##plugins.themes.academic_pro.article.main##
Perbandingan Model ARIMA dan SARIMA untuk Peramalan Harga Emas Harian
Abstract
Volatilitas harga emas mencapai 68,75% pada periode 2022–2025, mengakibatkan kerugian investor akibat ketidakakuratan model konvensional yang mengabaikan pola musiman jangka pendek. Penelitian ini mengidentifikasi kesenjangan literatur: belum ada studi yang mengeksplorasi pola musiman sub-bulanan (<30 hari) pada data harian, meskipun siklus perdagangan memiliki periodesitas 20–23 hari kerja. Kami mengembangkan model SARIMA (0,1,1) (1,1,1) yang mengintegrasikan pola musiman 23 hari menggunakan metodologi Box-Jenkins pada 963 observasi periode Januari 2022–Oktober 2025. Hasil menunjukkan SARIMA meningkatkan akurasi prediksi sebesar 36,41% (MAPE 10,16% vs 15,98%) dan secara signifikan mereduksi indikasi overfitting, yang ditandai dengan penyempitan disparitas error antara data latih dan uji dibandingkan ARIMA. Model ini dapat mengurangi kerugian prediksi hingga USD 58.200 per siklus perdagangan untuk portofolio USD 1 juta, memberikan keunggulan kompetitif bagi trader institusional. Sistem ini direkomendasikan sebagai alat bantu keputusan operasional dengan pembaruan parameter setiap 3–6 bulan.
##plugins.themes.academic_pro.article.details##
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
References
W. Mensi, I. Yousaf, X. V. Vo, and S. H. Kang, "Asymmetric spillover and network connectedness between gold, BRENT oil and EU subsector markets," J. Int. Financ. Mark. Inst. Money, vol. 76, 101487, Feb. 2023.
World Gold Council, "Gold Market Outlook 2025," London, UK, Rep. Q4 2024, Jan. 2025.
S. S. Kumar, M. P. Yadav, S. Kumar, and R. K. Singh, "Gold price forecasting using artificial neural network and support vector machines," Resour. Policy, vol. 80, 103215, Mar. 2023.
X. Zhang, Y. Zhao, and S. Sun, "A novel hybrid model for gold price forecasting based on variational mode decomposition and deep learning," Expert Syst. Appl., vol. 213, 119081, Mar. 2023.
R. H. Shumway and D. S. Stoffer, Time Series Analysis and Its Applications: With R Examples, 5th ed., Cham, Switzerland: Springer, 2024.
C. Chatfield and H. Xing, The Analysis of Time Series: An Introduction with R, 7th ed., Boca Raton, FL, USA: CRC Press, 2022.C. Francq and J. M. Zakoian, GARCH Models: Structure, Statistical Inference and Financial Applications, 2nd ed. Hoboken, NJ, USA: John Wiley & Sons, 2024.
N. N. Taleb, Statistical Consequences of Fat Tails: Real World Preasymptotics, Epistemology, and Applications, New York, NY, USA: STEM Academic Press, 2021.
C. Francq and J. M. Zakoian, GARCH Models: Structure, Statistical Inference and Financial Applications, 2nd ed., Hoboken, NJ, USA: John Wiley & Sons, 2024.
R. J. Hyndman and G. Athanasopoulos, Forecasting: Principles and Practice, 3rd ed., Melbourne, Australia: OTexts, 2021.
I. E. Livieris, E. Pintelas, and P. Pintelas, "A CNN-LSTM model for gold price time-series forecasting," Neural Comput. Appl., vol. 32, no. 23, pp. 17351-17360, Dec. 2020.
W. Setiawan, A. P. Wibawa, and M. A. Bijaksana, "Peramalan harga emas menggunakan metode ARIMA, support vector regression, dan random forest," Jurnal Teknologi Informasi dan Ilmu Komputer, vol. 9, no. 5, pp. 1051-1058, Oct. 2022.
A. K. Bentes, "Are central banks' gold reserves a safe haven? Evidence from the 2008-2020 period," Resour. Policy, vol. 74, p. 102380, Dec. 2021.
