Performance Evaluation of ARIMA and GRU Models for Forecasting Chili Price in East Jawa

Windi Pangesti; Nabila Syukri; Khairil Anwar Notodiputro; Yenni Angraini; Laily Nissa Atul Mualifah

doi:10.30595/juita.v13i2.26445

Authors

Windi Pangesti IPB University
Nabila Syukri IPB University
Khairil Anwar Notodiputro IPB University
Yenni Angraini IPB University
Laily Nissa Atul Mualifah IPB University

DOI:

https://doi.org/10.30595/juita.v13i2.26445

Keywords:

ARIMA, GRU, Time Series, Chili Price

Abstract

Time series forecasting plays a crucial role in predicting future conditions based on historical data, particularly in the food sector, which is highly susceptible to price fluctuations. This study compares two approaches: the conventional ARIMA method and the deep learning method GRU, to forecast the price of red chillies in East Java. East Java was chosen because it is the largest national producer of chilies, thus the stability of its prices has a broad impact. The research results indicate that the GRU model outperforms the ARIMA model with a MAPE value of 19.80% compared to a MAPE of 27.63% for the latter. The benefit of this research is to contribute to the literature on developing agricultural commodity price forecasting models as a basis for enhancing food security policies and stabilizing commodity prices, particularly in East Java Province, Indonesia

References

[1] G. Ghaly Ghiffary, E. Dicky Darmawan Yanuari, K. Anwar Notodiputro, Y. Angraini, and L. Nissa Atul Mualifah, “COMPARATIVE PERFORMANCE OF SARIMAX AND LSTM MODEL IN PREDICTING IMPORT QUANTITIES OF MILK, BUTTER, AND EGGS "COMPARATIVE PERFORMANCE OF SARIMAX AND LSTM MODEL IN PREDICTING IMPORT QUANTITIES OF MILK COMPARATIVE PERFORMANCE OF SARIMAX AND LSTM MODEL IN PREDICTING…,” BAREKENG: J. Math. & App, vol. 19, no. 1, pp. 407–0418, 2025, doi: 10.30598/barekengvol19iss1pp0407-0418.

[2] K. A. Notodiputro, Y. Angraini, and L. N. A. Mualifah, Analisis Data Deret Waktu dengan Python . Bogor: IPB Press, 2025.

[3] T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning, 2nd ed. New York, 2009.

[4] D. Peter and P. Silvia, “ARIMA vs ARIMAX-which approach is better to analyze and forecast macroeconomic time series?,” in Proceedings of 3oth International Conference Mathematical Methods in Economic, Sep. 2012, pp. 136–140.

[5] W. A. Pratiwi, A. F. Rizki, K. A. Notodiputro, Y. Angraini, and L. N. Mualifah, “THE COMPARISON OF ARIMA AND RNN FOR FORECASTING GOLD FUTURES CLOSING PRICES,” BAREKENG: J. Math. & App, vol. 19, no. 1, pp. 397–0406, 2025, doi: 10.30598/barekengvol19iss1pp0397-0406.

[6] X. Li, X. Ma, F. Xiao, C. Xiao, F. Wang, and S. Zhang, “Time-series production forecasting method based on the integration of Bidirectional Gated Recurrent Unit (Bi-GRU) network and Sparrow Search Algorithm (SSA),” J Pet Sci Eng, vol. 208, no. A, pp. 1–13, Jan. 2022, doi: 10.1016/j.petrol.2021.109309.

[7] P. L. Seabe, C. R. B. Moutsinga, and E. Pindza, “Forecasting Cryptocurrency Prices Using LSTM, GRU, and Bi-Directional LSTM: A Deep Learning Approach,” Fractal and Fractional, vol. 7, no. 2, Feb. 2023, doi: 10.3390/fractalfract7020203.

[8] Z. Shen, Y. Zhang, J. Lu, J. Xu, and G. Xiao, “A novel time series forecasting model with deep learning,” Neurocomputing, vol. 396, pp. 302–313, Jul. 2020, doi: https://doi.org/10.1016/j.neucom.2018.12.084.

[9] A. P. Meriani and A. Rahmatulloh, “PERBANDINGAN GATED RECURRENT UNIT (GRU) DAN ALGORITMA LONG SHORT TERM MEMORY (LSTM) LINEAR REGRESSION DALAM PREDIKSI HARGA EMAS MENGGUNAKAN MODEL TIME SERIES,” Jurnal Informatika dan Teknik Elektro Terapan, vol. 12, no. 1, Jan. 2024, doi: 10.23960/jitet.v12i1.3808.

[10] P. T. Yamak, L. Yujian, and P. K. Gadosey, “A Comparison between ARIMA, LSTM, and GRU for Time Series Forecasting,” in ACAI ’19: Proceedings of the 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence, Feb. 2020, pp. 49–55. doi: https://doi.org/10.1145/3377713.3377722.

[11] M. Ridwan, K. Sadik, and M. Afendi, “Comparison of ARIMA and GRU Models for High-Frequency Time Series Forecasting,” Scientific Journal of Informatics, vol. 10, no. 3, p. 389, 2023, doi: 10.15294/sji.v10i3.45965.

[12] I. W. R. Pinastawa, M. G. Pradana, D. S. Setiawan, and A. Izzety, “Comparison of ARIMA and GRU Methods in Predicting Cryptocurrency Price Movements,” sinkron, vol. 9, no. 1, pp. 96–105, Jan. 2025, doi: 10.33395/sinkron.v9i1.14235.

[13] A. M. Windhy and A. Syariful Jamil, “Peramalan Harga Cabai Merah Indonesia: Pendekatan ARIMA Forecasting Indonesian Red Chilli Prices: The ARIMA Approach,” 2021.

[14] R. Akademi, M. Cirebon, A. Badan, and P. Statistik, “PENGARUH HARGA CABAI TERHADAP TINGKAT INFLASI DI INDONESIA TAHUN 2016,” 2017.

[15] Kementerian Pertanian, ANALISIS KINERJA PERDAGANGAN CABAI MERAH Pusat Data dan Sistem Informasi Pertanian Sekretariat Jenderal Kementerian Pertanian 2024, vol. 14. Pusat Data dan Sistem Informasi Pertanian, 2024.

[16] J. D. Cryer and K.-S. Chan, Time Series Analysis, 2nd ed. Springer, 2008.

[17] W. W. S. Wei, Time Series Analysis: Univariate and Multivariate Methods, 2nd ed. New York: Greg Tobin, 2006.

[18] Siswanto, J. Sembiring, I. Setiawan, and A. Setyawan, “Number of Cyber Attacks Predicted With Deep Learning Based LSTM Model,” 2024.