SARIMA-GARCH and LSTM Performance for Broiler Meat Price Forecasting: A Case Study in West Sumatra

Joshua Bryan  Wijaya; Indah Dzulkharifah; Varel Geo Syah  Putra; Harits  Abdurahman; Laily Nissa Atul  Mualifah; Windi  Pangesti

doi:10.59395/ijadis.v7i1.1497

Authors

Joshua Bryan Wijaya Study Program of Statistics and Data Science, Bogor Agricultural University, Indonesia
Indah Dzulkharifah Study Program of Statistics and Data Science, Bogor Agricultural University, Indonesia
Varel Geo Syah Putra Study Program of Statistics and Data Science, Bogor Agricultural University, Indonesia
Harits Abdurahman Study Program of Statistics and Data Science, Bogor Agricultural University, Indonesia
Laily Nissa Atul Mualifah Study Program of Statistics and Data Science, Bogor Agricultural University, Indonesia
Windi Pangesti Study Program of Statistics and Data Science, Bogor Agricultural University, Indonesia

DOI:

https://doi.org/10.59395/ijadis.v7i1.1497

Keywords:

SARIMA-GARCH , LSTM , Broiler Chicken Price , Deep learning Hybrid

Abstract

The price of broiler chicken meat in West Sumatra is characterized by strong seasonality and high volatility. As a primary source of animal protein and a key contributor to regional inflation, accurate forecasting of these price fluctuations is essential for economic stability and policymaking. This study aims to compare the forecasting performance of the SARIMA-GARCH hybrid model against the Long Short-Term Memory (LSTM) model. The dataset consists of 1,198 daily observations spanning from 15 July 2022 to 24 October 2025, sourced from the National Food Agency (Badan Pangan Nasional). The results demonstrate that the SARIMA-GARCH model outperforms the LSTM model in terms of point forecast accuracy, as evidenced by lower prediction error metrics. Furthermore, the hybrid model successfully satisfies the statistical diagnostic criteria for volatility modeling by effectively resolving ARCH effects, ensuring the statistical validity of the residuals. While the LSTM model produces smoother long-term forecasts, the SARIMA-GARCH model effectively captures daily price fluctuations and indicates a modest upward trend over the next 28 days. These findings suggest that SARIMA-GARCH provides a more realistic depiction of short-term price movements for this specific regional market, offering a localized framework for stakeholders in West Sumatra to anticipate future market changes and maintain price stability.

1079 644

Downloads

Download data is not yet available.

References

[1] R. J. Hyndman and G. Athanasopoulos, Forecasting: Principles and Practice, 3rd ed. Melbourne, Australia: Otexts, 2021. Accessed: Nov. 29, 2025. [Online]. Available: https://otexts.com/fpp3/

[2] T. Bunnag, “Forecasting PM10 Caused by Bangkok’s Leading Greenhouse Gas Emission Using the SARIMA and SARIMA-GARCH Model,” International Journal of Energy Economics and Policy, vol. 14, no. 1, pp. 418–426, Jan. 2024, doi: 10.32479/ijeep.15275. DOI: https://doi.org/10.32479/ijeep.15275

[3] S. Kamolthip, “Macroeconomic forecasting with LSTM and mixed frequency time series data,” Sep. 2021, [Online]. Available: http://arxiv.org/abs/2109.13777

[4] L. N. A. Mualifah, A. M. Soleh, and K. A. Notodiputro, “Comparison of GARCH, LSTM, and Hybrid GARCH-LSTM Models for Analyzing Data Volatility,” International Journal of Advances in Soft Computing and its Applications, vol. 16, no. 2, pp. 150–165, 2024, doi: 10.15849/IJASCA.240730.10. DOI: https://doi.org/10.15849/IJASCA.240730.10

[5] J. K. Mutinda and A. K. Langat, “Stock price prediction using combined GARCH-AI models,” Sci. Afr., vol. 26, Dec. 2024, doi: 10.1016/j.sciaf.2024.e02374. DOI: https://doi.org/10.1016/j.sciaf.2024.e02374

[6] L. Budianti, M. Yasyfi Avicenna, A. Kusuma Putri, and G. Darmawan, “Pemodelan SARIMA dengan Pendekatan ARCH/GARCH untuk Meramalkan Penjualan Ritel Barang Elektronik,” INNOVATIVE: Journal Of Social Science Research, vol. 4, pp. 1037–1051, 2024.

