Comparative Study of Hybrid ARIMA-LSTM and CNN-LSTM for Palm Oil Price Forecasting

Rizki Alifah Putri, Khairil Anwar Notodiputro, Budi Susetyo

Abstract


The forecasting of highly volatile time series data remains a significant challenge due to complex, non-linear patterns. This study compared the performance of two hybrid frameworks, ARIMA-LSTM and CNN-LSTM, which were designed to integrate the statistical strengths of traditional models with the computational power of deep learning. In these architectures, the ARIMA component was utilized to extract linear trends, while the LSTM and CNN layers were employed to identify and manage non-linear dynamics within the data. Utilizing 384 monthly palm oil price data points (1993-2024) sourced from FRED, the models were evaluated using the Mean Absolute Percentage Error (MAPE) metric. The results demonstrated that the hybrid CNN-LSTM outperformed the ARIMA-LSTM and individual models, achieving a superior MAPE of 6.69%. These findings indicated that the integration of Convolutional Neural Networks (CNN) with Long Short-Term Memory (LSTM) networks was more effective in capturing the complexities of price fluctuations. Practically, the study concluded that accurate forecasting served as a critical tool for market stabilization, thereby supporting broader goals of financial certainty and ecological sustainability.

Keywords


ARIMA; CNN-LSTM; Crude Palm Oil; Deep Learning; Hybrid Models; Time Series Forecasting.

Full Text:

PDF

References


D. C. Montgomery, C. L. Jennings, and M. Kulahci, Introduction to Time Series Analysis and Forecasting, 2nd ed. Hoboken, NJ: Wiley, 2015.

K. He, L. Ji, C. W. D. Wu, and K. F. G. Tso, “Using SARIMA–CNN–LSTM approach to forecast daily tourism demand,” J. Hosp. Tour. Manag., vol. 49, no. October 2020, pp. 25–33, 2021, doi: 10.1016/j.jhtm.2021.08.022.

R. Fazira, D. Yudistira, and L. Sofinah Harahap, “Evaluasi Kinerja Model RNN & LSTM untuk Prediksi Magnitude Gempa di Indonesia,” Mars J. Tek. Mesin, Ind. Elektro Dan Ilmu Komput., vol. 2, no. 6, pp. 62–75, 2024, doi: 10.61132/mars.v2i6.498.

S. Sen, D. Sugiarto, and A. Rochman, “Komparasi Metode Multilayer Perceptron (MLP) dan Long Short Term Memory (LSTM) dalam Peramalan Harga Beras,” Ultim. J. Tek. Inform., vol. 12, no. 1, pp. 35–41, 2020, [Online]. Available: https://ejournals.umn.ac.id/index.php/TI/article/view/1572/954

C. Alkahfi, A. Kurnia, and A. Saefuddin, “Perbandingan Kinerja Model Berbasis RNN pada Peramalan Data Ekonomi dan Keuangan Indonesia,” MALCOM Indones. J. Mach. Learn. Comput. Sci., vol. 4, no.4, no. October, pp. 1235–1243, 2024.

Y. A. Nugroho and H. A. Hutahaean, “Pengembangan Model Deep Learning LSTM dan CNN untuk Peramalan Penjualan Sepeda Motor di Indonesia,” Jupiter Publ. Ilmu Keteknikan Ind. Tek. Elektro dan Inform., vol. 3, no. 2, pp. 94–104, 2025, doi: 10.61132/jupiter.v3i2.795.

M. Qaim, K. T.Sibhatu, H. Siregar, and I. Grass, “Environmental , Economic , and Social Consequences of the Oil Palm Boom,” Annu. Rev. Resourse Econ., vol. 12, no. 1, pp. 321–344, 2020, doi: 10.1146/annurev-resource-110119-024922.

G. P. Zhang, “Time series forecasting using a hybrid ARIMA and neural network model,” Neurocomputing, vol. 50, pp. 159–175, doi: 10.1016/S0925-2312(01)00702-0.

W. Lu, J. Li, Y. Li, A. Sun, and J. Wang, “A CNN-LSTM-based model to forecast stock prices,” Complexity, vol. 2020, p. 6622927, 2020, doi: 10.1155/2020/6622927.

M. Iaousse, Y. Jouilil, M. Bouincha, and D. Mentagui, “A Comparative Simulation Study of Classical and Machine Learning Techniques for Forecasting Time Series Data,” Int. J. Online Biomed. Eng., vol. 19, no. 8, pp. 56–65, 2023, doi: 10.3991/ijoe.v19i08.39853.

E. K. M. Uskono, “Aplikasi Metode ARIMA, LSTM, dan Hybrid ARIMA-LSTM pada Peramalan Harga Crude Palm Oil (CPO) Dunia,” Institut Pertanian Bogor, 2023.

