Forecasting Indonesian Nickel Reference Mineral Prices Using a Hybrid Intervention-Neural Network Model

Febiani Putri Ardhana; Meiliyani Siringoringo; Sri Wahyuningsih; Desi Yuniarti; Erlyne Nadhilah Widyaningrum

doi:10.35580/variansiunm501

Febiani Putri Ardhana Universitas Mulawarman
Meiliyani Siringoringo Universitas Mulawarman
Sri Wahyuningsih Universitas Mulawarman
Desi Yuniarti Universitas Mulawarman
Erlyne Nadhilah Widyaningrum Universitas Mulawarman

DOI: https://doi.org/10.35580/variansiunm501

Keywords: step function, neural network, indonesian nickel price, hybrid model, intervention analysis

Abstract

Time series data influenced by external events often exhibit abrupt changes and nonlinear patterns, making them difficult to model using a single forecasting approach. Hybrid models have emerged as an alternative by combining the strengths of linear and nonlinear models to improve forecasting accuracy. One approach that can be applied is the hybrid Intervention–Neural Network (NN) model. This study aims to obtain the best hybrid Intervention–NN model for forecasting Indonesian Nickel Reference Mineral Prices (Harga Mineral Acuan/HMA) using monthly data from January 2018 to February 2025, which were affected by the Russia–Ukraine conflict in February 2022. Modeling was conducted using intervention analysis with a step function combined with NN models consisting of 1, 2, 3, and 4 hidden neurons. The results indicate that the optimal model is the hybrid intervention ARIMA(1,1,0) step function model combined with a two-neuron NN, yielding an RMSE value of 1,074.3652 and a MAPE value of 4.7735%. Forecasts for the period from March 2025 to February 2026 indicate a downward trend in nickel prices.

References

Aprisal, & Abadi, A. M. (2019). Fuzzy Sistem : Estimasi Harga Nikel Dunia. Jurnal Matematika Ilmiah STKIP Muhammadiyah Kuningan, 5(1), 48-58.

Aswi, & Sukarna. (2006). Analisis Deret Waktu Aplikasi dan Teori. Makassar: Andira Publisher.

Carista, N., Mahadesyawardani, A., Dwiyanto, A. S., & Pusporani, E. (2025). Forecasting Nickel Prices in Indonesia Using ARIMA, SVR, and Hybrid ARIMA-SVR Approach. Jurnal Matematika, Statistika, dan Komputasi, 21, 627-645.

Ditjen Minerba. (2025, Agustus 1). Harga Acuan. Diambil kembali dari Minerba ESDM: https://www.minerba.esdm.go.id/harga_acuan

Fausett, L. (1994). Fundamentals of Neural Network, Achitectures, Algorithms, and Applications. New Jersey: Prentice-Hall.

Hudiyanti, C., Bachtiar, F., & Setiawan, B. (2019). Perbandingan Double Moving Average dan Double Exponential Smoothing untuk Peramalan Jumlah Kedatangan Wisatawan Mancanegara di Bandara Ngurah Rai. Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, 3(3), 2667-2672.

Kusumaningrum, N., Purnamasari, I., & Siringoringo, M. (2023). Peramalan Menggunakan Model Hybrid ARIMAX-NN untuk Total Transaksi Pembayaran Nontunai. VARIANSI: Journal of Statistics and Its Application on Teaching and Research, 5(1), 1-14.

Masrawanti, Wahyuningsih, S., & Hayati, M. (2019). Analisis Model Intervensi Fungsi Step Ganda untuk Peramalan Inflasi Indonesia ((Studi Kasus: Inflasi Indonesia Tahun 2009-2017). Jurnal Eksponensial, 10(2), 199-126.

Montgomery, D., Jenning, C., & Kulachi, M. (2008). Introduction to Time Series Analysis and Forecasting. New Jersey: John Wiley and Sons.

Natalia, D., & Hutabarat, E. C. (2025). Pengelolaan Risiko PT Vale Indonesia terhadap Volatilitas Harga Nikel akibat Konflik Geopolitik Global: Literature Review. Jurnal Ekonomi, Manajemen dan Akuntansi, 27(3), 427-433.

Primartha, R. (2018). Belajar Machine Learning Teori dan Praktek. Bandung: Informatika.

Puspitaningrum, D. (2006). Pengantar Jaringan Syaraf Tiruan. Yogyakarta: Penerbit ANDI.

Ramadhani, A., Wahyuningsih, S., & Siringoringo, M. (2022). Forecasting the Number of Foreign Tourist Visits to Indonesia Used Intervention Analysis with Step Function. Jurnal Matematika, Statistika dan Komputasi, 19(1), 146-162.

Saluza, I., Sartika, D., & Munarsih, E. (2022). Model Hybrid Menggunakan Dekomposisi-Neural Network Untuk Data Indeks Harga Saham Gabungan. Jurnal Ilmiah Informatika Global, 13(3), 206-213.

Suhartono. (2007). Teori dan Aplikasi Model Intervensi Fungsi Pulse. Jurnal Ilmiah MatStat, 79.

Wahidah, F. P., Wahyuningsih, S., & Siringoringo, M. (2024). Forecasting the Value of Indonesia’s Exports using Model Hybrid Arimax-NN. Science & Technology Asia, 29(4), 62-74.

Wahyuni, R. K., Wahyuningsih, S., & Siringoringo, M. (2023). Peramalan Harga Minyak Goreng di Kalimantan Timur Menggunakan Model Hybrid Time Series Regression Quadratic - Neural Network. Jurnal Eksponensial, 14(2), 75-84.

Wei, W. W. (2006). Time Series Analysis: Univariate and Multivariate Methods Second Edition. Boston: Pearson Education, Inc.

Zhang, G. P. (2003). Time Series Forecasting Using a Hybrid ARIMA and Neural Network Model. neurocomputing, 50, 159-175.