Analysis of Red Bird’s Eye Chili Price Dynamics in Surabaya Using an Optuna-Optimized ARIMA-LightGBM Model

Imara Luthfiya; Kartika Maulida Hindrayani; Aviolla Terza Damaliana

doi:10.30871/jaic.v10i5.13829

Authors

Imara Luthfiya Universitas Pembangunan Nasional "Veteran" Jawa Timur
Kartika Maulida Hindrayani Universitas Pembangunan Nasional "Veteran" Jawa Timur
Aviolla Terza Damaliana Universitas Pembangunan Nasional "Veteran" Jawa Timur

DOI:

https://doi.org/10.30871/jaic.v10i5.13829

Keywords:

ARIMA, LightGBM, Optuna, Prediction, Red Bird's Eye Chili

Abstract

Red bird’s eye chili is one of the food commodities widely needed by the community and tends to experience price fluctuations. This situation can create difficulties for consumers, traders, and food business operators in planning purchases. This is due to rapid price fluctuations, which may delays the chili purchases while prices remain unstable. In Surabaya, high demand and limited local production contribute to price variability. This study aims to predict red bird’s eye chili prices in Surabaya for a short-term horizon of 14 days by applying a hybrid ARIMA-LightGBM model optimized with Optuna. The data used in this study are historical red bird’s eye chili price data from Genteng Market and Keputran Market. ARIMA is used to capture linear patterns in time series data, while LightGBM is applied to model the residual patterns that cannot be fully explained by ARIMA. Optuna optimization is used to obtain optimal hyperparameter configuration. The evaluation results showed that the Optuna-optimized ARIMA-LightGBM model achieved the lowest forecasting errors among the evaluated models. The model obtained a MAPE of 22.84% for Genteng Market and 23.55% for Keputran Market. The comparison with Seasonal Naive, ARIMA, and ARIMA-LightGBM without optimization demonstrated that the hybrid ARIMA-LightGBM model with Optuna optimization provides improved prediction performance for short term red bird’s eye chili price prediction.

Downloads

Download data is not yet available.

References

[1] S. Pertanian and K. Pertanian, “Statistik Makro 2025 Pusat Data Dan Sistem Informasi Pertanian Center For Agricultural Data And Information System,” 2025.

[2] Khairani, Adriana, and Pardi, “Isolasi Dan Karakterisasi Senyawa Capsaicin Dari Cabai Rawit (Capsicum Frutescens L.) Sebagai Bahan Aditif Pangan Dengan Metode Ekstraksi Sokletasi,” J. Teknol., vol. 24, no. 1, pp. 35–40, 2024.

[3] W. Puspitasari, “Statistik Hortikultura Provinsi Jawa Timur 2024,” 2025.

[4] F. Hilmiyah and A. Supriono, “Market Integration And Price Transmission Of Cayenne Pepper In Indonesia,” JSEP (Journal of Social and Agricultural Economics), vol. 15, no. 2, p. 209, Jul. 2022, doi: 10.19184/jsep.v15i2.24690.

[5] Disperindag Jatim, “Harga Komoditas Jawa Timur,” Siskaperbako.

[6] R. J. Hyndman and G. Athanasopoulos, Forecasting: Principles and Practice, 3rd ed. Australia: OTexts, 2021.

[7] J. L. Az-Zahra and A. Voutama, “Implementasi Data Mining Untuk Prediksi Harga Cabai Rawit Merah Menggunakan Metode Single Moving Average (Studi Kasus: Kabupaten Bekasi),” Jurnal Mahasiswa Teknik Informatika, vol. 10, no. 3, 2026.

[8] Y. Ma and J. Li, “Recognition and Prediction of Multi-Level Handling Complexity at Automated Terminals Based on ARIMA,” J. Mar. Sci. Eng., vol. 12, pp. 1–6, Jul. 2024, doi: 10.3390/jmse12071201.

[9] R. J. Wishnuwardana, M. B. Omar, H. B. Zabiri, M. Faqih, K. Bingi, and R. Ibrahim, “Optuna-LightGBM : An Optuna hyperparameter optimization framework for the determination of solvent components in acid gas removal unit using LightGBM,” Clean. Eng. Technol., vol. 28, 2025, doi: 10.1016/j.clet.2025.101054.

[10] B. Cindy Thalita, B. Abyasa Arya Pradipta, M. Christiano, F. Indriana Yusuf, and E. W. Handamari, “Perbandingan Kinerja Prediksi Frekuensi Klaim Asuransi Kendaraan Menggunakan Arima Vs Algoritma Random Forest,” Jurnal Riset dan Aplikasi Matematika (JRAM), vol. 10, no. 1, pp. 13–28, 2026, doi: 10.26740/jram.v10n1.p13-28.

[11] S. Eka Oktaviani, Trimono, and A. Terza Damaliana, “Prediksi Permintaan Darah Di Utd Kota Surabaya Menggunakan Metode Hybrid Arima-Anfis,” Lebesgue: Jurnal Ilmiah Pendidikan Matematika, Matematika dan Statistika, vol. 6, no. 1, 2025, doi: 10.46306/lb.v6i1.

[12] G. D. Ahadi and N. N. L. E. Zain, “Pemeriksaan Uji Kenormalan dengan Kolmogorov-Smirnov, Anderson-Darling dan Shapiro-Wilk,” Eigen Mathematics Journal, vol. 6, no. 1, pp. 12–19, Jun. 2023, doi: 10.29303/emj.v6i1.131.

[13] I. Ginting, Trimono, and K. M. Hindrayani, “ARIMA-TGARCH Model for Return Prediction and Risk Estimation with VaR,” bit-Tech, vol. 8, no. 2, Dec. 2025, doi: 10.32877/bt.v8i2.3090.

[14] D. Raihan and I. Lubis, “Optimalisasi Model Peramalan Penjualan Dengan Pendekatan Algoritma Light Gradient Boosting Machine (LIGHTGBM),” Journal Computer and Technology, vol. 3, no. 2, pp. 137–143, 2025, doi: 10.69916/comtechno.v3i2.413.

[15] Y. Nur, K. Maulida Hindrayani, and A. Terza Damaliana, “Optimasi Elastic Net Regression Dengan Optuna Untuk Analisis Faktor Kemiskinan Di Indonesia,” 2025.

[16] B. Ramadhan and S. F. Pane, “Pengaruh Hyperparameter Tuning untuk Efektivitas pada Pendekatan Hybrid dalam Mendiagnosis Stres dan Depresi : Tinjauan Studi Literatur,” Jurnal Tekno Insentif, vol. 18, no. 2, pp. 104–118, 2024, doi: 10.36787/jti.v18i2.1516.

[17] A. J. Azizah, D. A. Prasetya, K. M. Hindrayani, and T. M. Fahrudin, “Implementation of Transfer Function ARIMA Model for Stock Price Prediction,” International Journal of Advances in Data and Information Systems, vol. 6, no. 2, pp. 434–446, Aug. 2025, doi: 10.59395/ijadis.v6i2.1396.