[7] T. Bollerslev, “The Story of GARCH: A Personal Odyssey,” 2022. DOI: https://doi.org/10.1016/j.jeconom.2023.01.015

[8] K. S. Sai, K. Suhasisni, and M. A. Baba, “Comparative Analysis of Hybrid SARIMA-GARCH and Neural Networks for Chilli Price Forecasting,” Indian Journal of Agricultural Economics, vol. 80, no. 2, pp. 370–385, 2025, doi: 10.63040/25827510.2025.02.007. DOI: https://doi.org/10.63040/25827510.2025.02.007

[9] M. Kalkuhi, J. von Braun, and M. Torero, MatthiassKalkuhll• JoachimmvonnBraun MaximooTorero Editors Food Price Volatility and Its Implications for Food Security and Policy. 2016. doi: DOI 10.1007/978-3-319-28201-5. DOI: https://doi.org/10.1007/978-3-319-28201-5

[10] P. Ghiyal and J. Kumar, “International Journal of Statistics and Applied Mathematics 2024; 9(2): 101-107 Use of hybrid SARIMA-GARCH model for predicting the prices of agricultural product in Haryana,” Maths, vol. 9, no. 2, pp. 101–107, 2024, [Online]. Available: https://www.mathsjournal.com

[11] H. Hasmon, F. Firmansyah, N. Idris, and F. Hoesni, “Volatilitas Harga Daging Ayam Broiler di Tingkat Pedagang Pengecer pada Berbagai Kabupaten/Kota di Provinsi Jambi,” Ekonomis: Journal of Economics and Business, vol. 8, no. 2, p. 1434, Sep. 2024, doi: 10.33087/ekonomis.v8i2.1824. DOI: https://doi.org/10.33087/ekonomis.v8i2.1824

[12] N. Niako, J. D. Melgarejo, G. E. Maestre, and K. P. Vatcheva, “Effects of missing data imputation methods on univariate blood pressure time series data analysis and forecasting with ARIMA and LSTM,” BMC Med. Res. Methodol., vol. 24, no. 1, Dec. 2024, doi: 10.1186/s12874-024-02448-3. DOI: https://doi.org/10.1186/s12874-024-02448-3

[13] G. E. P. Box, G. M. Jenkins, and G. C. Reinsel, Time Series Analysis-Forecasting and Control, 3rd ed. Upper Saddle River, New Jersey, USA: Prentice-Hall, Inc, 1994.

[14] K. A. Notodiputro, Y. Angraini, and L. N. A. Mualifah, Analisis Data Deret Waktu dengan Python Pendekatan Box-Jenkins dan Machine Learning, 1st ed. Bogor: PT Penerbit IPB Press, 2025.

[15] S. Wulandari and T. Wahyuningsih, “PERAMALAN JUMLAH TAMU THE AMRANI SYARIAH HOTEL MENGGUNAKAN MODEL ARIMA,” Majamath: Jurnal Matematika dan Pendidikan Matematika, vol. 7, Mar. 2024. DOI: https://doi.org/10.36815/majamath.v7i1.3145

[16] F. Merabet, H. Zeghdoudi, R. H. Yahia, and I. Saba, “MODELLING OF OIL PRICE VOLATILITY USING ARIMA-GARCH MODELS F. Merabet, H. Zeghdoudi, R. H Yahia, and I. Saba,” Advances in Mathematics: Scientific Journal, vol. 10, no. 5, pp. 2361–2380, May 2021, doi: 10.37418/amsj.10.5.6. DOI: https://doi.org/10.37418/amsj.10.5.6

[17] R. S. Chadha, Jugesh, S. Parveen, and J. Singh, “Fuel Sales Forecasting with SARIMA-GARCH and Rolling Window,” Journal of Soft Computing Paradigm, vol. 5, no. 3, pp. 310–326, Sep. 2023, doi: 10.36548/jscp.2023.3.007. DOI: https://doi.org/10.36548/jscp.2023.3.007

[18] M. R. Nurhambali, Y. Angraini, and A. Fitrianto, “Implementation of Long Short-Term Memory for Gold Prices Forecasting,” Malaysian Journal of Mathematical Sciences, vol. 18, no. 2, pp. 399–422, 2024, doi: 10.47836/mjms.18.2.11. DOI: https://doi.org/10.47836/mjms.18.2.11

