Performance Evaluation of ARIMA and ANN Models for Forecasting Oil Palm Production Trends
DOI:
https://doi.org/10.64570/agrivolution.v1i2.33Keywords:
ARIMA, Artificial Neural Network, Forecasting, Palm oil production, Time SeriesAbstract
This study compares the performance of the Autoregressive Integrated Moving Average (ARIMA) model and an Artificial Neural Network (ANN) in forecasting annual palm oil production in Kampar Regency, using a univariate time series covering the period from 2013 to 2024. The forecasting aim is to support regional agricultural planning and decision-making in one of Riau Province’s key oil palm-producing regions. The ARIMA model was developed using the Box–Jenkins approach, which involves stationarity testing, optimal model identification, parameter estimation, and residual diagnostics, including ACF/PACF, Shapiro–Wilk, Jarque–Bera, and Ljung–Box tests. A feedforward ANN with three lagged inputs, five hidden neurons, sigmoid activation, and backpropagation training was constructed for comparison. Model performance was evaluated using RMSE, MAPE, and R². The results indicate that the ARIMA (1,1,1) model yields more stable and reliable forecasts, with diagnostic tests confirming white noise residuals and no significant autocorrelation. Conversely, the ANN model produced higher errors and indications of overfitting, likely due to the limited number of observations and the sharp increase in production recorded in the final data year. While ANN captured a stronger upward trend, which may represent an optimistic scenario, ARIMA provided more conservative and statistically valid forecasts under constrained data conditions. Overall, the ARIMA(1,1,1) model proved more suitable for the short univariate palm oil production series, yielding lower forecasting errors (RMSE = 273.88; MAPE = 8.92%) than the ANN model (RMSE = 283.53; MAPE = 9.03%).
References
Akbar, M., Guterres, C., & Araújo, A. (2025). A Backpropagation-Based Artificial Neural Network Model for Predicting Pharmaceutical Demand. Jurnal Riset Ilmu Teknik, 3, 1-15. https://doi.org/10.59976/jurit.v3i1.155
Ali, A., Raheem, A., & Khidir, K. (2020). Daily Streamflow Prediction for Khazir River Basin Using ARIMA and ANN Models. ZANCO JOURNAL OF PURE AND APPLIED SCIENCES, 32, 30-39. https://doi.org/10.21271/ZJPAS.32.3.4
Aser, D. A., & Firuzan, E. (2022). Impact of Structural Break Location on Forecasting Accuracy: Traditional Methods Versus Artificial Neural Network. Turkish Journal of Forecasting, 6(2), 83-96.
BPS. (2025). Provinsi Riau dalam Angka. Badan Pusat Statistik.
Dawson, C. (2018). Applied Artificial Neural Networks. Mdpi AG. https://books.google.co.id/books?id=bKpwDwAAQBAJ
Harahap, I. Y., & Lubis, M. E. S. (2018). Aplication of An Artificial Neural Network (ANN) Model for Prediction Oil Palm Fres Fruit Bunch (FFB) Yield Based on Rainfall and the Yield Previously. Jurnal Penelitian Kelapa Sawit, 26(2), 59-70.
Hermantoro. (2009). Pemodelan dan Simulasi Produktivitas Perkebunan Kelapa Sawit Berdasarkan Kualitas Lahan dan Iklim Menggunakan Jaringan Syaraf Tiruan. Jurnal Agromet, 23(1), 45-51.
Hermantoro, & Rudyanto. (2018). Modeling and Simulation of Oil Palm Plantation Productivity Based on Land Quality and Climate Using Artificial Neural Network. International Journal of Oil Palm, 1(2), 65-70.
Ismanto, E., Effendi, N., & Cynthia, E. P. (2018). Implementation of Backpropagation Artificial Neural Networks to Predict Palm Oil Price Fresh Fruit Bunches. International Journal of Information System and Technology, 2(1), 26-34.
Izudin, N. E. M., Sokkalingam, R., Daud, H., Mardesci, H., & Husin, A. (2021, 2021//). Forecasting Electricity Consumption in Malaysia by Hybrid ARIMA-ANN. Proceedings of the 6th International Conference on Fundamental and Applied Sciences, Singapore.
Khashei, M., & Bijari, M. (2011). A novel hybridization of artificial neural networks and ARIMA models for time series forecasting. Appl. Soft Comput., 11, 2664-2675.
Mardesci, H., Maryam, & Ihwan, K. (2023). Forecasting Coconut Production in Indragiri Hilir with Autoregressive Moving Average Model. SISTEMASI: Jurnal Sistem Informasi, 12(1), 219-228.
Micheal, V. A., & Bolarinwa, I. A. (2025). An Investigation of the Impact of Series Length on Forecast Behavioe Using Artificial Neural Networks. International Journal of Science Research and Technology.
Nikopoulus, K. (2010). Forecasting with Quantitative Methods the Impact of Special Events in Time Series. Applied Economics, 42(8), 947-955.
Putra, A. P., & Harahap, A. M. (2025). Implementasi Time Series Forecasting dengan Algoritma LSTM untuk Pemantauan dan Prediksi Produktivitas Kelapa Sawit Berdasarkan Hasil Panen. JURIKOM (Jurnal Riset Komputer).
Rahma, A. S., & Dahda, S. S. (2024). Comparison of ARIMA and Linear Trend Forecasting Models for Product X at PT ABC. G-Tech: Jurnal Teknologi Terapan, 8(2), 909-920.
Rakhmawati, D., Fajarwati, S., Astuti, T., & Arsi, P. (2022). Model ARIMA-GARCH pada Data Kurs JISDOR Selama Masa Pandemi COVID-19. Vygotsky: Jurnal Pendidikan Matematika dan Matematika, 4(2), 129-188.
Syarovy, M., Nugroho, A. P., Sutiarso, L., Suwardi, Muna, M. S., Wiratmoko, A., Sukarman, & Primananda, S. (2022, 2022/12/28). Utilization of Big Data in Oil Palm Plantation to Predict Production Using Artificial Neural Network Model. Proceedings of the International Conference on Sustainable Environment, Agriculture and Tourism (ICOSEAT 2022),
Velasco, L. C. P., Polestico, D. L. L., Macasieb, G. P. O., Reyes, M. B. V., & Jr, F. B. V. (2019). A Hybris Model of Autoregressive Integrated Movin Average and Artificial Neural Network for Load Forecasting. International Journal of Advance Computer Science and Application, 10(11), 14-22.
Wahyudi, S. T. (2017). The ARIMA model for the Indonesia stock price. International Journal of Economics and Management, 11, 223-236.
