Melola Discovery

← Melola Discovery

Jurnal Tanpa peringkat SINTA

Performance of SARIMA, LSTM, GRU and Ensemble Methods for Forecasting Nickel Prices

Scientific Journal of Informatics · Vol. 12 No. 4 (2025) · hlm. 611–622

DOI
10.15294/sji.v12i4.32225
ISSN
2407-7658, 2460-0040
Terbit
2025-11-19
Penerbit
Universitas Negeri Semarang
Bahasa
eng

Abstrak

Purpose: There are several forecasting methods, including SARIMA, LSTM, and GRU, which are often claimed to exhibit strong performance in capturing patterns in time series data. However, few studies have conducted direct comparisons among these methods. Therefore, it is necessary to conduct a performance evaluation using empirical data, particularly nickel prices data. This study also aims to improve forecasting performance by combining prediction outputs from deep learning-based models. Methods: This study utilized data on monthly global nickel prices from January 1990 to May 2025. The models developed include SARIMA, LSTM, GRU, and two ensemble approaches: Weighted Averaging and Bayesian Model Averaging (BMA). Model validation was conducted using walk-forward validation with a sliding window approach to evaluate each model’s generalization performance on out-of-sample validation data. The performance was evaluated using MAPE, RMSE, and MAE. Result: The BMA Ensemble approach shows the best performance in forecasting nickel prices, with a MAPE value of 5.39%, RMSE of 1897.84, and MAE of 1133.96. Prediction validation produces MAPE values below 10%, which indicates that the forecasting results are accurate. The ensemble BMA approach is able to produce more accurate and stable predictions compared to other models. Novelty: This study offers a novel approach combining LSTM and GRU through ensemble methods to forecast global nickel prices using monthly historical data from 1990 to 2025. In contrast to previous studies that relied on single models, the proposed method with the ensemble BMA approach demonstrates improved forecasting accuracy and stability.

Kata kunci

Jaringan kolaborasi para penulis

40 penulis · 121 tautan kepenulisan bersama · 24 lintas organisasi · menampilkan 40 yang paling banyak terhubung

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • IPB University
  • Bandung Islamic University
  • State University of Jakarta
  • Universitas Sulawesi Barat
  • Universitas Islam Negeri Alauddin Makassar
  • Universitas Prasetiya Mulya
  • President University
  • Organisasi lain
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama
Yenni AngrainiIPB University10
Bagus SartonoIPB University10
Laily Nissa Atul MualifahIPB University7
Budi SusetyoIPB University2
Kusman SadikIPB University2
Fatma Hilali Moh’dIPB University2
Muhammad Nur AidiIPB University2
Anang KurniaIPB University2
I Made SumertajayaIPB University2
ERFIANI ERFIANIIPB University2
Anwar FitriantoIPB University2
Teguh PrasetyoIPB University1
Rizki Alifah PutriIPB University1
Dini RamadhaniIPB University1
Dwi Agustin Nuriani SirodjBandung Islamic University1
Pradnya Sri RahayuIPB University1
Nabila Ghoni Trisno HidayatullohIPB University1
Vera Maya SantiState University of Jakarta1
INDAHWATI INDAHWATIIPB University1
Hafizah IlmaIPB University1
Andika Putri RatnasariIPB University1
Rahmatin Nur AmaliaIPB University1
Asrirawan AsrirawanUniversitas Sulawesi Barat1
Vivin Nur AzizaIPB University1
Firda Aulia MaghfirohIPB University1
Khalilah NurfadilahUniversitas Islam Negeri Alauddin Makassar1
Muhammad Azis SuprayogiIPB University1
Agus Sofian Eka HidayatPresident University1
Dian KusumaningrumUniversitas Prasetiya Mulya1
Arie PurwantoUniversitas Mercu Buana Yogyakarta1
Indra Rivaldi SiregarIPB University1
Adhiyatma NugrahaIPB University1
Riska YuliantiIPB University1
Nabila Tri AmandaIPB University1
Aleytha Ilahnugrah KurnadipareIPB University1
Sri AmaliyaIPB University1
Windy Ayu PratiwiIPB University1

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OAI-PMH (metadata jurnal) https://journal.unnes.ac.id/journals/sji/oai, pertama di-harvest 6 Nov 2026, terakhir terlihat 8 Nov 2026.
Metadata asli (oai_dc)
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en">Performance of SARIMA, LSTM, GRU and Ensemble Methods for Forecasting Nickel Prices</dc:title>
	<dc:creator xml:lang="en">Irdayanti</dc:creator>
	<dc:creator xml:lang="en">Notodiputro, Khairil Anwar</dc:creator>
	<dc:creator xml:lang="en">Oktarina, Sachnaz Desta</dc:creator>
	<dc:subject xml:lang="en">Decent work and economic growth</dc:subject>
	<dc:subject xml:lang="en">Deep learning</dc:subject>
	<dc:subject xml:lang="en">Ensemble forecast</dc:subject>
	<dc:subject xml:lang="en">Volatility</dc:subject>
	<dc:description xml:lang="en">Purpose: There are several forecasting methods, including SARIMA, LSTM, and GRU, which are often claimed to exhibit strong performance in capturing patterns in time series data. However, few studies have conducted direct comparisons among these methods. Therefore, it is necessary to conduct a performance evaluation using empirical data, particularly nickel prices data. This study also aims to improve forecasting performance by combining prediction outputs from deep learning-based models.
Methods: This study utilized data on monthly global nickel prices from January 1990 to May 2025. The models developed include SARIMA, LSTM, GRU, and two ensemble approaches: Weighted Averaging and Bayesian Model Averaging (BMA). Model validation was conducted using walk-forward validation with a sliding window approach to evaluate each model’s generalization performance on out-of-sample validation data. The performance was evaluated using MAPE, RMSE, and MAE.
Result: The BMA Ensemble approach shows the best performance in forecasting nickel prices, with a MAPE value of 5.39%, RMSE of 1897.84, and MAE of 1133.96. Prediction validation produces MAPE values below 10%, which indicates that the forecasting results are accurate. The ensemble BMA approach is able to produce more accurate and stable predictions compared to other models.
Novelty: This study offers a novel approach combining LSTM and GRU through ensemble methods to forecast global nickel prices using monthly historical data from 1990 to 2025. In contrast to previous studies that relied on single models, the proposed method with the ensemble BMA approach demonstrates improved forecasting accuracy and stability.</dc:description>
	<dc:publisher xml:lang="en">Universitas Negeri Semarang</dc:publisher>
	<dc:date>2025-11-19</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:type xml:lang="en">Peer-reviewed Article</dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://journal.unnes.ac.id/journals/sji/article/view/32225</dc:identifier>
	<dc:identifier>10.15294/sji.v12i4.32225</dc:identifier>
	<dc:source xml:lang="en">Scientific Journal of Informatics; Vol. 12 No. 4: Special Issue; 611-622</dc:source>
	<dc:source>2407-7658</dc:source>
	<dc:source>2460-0040</dc:source>
	<dc:source>10.15294/sji.v12i4</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://journal.unnes.ac.id/journals/sji/article/view/32225/7444</dc:relation>
	<dc:rights xml:lang="en">Copyright (c) 2025 Scientific Journal of Informatics</dc:rights>
</oai_dc:dc>