[19] N. Kalchbrenner, I. Danihelka, and A. Graves, “Grid Long Short-Term Memory,” Jan. 2016, [Online]. Available: http://arxiv.org/abs/1507.01526

[20] W. A. Pratiwi, I. M. Sumertajaya, and K. A. Notodiputro, “Stacking Ensemble RNN-LSTM Models for Forecasting the IDR/USD Exchange Rate with Nonlinear Volatility,” Jurnal Teknik Informatika (Jutif), vol. 6, no. 4, pp. 2331–2347, Aug. 2025, doi: 10.52436/1.jutif.2025.6.4.5057. DOI: https://doi.org/10.52436/1.jutif.2025.6.4.5057

[21] X. Song, L. Deng, H. Wang, Y. Zhang, Y. He, and W. Cao, “Deep learning-based time series forecasting,” Artif. Intell. Rev., vol. 58, no. 1, Jan. 2025, doi: 10.1007/s10462-024-10989-8. DOI: https://doi.org/10.1007/s10462-024-10989-8

[22] S. Sinsomboonthong, “Performance Comparison of New Adjusted Min-Max with Decimal Scaling and Statistical Column Normalization Methods for Artificial Neural Network Classification,” Int. J. Math. Math. Sci., vol. 2022, 2022, doi: 10.1155/2022/3584406. DOI: https://doi.org/10.1155/2022/3584406

[23] Y. S. Kim, M. K. Kim, N. Fu, J. Liu, J. Wang, and J. Srebric, “Investigating the impact of data normalization methods on predicting electricity consumption in a building using different artificial neural network models,” Sustain. Cities Soc., vol. 118, Jan. 2025, doi: 10.1016/j.scs.2024.105570. DOI: https://doi.org/10.1016/j.scs.2024.105570

[24] N. Passalis, A. Tefas, J. Kanniainen, M. Gabbouj, and A. Iosifidis, “Deep Adaptive Input Normalization for Time Series Forecasting,” Sep. 2019, [Online]. Available: http://arxiv.org/abs/1902.07892

[25] A. Vamsikrishna and E. V. Gijo, “New Techniques to Perform Cross-Validation for Time Series Models,” Operations Research Forum, vol. 5, no. 2, p. 51, Jun. 2024, doi: 10.1007/s43069-024-00334-8. DOI: https://doi.org/10.1007/s43069-024-00334-8

[26] D. Febri Sakina, A. Muhaimin, J. Rungkut Madya, and E. Java, “Application of ARIMAX-LSTM Model in Forecasting the Price of Broiler Chicken in Central Java Universitas Pembangunan ‘Veteran’ Jawa Timur, Indonesia,” 2025. DOI: https://doi.org/10.36456/jstat.vol18.no1.a10555

[27] J. Sarangapani, Neural Network Control of Nonlinear Discrete-Time Systems. Manchester, United Kingdom: CRC Press, 2006.

[28] P. Goyal, S. Pandey, and K. Jain, Deep Learning for Natural Language Processing. Berkeley, CA: Apress, 2018. doi: 10.1007/978-1-4842-3685-7. DOI: https://doi.org/10.1007/978-1-4842-3685-7

[29] C. Tofallis, “A better measure of relative prediction accuracy for model selection and model estimation,” Journal of the Operational Research Society, vol. 66, no. 8, pp. 1352–1362, Aug. 2015, doi: 10.1057/jors.2014.103. DOI: https://doi.org/10.1057/jors.2014.103

[30] Badan Pusat Statistik, “Berita Resmi Statistik,” Jakarta, 2024. Accessed: Dec. 04, 2025. [Online]. Available: https://bps.go.id/pressrelease.html

[31] E. P. Cynthia, A. H. Saeed, M. Eka, and F. Nursalisah, “Pengaruh Parameter Learning Rate terhadap Konvergensi Model Neural Network dalam Proses Pelatihan,” 2025. [Online]. Available: https://journals.raskhamedia.or.id/index.php/juiktiDOI:https://doi.org/99.9999/juikti.vxix.xxxx DOI: https://doi.org/10.64803/juikti.v1i1.45