OPTIMIZING CAYENNE PEPPER PRICE FORECASTING USING HYBRID SARIMAX-LSTM MODEL FOR FOOD SECURITY
DOI:
https://doi.org/10.33480/jitk.v11i4.7917Keywords:
Cayenne Pepper, Food Price Prediction, Hybrid Model, LSTM, SARIMAXAbstract
The price volatility of cayenne pepper in traditional markets significantly impacts household purchasing power and regional inflation. While traditional statistical models can capture seasonal patterns, they often fail to model complex non-linear fluctuations driven by external factors such as weather anomalies and national holidays. To address these limitations, this study proposes a hybrid SARIMAX-LSTM model. The Seasonal AutoRegressive Integrated Moving Average with eXogenous variables (SARIMAX) component is utilized to model linear structures, seasonality, and the influence of exogenous variables (temperature, rainfall, and holidays), whereas the Long Short-Term Memory (LSTM) component specifically models the remaining non-linear patterns within the residuals. Daily data comprising chili prices, weather metrics, and holiday schedules were employed to train and test the model using Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE) as performance metrics. Experimental results demonstrate that the proposed hybrid model significantly outperforms the single SARIMAX baseline model, reducing the RMSE by 26.7% (from 11.09 to 8.13) and MAPE by 28.6% (from 23.45% to 16.74%). This approach not only provides a more accurate and robust decision-support tool for price stability but also contributes to the advancement of artificial intelligence-based hybrid methods in the domain of food security.
Downloads
References
[1] M. del R. Venegas, J. Feregrino, N. Lay, and J. F. Espinosa-Cristia, “Food Financialization: Impact of Derivatives and Index Funds on Agri-Food Market Volatility,” Int. J. Financ. Stud., vol. 12, no. 4, 2024, doi: 10.3390/ijfs12040121.
[2] N. M. Ginting, A. R. Lubis, and M. Zendrato, “Analisis Volatilitas, Integrasi Pasar Dan Transmisi Harga Cabai Merah Di Provinsi Sumatera Utara, Indonesia,” Agro Bali Agric. J., vol. 6, no. 3, pp. 827–839, 2023, doi: 10.37637/ab.v6i3.1519.
[3] O. Helbawanti, W. A. Saputro, and A. N. Ulfa, “Pengaruh Harga Bahan Pangan Terhadap Inflasi Di Indonesia,” AGRISAINTIFIKA J. Ilmu-Ilmu Pertan., vol. 5, no. 2, pp. 107–116, 2021, doi: 10.32585/ags.v5i2.1859.
[4] Y. J. Siregar, R. Hartono, and A. E. Hardana, “Peramalan Harga Cabai Rawit Di Kota Malang Dengan Metode Holt-Winters Exponential Smoothing,” Agricore J. Agribisnis dan Sos. Ekon. Pertan. Unpad, vol. 6, no. 2, pp. 99–110, 2021, doi: 10.24198/agricore.v6i2.34778.
[5] M. M. Rahman, R. Nguyen, and L. Lu, “Multi-level impacts of climate change and supply disruption events on a potato supply chain: An agent-based modeling approach,” Agric. Syst., vol. 201, pp. 1–34, 2022, doi: 10.1016/j.agsy.2022.103469.
[6] E. Obermair, A. Holzapfel, and H. Kuhn, “Operational planning for public holidays in grocery retailing - managing the grocery retail rush,” Oper. Manag. Res., vol. 16, no. 2, pp. 931–948, 2023, doi: 10.1007/s12063-022-00342-z.
[7] D. W. L. Lestari and S. K. Dini, “Forecasting The Price Of Shallots And Red Chilies Using The ARIMAX Model,” EKSAKTA J. Sci. Data Anal., vol. 5, no. 1, pp. 42–49, 2024, doi: 10.20885/eksakta.vol5.iss1.art5.
[8] F. N. Fikri and N. Nurochman, “Performance Evaluation of Long Short-Term Memory for Chili Price Prediction,” JISKA (Jurnal Inform. Sunan Kalijaga), vol. 10, no. 1, pp. 33–47, 2025, doi: 10.14421/jiska.2025.10.1.33-47.
