A Comparison of the Holt-Winters Additive and Multiplicative Methods with Grid search Optimization in Forecasting Red Chili Prices in Bengkulu City

Jose Rizal; Ressy Fitrizka Haryanti; Winalia Agwil

doi:10.20956/j.v22i1.45755

Authors

Jose Rizal Statistics Study Program, Department of Mathematics, Faculty of Mathematics and Natural Sciences, University of Bengkulu
Ressy Fitrizka Haryanti Statistics Study Program, Department of Mathematics, Faculty of Mathematics and Natural Sciences, University of Bengkulu
Winalia Agwil Statistics Study Program, Department of Mathematics, Faculty of Mathematics and Natural Sciences, University of Bengkulu

DOI:

https://doi.org/10.20956/j.v22i1.45755

Keywords:

Holt-Winters, Grid search, Red Chili, Statistical optimization, Box-Jenkins method.

Abstract

The Holt-Winters Additive and Multiplicative methods are time series forecasting techniques that consider trend and seasonal patterns. To improve forecasting accuracy, optimization of model parameters, such as alpha, beta, and gamma, is required. This study compares four parameter optimization methods, namely Grid search, Bayesian optimization, Trial and error, and Nelder-mead, through simulation on the generation data and application on weekly red chili price data in Bengkulu City. Red chili was chosen as the object of study because it is a strategic horticultural commodity that has high demand and significant price fluctuations, thus affecting inflation and deflation in Bengkulu City. Simulation results show that the Grid search method consistently produces lower error values and more efficient computation time at iterations 15, 25, 50, and 100. Based on the optimal parameters of Grid search (alpha = 1, beta = 0.1, gamma = 0.1), a Holt-Winters model is obtained that can be used to forecast the price of red chili in Bengkulu City in the first 3 months of 2025. Based on the evaluation of the prediction results, the Additive model provides better performance than the Multiplicative model, with a MAPE value of 11,92% and an RMSE of 7450,52. These findings indicate that the combination of the Holt-Winters Additive method and Grid search optimization is effective in forecasting weekly red chili pepper prices, and can be used as a basis for policy making to control the price of strategic commodities in Bengkulu City

References

[1] Anggraeni, H.Y.D., 2022. Peramalan Suhu Udara Maksimum Dan Minimum Harian Menggunakan Metode Arima Dan Exponential Smoothing. Fakultas Matematika dan Ilmu Pengetahuan Alam, Universitas Nahdatul Ulama Al Ghazali, Cilacap.

[2] Chandrasa, M.A.D., Lesmana, E. & Hertini, E., 2020. Peramalan Jumlah Kedatangan Wisatawan Mancanegara Ke Indonesia Dengan Metode Holt-Winters Dan Hubungannya Terhadap Pendapatan Devisa Pariwisata. Teorema Teor. dan Ris. Mat., Vol. 5, No. 2, 230–238.

[3] Dewi, N., P. & Listiowarni, I., 2020. Implementasi Holt-Winters Exponential Smoothing untuk Peramalan Harga Bahan Pangan di Kabupaten Pamekasa. Digit. Zo. J. Teknol. Inf. dan Komun., Vol. 11, No. 2, 223–236.

[4] Drop, N. & Bohdan, A., 2025. Application of the Holt–Winters Model in the Forecasting of Passenger Traffic at Szczecin–Goleniów Airport (Poland). Sustainability, Vol. 17, No. 14, 1–21.

[5] Fahik, D., S. & Jatipaningrum, M. T., 2021. Peramalan Jumlah Penumpang Penerbangan Internasional Di Bandar Udara Internasional Soekarno Hatta Dengan Metode Holt-Winters Exponential Smoothing Dan Seasonal Arima. Stat. Ind. dan Komputasi, Vol. 6, No. 1, 77–87.

[6] Febriyanti, A., N. & Rifai, N.A.K., 2022. Metode Triple Exponential Smoothing Holt-Winters untuk Peramalan Jumlah Penumpang Kereta Api di Pulau Jawa. Bandung Conf. Ser. Stat., Vol. 2, No. 2, 152–158.

[7] Haben, S., Voss, M. & Holderbaum, W., 2023. Core concepts and methods in load forecasting: With applications in distribution networks. Springer Nature.

[8] Kusuma, E., J., Nurmandhani, R., Aryani, L., Pantiawati, I. & Shidik, G.F., 2025. Optimasi Model Extreme Gradient Boosting Dalam Upaya Penentuan Tingkat Risiko Pada Ibu Hamil Berbasis Bayesian Machine Learning Optimization In Determining The Maternal Risk. Vol. 12, No. 1, 111–120.

