Peramalan Inflasi dan Harga Minyak Mentah dengan Pendekatan Hybrid Statistika-Machine Learning dan Statistika-Deep Learning
DOI:
https://doi.org/10.53513/jursi.v5i1.12342Keywords:
Deep Learning, Hybrid, Machine Learning, Statistika, Time SeriesAbstract
Inflasi dan harga minyak mentah merupakan dua indikator ekonomi strategis yang memengaruhi stabilitas ekonomi nasional dan arah kebijakan publik. Peramalan yang akurat terhadap kedua variabel ini sangat penting untuk mendukung perencanaan fiskal, moneter, serta strategi sektor industri dan perdagangan. Karakteristik keduanya berbeda, dimana inflasi cenderung memiliki pola tren dan musiman yang relatif stabil, sedangkan harga minyak mentah bersifat fluktuatif dengan pengaruh faktor eksternal global. Perbedaan ini menuntut metode peramalan yang adaptif dan mampu bekerja baik pada kondisi data yang berbeda. Penelitian ini memiliki keterkaitan dengan Sustainable Development Goals (SDG 8 dan SDG 9). Penelitian ini bertujuan mengembangkan metode time series forecasting berbasis pendekatan hybrid melalui model statistika-machine learning dan statistika-deep learning. Pendekatan statistika dengan model Autoregressive Integrated Moving Average (ARIMA) digunakan untuk menangkap pola linear, kemudian hasil prediksi atau residual dari model ARIMA diproses lebih lanjut menggunakan algoritma machine learning yaitu Support Vector Regression (SVR) dan model deep learning yaitu Long Short-Term Memory (LSTM) untuk mempelajari pola non-linear. Dalam hal ini, evaluasi akurasi model diukur dengan metrik symmetric Mean Absolute Percentage Error (sMAPE). Hasil penelitian menunjukkan bahwa model ARIMA-SVR memiliki akurasi lebih baik dalam meramalkan data inflasi dengan nilai sMAPE sebesar 0,2072. Sebaliknya, model ARIMA-LSTM lebih akurat dalam meramalkan data harga minyak dengan nilai sMAPE sebesar 0,0548. Dengan demikian, pendekatan hybrid statistika-machine learning dan statistika-deep learning memiliki akurasi yang baik dalam memprediksi data yang bersifat time series.
References
A. Bilalli, M. Sadiku, and L. Sadiku, “The impact of inflation on financial sector performance: Evidence from OECD countries,” Economics, vol. 12, pp. 263–276, 2024, doi: 10.2478/eoik-2024-0028.
G. Brancaccio, M. Kalouptsidi, and T. Papageorgiou, “The impact of oil prices on world trade,” Review of International Economics, 2022, doi: 10.1111/roie.12632.
W. Juraphanthong and K. Kesorn, “Autoregressive integrated moving average with semantic information: An efficient technique for intelligent prediction of dengue cases,” Engineering Applications of Artificial Intelligence, vol. 143, p. 109985, 2025, doi: 10.1016/j.engappai.2024.109985.
C. Andreas, I. A. Rahmayanti, and S. M. Ulyah, “The impact of US-China trade war in forecasting the gold price using ARIMAX model,” in AIP Conference Proceedings, vol. 2329, no. 1, p. 060011, Feb. 2021, doi: 10.1063/5.0043277.
P. Bartlett, A. Montanari, and A. Rakhlin, “Deep learning: a statistical viewpoint,” Acta Numerica, vol. 30, pp. 87–201, 2021, doi: 10.1017/S0962492921000027.
Y. Zhao and Z. Chen, “Forecasting stock price movement: New evidence from a novel hybrid deep learning model,” Journal of Asian Business and Economic Studies, 2021, doi: 10.1108/jabes-05-2021-0061.
M. Ahmadi, S. Jafarzadeh-Ghoushchi, R. Taghizadeh, and A. Sharifi, “Presentation of a new hybrid approach for forecasting economic growth using artificial intelligence approaches,” Neural Computing and Applications, vol. 31, pp. 8661–8680, 2019, doi: 10.1007/s00521-019-04417-0.
S. Jafarian-Namin, S. Ghomi, M. Shojaie, and S. Shavvalpour, “Annual forecasting of inflation rate in Iran: Autoregressive integrated moving average modeling approach,” Engineering Reports, vol. 3, 2021, doi: 10.1002/eng2.12344.
I. A. Rahmayanti, C. Andreas, and S. M. Ulyah, “Does US-China trade war affect the Brent crude oil price? An ARIMAX forecasting approach,” in AIP Conference Proceedings, vol. 2329, no. 1, p. 060010, Feb. 2021, doi: 10.1063/5.0042003.
A. Altan and S. Karasu, “Crude oil time series prediction model based on LSTM network with chaotic Henry gas solubility optimization,” Energy, 2021, doi: 10.1016/j.energy.2021.122964.
C. Zhang and X. Zhou, “Forecasting value-at-risk of crude oil futures using a hybrid ARIMA-SVR-POT model,” Heliyon, vol. 10, p. e23358, 2023, doi: 10.1016/j.heliyon.2023.e23358.
D. Fan, H. Sun, J. Yao, K. Zhang, X. Yan, and Z. Sun, “Well production forecasting based on ARIMA-LSTM model considering manual operations,” Energy, vol. 220, p. 119708, Mar. 2021, doi: 10.1016/j.energy.2020.119708.
C. Andreas, “Perbandingan Pendekatan Statistika dan Machine Learning dalam Peramalan Data Time Series,” Jurnal Sistem Informasi Triguna Dharma (JURSI TGD), vol. 4, no. 4, pp. 778–785, Jul. 2025.
J. Tayman and D. Swanson, “On the validity of MAPE as a measure of population forecast accuracy,” Population Research and Policy Review, vol. 18, pp. 299–322, 1999, doi: 10.1023/a:1006166418051.
A. S. Panjaitan, M. R. Maretha, Hilmiah, and B. Mardhotillah, “Optimalisasi Penerapan Metode ARIMA dalam Mengestimasi Harga Emas di Negara Indonesia”, JESI, vol. 3, no. 2, pp. 136-146, Oct. 2023.
P. Visutsak, R. Wongpanti and P. Netisopakul, "FORECASTING CBOE OPENING VALUES: AN EFFECTIVE ARIMA APPROACH WITH TRANSFORMATION AND MODEL DIAGNOSTICS," Suranaree Journal of Science and Technology, vol. 31, no. 4, pp. 1-11, 2024.
D. Basak, S. Pal and D. C. Patranabis, "Support Vector Regression," Neural Information Processing - Letters and Reviews, vol. 11, no. 10, 2007.
I. R, Sudarmin, and Z. Rais, “Analisis Support Vector Regression (SVR) dengan Kernel Radial Basis Function (RBF) untuk Memprediksi Laju Inflasi di Surabaya,” VARIANSI: Journal of Statistics and Its Application on Teaching and Research, vol. 4, no. 1, pp. 30-28, 2022.
G. Van Houdt, C. Mosquera, and G. Nápoles, “A review on the long short-term memory model,” Artificial Intelligence Review, vol. 53, no. 8, May 2020, doi: https://doi.org/10.1007/s10462-020-09838-1.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Jurnal Sistem Informasi Triguna Dharma (JURSI TGD)
This work is licensed under a Creative Commons Attribution 4.0 International License.