[9] B. Butar Butar, A. Giffari, Z. D. Putri, M. Karisma, W. Kurniawan, and M. H. Fuad, “Forecasting Rice Prices Using the ARIMA Method: A Case Study in DKI Jakarta Province-Belsana Butar Butar et.al Forecasting Rice Prices Using the ARIMA Method: A Case Study in DKI Jakarta Province,” J. Multidisiplin Sahombu, vol. 5, no. 02, pp. 299–308, 2025, doi: 10.58471/jms.v5i02.
[10] E. Nurhasanah, Y. Sukmawaty, and M. Maisarah, “Peramalan Ekspor Migas di Indonesia Menggunakan Pendekatan Seasonal Autoregressive Integrated Moving Average with Exogenous (SARIMAX),” Indones. J. Appl. Stat., vol. 7, no. 1, p. 87, 2024, doi: 10.13057/ijas.v7i1.84934.
[11] Faris Nasirudin and Abdullah Ahmad dzikrullah, “Pemodelan Harga Cabai Indonesia dengan Metode Seasonal ARIMAX,” J. Stat. dan Apl., vol. 7, no. 1, pp. 105–115, 2023, doi: 10.21009/jsa.07110.
[12] D. Wang, I. Gryshova, M. Kyzym, T. Salashenko, V. Khaustova, and M. Shcherbata, “Electricity Price Instability over Time: Time Series Analysis and Forecasting,” Sustain., vol. 14, no. 15, pp. 1–24, 2022, doi: 10.3390/su14159081.
[13] M. Tami and A. Y. Owda, “Efficient commodity price forecasting using long short-term memory model,” IAES Int. J. Artif. Intell., vol. 13, no. 1, pp. 994–1004, 2024, doi: 10.11591/ijai.v13.i1.pp994-1004.
[14] B. Yun, J. Lai, Y. Ma, and Y. Zheng, “Research on Grain Futures Price Prediction Based on a Bi-DSConvLSTM-Attention Model,” Systems, vol. 12, no. 6, 2024, doi: 10.3390/systems12060204.
[15] M. Waqas and U. W. Humphries, “A critical review of RNN and LSTM variants in hydrological time series predictions,” MethodsX, vol. 13, no. July, p. 102946, 2024, doi: 10.1016/j.mex.2024.102946.
[16] C. S. Fiskin, O. Turgut, S. Westgaard, and A. G. Cerit, “Time series forecasting of domestic shipping market: Comparison of SARIMAX, ANN-based models and SARIMAX-ANN hybrid model,” Int. J. Shipp. Transp. Logist., vol. 14, no. 3, pp. 193–221, 2022, doi: 10.1504/IJSTL.2022.122409.
[17] D. Kurniasari, A. D. Salsabila, M. Usman, and W. Warsono, “Enhancing Weather Forecasting in Bandar Lampung: A Hybrid SARIMA-LSTM Approach,” JTAM (Jurnal Teor. dan Apl. Mat., vol. 9, no. 1, p. 206, 2025, doi: 10.31764/jtam.v9i1.27188.
[18] J. Sung, X. Shi, S. Teske, and M. Li, “A hybrid SARIMAX-LSTM model optimised by ANN for near-term forecasting: An application to China’s natural gas consumption,” Centre for Climate Risk and Resilience (CCRR), University of Technology Sydney, Sydney, Australia, 2025. [Online]. Available: https://opus.lib.uts.edu.au/handle/10453/187869.
[19] J. Bana and K. Utnik-bana, “Evaluating a seasonal autoregressive moving average model with an exogenous variable for short-term timber price forecasting,” For. Policy Econ. J., vol. 131, no. July, pp. 1–7, 2021, doi: 10.1016/j.forpol.2021.102564.
[20] D. Ashtar, S. S. Mohammadi Ziabari, and A. M. M. Alsahag, “Hybrid Forecasting for Sustainable Electricity Demand in The Netherlands Using SARIMAX, SARIMAX-LSTM, and Sequence-to-Sequence Deep Learning Models,” Sustain., vol. 17, no. 16, 2025, doi: 10.3390/su17167192.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Adi Supriyatna, Mari Rahmawati, Burhanudin Rabbani, Asta Wenang, Sulthan Adly
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
-a.jpg)
-b.jpg)
