Synergizing ARDL and LSTM methods for enhanced crude palm oil price forecasting in Malaysia
Abstract
Understanding the volatile nature of palm oil prices is essential due to its profound economic and market implications. The complexity of forecasting palm oil prices stems from the interplay of various demand and supply forces, making it challenging for scholars to pinpoint the key determinants. This study addresses the intricate challenges in the palm oil industry, including price volatility, shifting consumer preferences, and environmental sustainability, by analysing the factors influencing Malaysian Crude Palm Oil (CPO) pricing dynamics. Utilising data from the Malaysian Palm Oil Board, covering the period from January 2004 to December 2021, we examined the impact of these variables on CPO prices. Methodologically, we employed Autoregressive Distributed Lag (ARDL) and Long Short-Term Memory (LSTM) models to evaluate and forecast CPO prices. Our findings indicate that the LSTM method outperformed the ARDL method in terms of forecasting accuracy. Specifically, the LSTM model showed superior performance when using a selection of ten independent variables identified through LASSO and SHAP estimation, compared to using eleven or four variables based on ARDL regression results. The analysis underscores the significant influence of weather conditions and macroeconomic factors, particularly tax rates, on CPO prices. These findings contribute to a deeper understanding of market dynamics and enhance the accuracy of CPO price forecasting.
References
Althaea, K. A., El-Alfy, E. S. M., & Mohammed, S. (2018). Stock market forecast using multivariate analysis with bidirectional and stacked (LSTM, GRU). In 2018 21st Saudi Computer Society National Computer Conference (NCC) (pp. 1-7). IEEE. https://doi.org/10.1109/NCG.2018.8593076
Amin, S. I. M., Shukor, M. S., & Abdul-Rahman, A. (2024). Determinants of Malaysian palm oil export efficiency: A gravity stochastic frontier model. Geografia-Malaysian Journal of Society and Space, 20(2), 145-155.
Banerjee, A., Dolado, J., Galbraith, J. W., & Hendry, D. (1993). Cointegration, error correction, and the econometric analysis of non-stationary data. Oxford University Press. https://books.google.com.my/books?hl=en&lr=&id=LfVQEAAAQBAJ&oi=fnd&pg=PR7&dq=Banerjee,+A.,+Dolado,+J.,+Galbraith,+J.+W.,+%26+Hendry,+D.+(1993).+Cointegration,+error+correction,+and+the+econometric+analysis+of+non-stationary+data.+Oxford+University+Press&ots=-8SvWMGiUY&sig=twi7s6vceseLKcUE1oByDQ7ipPE
Castle, J. L., Doornik, J. A., & Hendry, D. F. (2021). Selecting a model for forecasting. Econometrics, 9(3), 26. https://doi.org/10.3390/econometrics9030026
Cespedes, L. F., & Velasco, A. (2012). Assessing the impact of food trade policies on poverty alleviation and welfare. Journal of Policy Modelling, 34(6), 879-894. https://doi.org/10.1057/imfer.2012.22
Chandrarin, G., Sohag, K., Cahyaningsih, D. S., Yuniawan, D., & Herdhayinta, H. (2022). The response of exchange rate to coal price, palm oil price, and inflation in Indonesia: Tail dependence analysis. Resources Policy, 77, 102750. https://doi.org/10.1016/j.resourpol.2022.102750
Enghiad, A., Ufer, D., Countryman, A., & Thilmany, D. (2017). An Overview of Global Wheat Market Fundamentals in an Era of Climate Concerns. International Journal of Agronomy, 2017(1), 3931897.. https://doi.org/10.1155/2017/3931897.
Hamid, M. F. A., & Shabri, A. (2017). Palm oil price forecasting model: An autoregressive distributed lag (ARDL) approach. AIP Conference Proceedings, 1842(1). https://doi.org/10.1063/1.4982864.
Hassan, A., & Balu, N. (2016). Examining the long-term relationships between the prices of palm oil and soybean oil, palm oil production and export: Cointegration and causality. Oil Palm Industry Economic Journal, 16(1), 31-37. https://www.researchgate.net/publication/324983472
Headey, D., & Fan, S. (2008). Anatomy of a crisis: The causes and consequences of surging food prices. Agricultural Economics, 39(1), 375-391. https://doi.org/10.1111/J.1574-0862.2008.00345.X.
Hisham, A. A. M., Karim, Z. A., & Khalid, N. (2019). Determinants of capital expenditure spending in Malaysian palm oil industries: A dynamic panel data analysis. Economic Journal of Emerging Markets, 223-233. https://doi.org/10.20885/ejem.vol11.iss2.art9.
Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735-1780. https://doi:10.1162/neco.1997.9.8.1735
Karia, A., Bujang, I., & Ahmad, I. (2013). Forecasting on Crude Palm Oil Prices Using Artificial Intelligence Approaches. American Journal of Operations Research, 3(2), 259-267. https://doi.org/10.4236/AJOR.2013.32023.
Karim, F., Majumdar, S., Darabi, H., & Harford, S. (2019). Multivariate LSTM-FCNs for time series classification. Neural networks, 116, 237-245. https://arxiv.org/pdf/1801.04503
Lu, Q., Sun, S., Duan, H., & Wang, S. (2021). Analysis and forecasting of crude oil price based on the variable selection-LSTM integrated model. Energy Informatics, 4(1), 1-20. https://doi.org/10.1186/s42162-021-00166-4
Ma, Q., Huang, J., Başar, T., Liu, J., & Chen, X. (2021). Reputation and Pricing Dynamics in Online Markets. IEEE/ACM Transactions on Networking, 29(4), 1745-1759. https://doi.org/10.1109/TNET.2021.3071506.
