Optimizing Forecasting for Indonesia's Coal and Palm Oil Exports: A Comparative Analysis of ARIMA, ANN, and LSTM Methods

Authors: Mochammad Dewo, Sumarsono Sudarto

Abstract:

The Exponential Triple Smoothing Algorithm approach nowadays, which is used to anticipate the export value of Indonesia's two major commodities, coal and palm oil, has a Mean Percentage Absolute Error (MAPE) value of 30-50%, which may be considered as a "reasonable" forecasting mistake. Forecasting errors of more than 30% shall have a domino effect on industrial output, as extra production adds to raw material, manufacturing and storage expenses. Whereas, reaching an "excellent" classification with an error value of less than 10% will provide new investors and exporters with confidence in the commercial development of related sectors. Industrial growth will bring out a positive impact on economic development. It can be applied for other commodities if the forecast error is less than 10%. The purpose of this project is to create a forecasting technique that can produce precise forecasting results with an error of less than 10%. This research analyzes forecasting methods such as ARIMA (Autoregressive Integrated Moving Average), ANN (Artificial Neural Network) and LSTM (Long-Short Term Memory). By providing a MAPE of 1%, this study reveals that ANN is the most successful strategy for forecasting coal and palm oil commodities in Indonesia.

Keywords: ANN, Artificial Neural Network, ARIMA, Autoregressive Integrated Moving Average, export value, forecast, LSTM, Long Short Term Memory.

References:

[1] ITC (2023b). Trade Statistics for International Business Development. Trade Map - List of importers for the selected product in 2022 (Coal; briquettes, ovoids and similar solid fuels manufactured from coal). https://www.trademap.org/Country_SelProduct.aspx?nvpm=1%7C%7C%7C%7C%7C270120%7C%7C%7C6%7C1%7C1%7C1%7C1%7C1%7C2%7C1%7C1%7C1
[2] ITC (2023a). Trade Statistics for International Business Development. Trade Map - List of exporters for the selected product (Palm oil and its fractions, whether or not refined (excl. chemically modified)). https://www.trademap.org/Country_SelProduct_TS.aspx?nvpm=1%7C%7C42%7C%7C%7C1511%7C%7C%7C4%7C1%7C1%7C2%7C2%7C1%7C3%7C1%7C1%7C1
[3] Badan Pusat Statistik. (2017-2021). Statistik Perdagangan Luar Negeri Indonesia Ekspor (2017-2021), Jilid I. Badan Pusat Statistik. https://www.bps.go.id/publication/2022/07/06/d3580f9e1b55a44b265d5ad8/statistik-perdagangan-luar-negeri-indonesia-ekspor-2021-jilid-i.html
[4] Lewis, C. D. (1982). Industrial and business forecasting methods: A practical guide to exponential smoothing and curve fitting. Butterworth Scientific.
[5] Yee, K. W., & Samsudin, H. B. (2021). Comparison between Artificial Neural Network and ARIMA Model in Forecasting Palm Oil Price in Malaysia. International Journal of Scientific Engineering and Science, 5(11), 12–15.
[6] Pandey, A. K., Sahay, K. B., Tripathi, M. M., Chandra, D. (2014). Short-term load forecasting of UPPCL using ANN.
[7] Manowska, A., & Bluszcz, A. (2022). Forecasting crude oil consumption in Poland based on LSTM recurrent neural network. Energies, 15(13), 4885. https://doi.org/10.3390/en15134885
[8] G.E.P. Box, G. Jenkins, “Time Series Analysis, Forecasting and Control”, Holden-Day,San Francisco, CA, 1970.
[9] Jain, G., & Mallick, B. (2017). A study of time series models Arima and ETS. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.2898968
[10] da Silva, I. N., Spatti, D. H., Flauzino, R. A., Liboni, L. H. B., & Reis Alves, S. F. dos. (2017). Artificial Neuron. In Artificial Neural Network A Practical Course (pp. 11–13). essay, Springer International Publishing Switzerland.
[11] Huang, B., Tong, L., & Zuo, Y. (2022). Short-term Power Generation Load Forecasting based on LSTM Neural Network. Journal of Physics: Conference Series, 2247(1), 012033. https://doi.org/10.1088/1742-6596/2247/1/012033
[12] Liu, Yamei, "Overfitting and forecasting: linear versus non-linear time series models " (2000). Retrospective Theses and Dissertations. 13915. https://lib.dr.iastate.edu/rtd/13915
[13] Heizer, J., & Render, B. (2009). Operations management (9th ed.). Pearson Prentice Hall.
[14] Urrutia, J. D., Abdul, A. M., & Atienza, J. B. (2019). Forecasting Philippines imports and exports using Bayesian Artificial Neural Network and autoregressive integrated moving average. AIP Conference Proceedings. https://doi.org/10.1063/1.5139185
[15] Rahim, N. F., Othman, M., & Sokkalingam, R. (2018). A comparative review on various method of forecasting crude palm oil prices. Journal of Physics: Conference Series, 1123, 012043. https://doi.org/10.1088/1742-6596/1123/1/012043
[16] Liu, X. (2021). Research on the forecast of coal price based on LSTM with improved Adam Optimizer. Journal of Physics: Conference Series, 1941(1), 012069. https://doi.org/10.1088/1742-6596/1941/1/012069
[17] Khalid, N., Hamidi, H. N. A., Thinagar, S., & Marwan, N. F. (2018). Crude palm oil price forecasting in Malaysia: An econometric approach. Jurnal Ekonomi Malaysia, 52(3). https://doi.org/10.17576/jem-2018-5203-19.