J. D. Cryer and K.-S. Chan, Time Series Analysis with Application in R, 2nd ed. New York: Springer New York, 2008.

X. Li, D. Li, Y. Cheng, and W. Li, “Forecasting the Volatility of Educational Firms Based on HAR Model and LSTM Models Considering Sentiment and Educational Policy,” Heliyon, vol. 10, no. 19, 2024, doi: https://doi.org/10.1016/j.heliyon.2024.e38560.

A. Agga, S. A. Abbou, Y. El Houm, and M. Labbadi, “Short-Term Load Forecasting Based on CNN and LSTM Deep Neural Networks,” IFAC-PapersOnLine, vol. 55, no. 12, pp. 777–781, 2022, doi: 10.1016/j.ifacol.2022.07.407.

H. Abbasimehr, M. Shabani, and M. Yousefi, “An optimized model using LSTM network for demand forecasting,” Comput. Ind. Eng., vol. 143, no. July 2019, p. 106435, 2020, doi: 10.1016/j.cie.2020.106435.

A. Z. A. Ra, “COMPARISON OF DYNAMIC FACTOR MODELS (DFM) AND LONG SHORT-TERM MEMORY (LSTM) NETWORKS IN FORECASTING HOUSEHOLD CONSUMPTION,” Institut Pertanian Bogor, 2022.

B. Zhao, H. Lu, S. Chen, J. Liu, and D. Wu, “Convolutional neural networks for time series classification,” J. Syst. Eng. Electron., vol. 28, no. 1, pp. 162–169, 2017, doi: 10.21629/JSEE.2017.01.18.

M. Lenderink, “Accounts Receivable Cash Flow Forecasting: A comparison between SES, ARIMA, LSTM and Hybrid ARIMA-LSTM,” Tilburg University, 2022.

Y. Widhiyasana, T. Semiawan, I. G. A. Mudzakir, and M. R. Noor, “Penerapan Convolutional Long Short-Term Memory untuk Klasifikasi Teks Berita Bahasa Indonesia,” J. Nas. Tek. Elektro dan Teknol. Inf., vol. 10, no. 4, pp. 354–361, 2021, doi: 10.22146/jnteti.v10i4.2438.

J. Nathaniel and V. J. L. Engel, “Penerapan Nonpooling CNN-LSTM Untuk Prediksi Pemakaian Obat Rumah Sakit,” Institut Teknologi Harapan Bangsa, 2022. [Online]. Available: https://repository.ithb.ac.id/id/eprint/30/9/1117012_Paper-TA.pdf

D. Al Mahkya, K. A. Notodiputro, and B. Sartono, “Extra Trees Method for Stock Price Forecasting With Rolling Origin Accuracy Evaluation,” Media Stat., vol. 15, no. 1, pp. 36–47, 2022, doi: 10.14710/medstat.15.1.36-47.

F. Bresciani, G. Feder, D. O. Gilligan, H. G. Jacoby, T. Onchan, and J. Quizon, “Weathering the Storm : The Impact of the East Asian Crisis on Farm Households in Indonesia and Thailand,”World Bank Res. Obs., vol. 17, no. 1, pp. 1–20, 2002.

D. Mitchell, “A Note on Rising Food Prices,” Washington, D.C, 2008.

J. Baffes and T. Haniotis, “Placing the 2006 / 08 Commodity Price Boom into Perspective,” Washington, D.C, 2010.

World Bank, “Commodity Markets Outlook: The Impact of the War in Ukraine on Commodity Markets,” Washington, D.C, 2022.

J. Glauber, D. Labor, and A. Mamun, “Food export restrictions have eased as the Russia-Ukraine war continues, but concerns remain for key commodities,” IFPRI Blog. [Online]. Available: https://www.ifpri.org/blog/food-export-restrictions-have-eased-russia-ukraine-war-continues-concerns-remain-key/

S. G. C. Insights, “Global Biofuels Special Report: 5 issues to watch in 2025 and what you can expect,” New York, NY (Markas besar S&P Global), 2025.

K. A. Notodiputro and Y. Anggraini, R, Data dan Statistik Deskriptif. Bogor: IPB Publisher, 2023.

E. Arif, E. Herlinawati, D. Devianto, M. Yollanda, and D. Permana, “Hybridization of long short-term memory neural network in fractional time series modeling of inflation,” Front. Big Data, vol. 6, 2024, doi: 10.3389/fdata.2023.1282541.




DOI: http://dx.doi.org/10.30829/zero.v10i1.27631

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Publisher :
Department of Mathematics
Faculty of Science and Technology
Universitas Islam Negeri Sumatera Utara Medan
✉Email: zero_journal@uinsu.ac.id
☎WhatsApp: 085270009767 (Admin Official)
SINTA 2 Google Scholar CrossRef Garuda DOAJ