[9] Masyuni, I., A., Nugroho, B.K., Mardikawati, B. & Hidayat, D., W., 2020. Peramalan Jumlah Penumpang Angkutan Bus Antar Kota Antar Propinsi Menggunakan Metode Holt-Winters. J. Teknol. Transp. dan Logistik, Vol. 2, No. 1, 49–56.

[10] Milniadi, A., D. & Adiwijaya, N.O., 2023. Analisis Perbandingan Model Arima Dan Lstm Dalam Peramalan Harga Penutupan Saham (Studi Kasus : 6 Kriteria Kategori Saham Menurut Peter Lynch). SIBATIK J. J. Ilm. Bid. Sos. Ekon. Budaya, Teknol. dan Pendidik., Vol. 2, No. 6, 1683–1692.

[11] Mohapatra, A. & Nayak, B., 2018. Parameter estimation of single diode PV module based on Nelder-Mead optimization algorithm. World J. Eng., Vol. 15, No. 1, 70–81.

[12] Oriekhoe, O. I., Addy, W. A., Okoye, C. C., Oyewole, A. T., Ofodile, O. C. & Ugochukwu, C. E., 2024. The role of accounting in mitigating food supply chain risks and food price volatility. International Journal of Science and Research Archive. Vol. 11, No. 1, 2557-2565.

[13] Pattipeilohy, W., J., Barung, F., M. & Ronsumbre, E., Y., 2024. Analisis Analisis Perubahan Pola Musim dan Distribusi Frekuensi Curah Hujan di Sentani. Bul. GAW Bariri, Vol. 5, No. 1, 1–9.

[14] Prasetyo, V., R., Lazuardi, H., Mulyono, A., A. & Lauw, C., 2021. Penerapan Aplikasi RapidMiner Untuk Prediksi Nilai Tukar Rupiah Terhadap US Dollar Dengan Metode Linear Regression. J. Nas. Teknol. dan Sist. Inf., Vol. 7, No. 1, 8–17.

[15] Purnama, D. I. & Hendarsin, O.P., 2020. Peramalan Jumlah Penumpang Berangkat Melalui Transportasi Udara di Sulawesi Tengah Menggunakan Support Vector Regression (SVR). Jambura J. Math., Vol. 2,No. 2, 49–59.

[16] Rais, A., N., Rousyati, R., Thira, I., J., Kholifah, D., N., Purwati, N. & Kristania, Y.M., 2020. Evaluasi Metode Forecasting pada Data Kunjungan Wisatawan Mancanegara ke Indonesia. EVOLUSI J. Sains dan Manaj., Vol. 8, No. 2, 104–11.

[17] Safitri, T., Dwidayati, N. & Sugiman, 2017. Perbandingan Peramalan Menggunakan Metode Exponential Smoothing Holt-Winters dan Arima. Unnes J. Math., Vol. 6, No. 1, 48–58.

[18] Sawalha, S. & Al-Naymat, G., 2025. An Adaptive Holt–Winters Model for Seasonal Forecasting of Internet of Things (IoT) Data Streams. IoT, Vol. 6, No. 3, 1–18.

[19] Sergio, A., Wahyuningsih, S. & Siringoringo, M., 2023. Peramalan Inflasi Kota Balikpapan Menggunakan Metode Singular Spectrum Analysis. Eksponensial, Vol. 14, No. 1, 21–30.

[20] Setyo, V., K. & Abdillah, M.Z., 2024. Prediksi Tonase Penjualan Pt . Immanuel Periode 2015-2024 Dengan Metode Triple Exponential Smoothing Sales Forecasting For Pt . Immanuel Using Triple Exponential Smoothing. Vol. 4, No. 12, 585–595.

[21] Surur, A. M., 2021. Thorndike’s theory for improving madrasah teacher’s creative thinking and publication. In International Conference on Engineering, Technology and Social Science (ICONETOS 2020), 828-839.

[22] Takenaga, S., Ozaki, Y. & Onishi, M., 2023. Practical initialization of the Nelder–Mead method for computationally expensive optimization problems. Optimization Letters, Vol. 17, No. 2, 283-297.

[23] Tönnsen, K.C., 2021. The relevance of trial-and-error: Can trial-and-error be a sufficient learning method in technical problem-solving-contexts?. Techne serien-Forskning i slöjdpedagogik och slöjdvetenskap. Vol. 28, No. 2, 303-312.

[24] Trianto, A., Muliawati. & Irmanda, H.N., 2022. Penerapan Borderline-SMOTE dan Grid search pada Bagging-SVM untuk Klasifikasi Penyakit Diabetes. Semin. Nas. Mhs. Ilmu Komput. dan Apl., Vol. 3, No. 2, 102–113.

[25] Zayat, W. & Sennaroglu, B., 2020. Performance Comparison of Holt-Winters and SARIMA Models for Tourism Forecasting in Turkey. Vol. 21, No. 2, 63–77.