Md Isa, M. A., Samsudin, S., & Noh, M. K. A. (2016). Co-integration and causality between the spot and futures markets: pre and post implementation of NKEAs. Advances in Business Research International Journal, 2(1), 1-13.
Murphy, D.J., Goggin, K. & Paterson, R.R.M. (2021) Oil palm in the 2020s and beyond: challenges and solutions. CABI agriculture and bioscience, 2, 1-22. https://doi.org/10.1186/s43170-021-00058-3
Netayarak, P. (2007). Agricultural Economics. Bangkok: Thammasat University.
Ofuoku, M., & Ngniatedema, T. (2022). Predicting the Price of Crude Palm Oil: A Deep Learning Approach. International Journal of Strategic Decision Sciences (IJSDS), 13(1), 1-15. https://www.igi-global.com/article/predicting-the-price-of-crude-palm-oil/305830
Oosterveer, P. (2015). Promoting sustainable palm oil: viewed from a global networks and flows perspective. Journal of Cleaner Production, 107, 146-153. https://doi.org/10.1016/J.JCLEPRO.2014.01.019.
Pashigian, B. P. (2008). Cobweb Theorem: The New Palgrave Dictionary of Economics. Springer. doi, 10, 978-1. https://books.google.com/books?hl=en&lr=&id=EO40DAAAQBAJ&oi=fnd&pg=PR2&dq=+%22Cobweb+Theorem%22.+The+New+Palgrave+Dictionary+of+Economics+(2nd+ed.)&ots=8m56JYBDlX&sig=7-xm8vvetDXl5pqFeoolI2_XzbI
Pesaran, M. H., & Shin, Y. (1995). An autoregressive distributed lag modelling approach to cointegration analysis (Vol. 9514, pp. 371-413). Cambridge, UK: Department of Applied Economics, University of Cambridge.
Pesaran, M. H., Shin, Y., & Smith, R. J. (2001). Bounds testing approaches to the analysis of level relationships. Journal of Applied Econometrics, 16(3), 289-326. https://doi.org/10.1002/jae.616
Peterson, P. (2014). Fixing Prices and Fixing Markets. farmdoc daily, 4. https://ageconsearch.umn.edu/record/283094/files/fdd250614.pdf
Putri, P. Y., Achsani, N. A., & Pranowo, K. (2019). The Effects of Macroeconomic Variables and Corporate Financial Performance on Stock Prices of Palm Oil Companies in Indonesia. Jurnal Manajemen & Agribisnis, 16(1), 12-12. /DOI: http://dx.doi.org/10.17358/jma.16.1.12
Ricci, E., Peri, M., & Baldi, L. (2019). The Effects of Agricultural Price Instability on Vertical Price Transmission: A Study of the Wheat Chain in Italy. Agriculture, 9(2), 36. https://doi.org/10.3390/AGRICULTURE9020036.
Sagheer, A., & Kotb, M. (2019). Unsupervised pre-training of a deep LSTM-based stacked autoencoder for multivariate time series forecasting problems. Scientific reports, 9(1), 19038. https://www.nature.com/articles/s41598-019-55320-6
Tibshirani, R. (1996). Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society Series B: Statistical Methodology, 58(1), 267-288. https://doi.org/10.1111/j.2517-6161.1996.tb02080.x
Tomek, W.G. & Robinson, K.L. 1981. Agricultural Product Prices. Ithaca, New York.: Cornell University Press. https://www.cabidigitallibrary.org/doi/full/10.5555/19811875109
Tomek, W. G., & Kaiser, H. M. (2014). Agricultural product prices. Cornell University Press.
Urolagin, S., Sharma, N., & Datta, T. K. (2021). A combined architecture of multivariate LSTM with Mahalanobis and Z-Score transformations for oil price forecasting. Energy, 231, 120963. https://www.sciencedirect.com/science/article/pii/S0360544221012111
Widiputra, H., Mailangkay, A., & Gautama, E. (2021). Multivariate cnn-lstm model for multiple parallel financial time-series prediction. Complexity, 2021 (1), 9903518. https://www.hindawi.com/journals/complexity/2021/9903518/
Wilson, N., & Cacho, J. (2007). Linkage between foreign direct investment, trade and trade policy: an economic analysis with application to the food sector in OECD countries and case studies in Ghana, Mozambique, Tunisia and Uganda. https://www.oecd-ilibrary.org/content/paper/152275474424
Zaidi, M. A. S., Karim, Z. A., & Zaidon, N. A. (2021). External and internal shocks and the movement of palm oil price: SVAR evidence from Malaysia. Economies, 10(1), 7. https://doi.org/10.3390/economies10010007
Zainalabidin, S. M., & Rahim, K. A. (2012). Impact of climate change on palm oil production. In Proceedings of USM-AUT International Conference 2012 Sustainable Economic Development: Policies and Strategies (Vol. 167, p. 109).
Zhang, K., Hong, M., Zhang, K., & Hong, M. (2022). Forecasting crude oil price using LSTM neural networks. Data Sci. Financ. Econ, 2, 163-180. https://doi.org/10.3934/dsfe.2022008.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Mohd Shahrin Bahar, Imbarine, Abdul Aziz , Nurzahidah Baharudin
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
