S. (2022). Forecasting Crude Oil Prices with Major S&P 500 Stock Prices: Deep Learning, Gaussian Process, and Vine Copula. Axioms, 11, 375. https://doi.org/10.3390/axioms11080375
Li, X., Shang, W., & Wang, S. (2019). Text-based crude oil price forecasting: A deep learning approach. International Journal of Forecasting, 35, 1548–1560. https://doi.org/10.1016/j.ijforecast.2018.07.006
Makala, D., & Li, Z. (2019). Economic Forecasting With Deep Learning: Crude Oil. MATTER: International Journal of Science and Technology, 5(2), 213–228. https://doi.org/10.20319/mijst.2019.52.213228
Manowska, A., & Bluszcz, A. (2022). Forecasting Crude Oil Consumption in Poland Based on LSTM Recurrent Neural Network. Energies, 15, 4885. https://doi.org/10.3390/en15134885
Nasir, J., Aamir, M., Haq, Z. U., Khan, S., Amin, M. Y., & Naeem, M. (2023). A new approach for forecasting crude oil prices based on stochastic and deterministic influences of LMD Using ARIMA and LSTM Models. IEEE Access, 11, 14322–14339. https://doi.org/10.1109/ACCESS.2023.3243232
Niu, T., Wang, J., Lu, H., Yang, W., & Du, P. (2021). A Learning System Integrating Temporal Convolution and Deep Learning for Predictive Modeling of Crude Oil Price. IEEE Transactions on Industrial Informatics, 17(7), 4602–4612. https://doi.org/10.1109/TII.2020.3016594
Olah, C. (2015). Understanging LSTM Networks. GitHub Repository. http://colah.github.io/posts/2015-08-Understanding-LSTMs/
Remy, P. (2020). Conditional RNN for Keras. GitHub Repository. https://github.com/philipperemy/cond_rnn
Safi, S., Aliyu, S., Ibrahim, K. S., & Sanusi, O. I. (2022). Can Oil Price Predict Exchange Rate? Empirical Evidence from Deep Learning. International Journal of Energy Economics and Policy, 12(4), 482–493. https://doi.org/10.32479/ijeep.13200
Sajadi, S. M. A., Khodaee, P., Hajizadeh, E., Farhadi, S., Dastgoshade, S., & Du, B. (2022). Deep Learning-Based Methods for Forecasting Brent Crude Oil Return Considering COVID-19 Pandemic Effect. Energies, 15, 8124. https://doi.org/10.3390/en15218124
Salamai, A. A. (2023). Deep learning framework for predictive modeling of crude oil price for sustainable management in oil markets. Expert Systems with Applications, 211, 118658. https://doi.org/10.1016/j.eswa.2022.118658
Santoso, A., Wijaya, F. D., Setiawan, N. A., & Waluyo, J. (2022). Data Mining Algorithms for Operating Pressure Forecasting of Crude Oil Distribution Pipelines to Identify Potential Blockages. Machine Learning and Knowledge Extraction, 4, 700–714. https://doi.org/10.3390/make4030033
Yahoo Finance. (n.d.). Retrieved February 14, 2022, from https://finance.yahoo.com/
Yiğit, T., Aksoy, B., Ersoy, M., Şenol, R., & Salman, O. K. M. (2021). Petrol fiyatlarının zaman serileri ve LSTM modeli kullanılarak tahminlenmesi. Uluslararası Teknolojik Bilimler Dergisi, 13(1), 34–38.
Zhang, K., & Hong, M. (2022). Forecasting crude oil price using LSTM neural networks. Data Science in Finance and Economics, 2(3), 163–180. https://doi.org/10.3934/dsfe.2022008
Zhao, Y., Li, J., & Yu, L. (2017). A deep learning ensemble approach for crude oil price forecasting. Energy Economics, 66, 9–16. https://doi.org/10.1016/j.eneco.2017.05.023
