Peramalan Multivariate Time Series Harga Aspal Menggunakan Algoritma Gated Recurrent Unit: Multivariate Time Series Forecasting of Asphalt Prices Using the Gated Recurrent Unit Algorithm

Winaldi Putra Jaya; Puput Budi Wintoro; Trisya Septiana; Yessi Mulyani

doi:10.57152/malcom.v5i4.2198

Authors

Winaldi Putra Jaya Universitas Lampung
Puput Budi Wintoro Universitas Lampung
Trisya Septiana Universitas Lampung
Yessi Mulyani Universitas Lampung

DOI:

https://doi.org/10.57152/malcom.v5i4.2198

Keywords:

Forecasting, Gated Recurrent Unit, Harga Aspal, Multivariate Time Series

Abstract

Fluktuasi harga minyak global menimbulkan volatilitas tinggi pada harga aspal dan menciptakan ketidakpastian dalam perencanaan bisnis. Penelitian ini mengembangkan model multivariate forecasting harga aspal menggunakan algoritma Gated Recurrent Unit (GRU). Proses penelitian mengikuti tahapan Business Understanding, Data Understanding, Data Preprocessing, Data Modelling, Evaluation, dan Deployment. Data yang dianalisis mencakup harga aspal (kategori low dan high) serta harga minyak global (close) periode 2016–2023, dengan total 371 observasi. Hasil eksplorasi menunjukkan bahwa harga minyak menjadi prediktor dominan terhadap perubahan harga aspal. Evaluasi model memperlihatkan kinerja GRU yang sangat baik dengan nilai rata-rata MAE 6,2441, RMSE 8,2880, dan R² sebesar 96,05%, yang menandakan kemampuan model dalam mengenali pola deret waktu secara akurat. Namun demikian, keterbatasan penelitian ini terletak pada cakupan data yang bersumber dari satu perusahaan dengan rentang waktu terbatas, sehingga berpotensi menimbulkan bias representatif. Selain itu, model GRU cenderung sensitif terhadap parameter pelatihan dan ukuran windowing, yang dapat mempengaruhi stabilitas hasil pada data dengan pola musiman ekstrem. Dalam implementasi praktis, integrasi GRU ke dalam sistem bisnis juga memerlukan kapasitas komputasi dan pembaruan model berkala agar hasil prediksi tetap adaptif terhadap dinamika pasar global. Model akhir diimplementasikan dalam dashboard interaktif berbasis Power BI untuk mendukung visualisasi tren harga dan mempercepat pengambilan keputusan strategis

Downloads

Download data is not yet available.

References

S. Khan and H. Alghulaiakh, "ARIMA Model for Accurate Time Series Stocs Forecasting," International Journal of Advances Computer Science and Applications (IJACSA), vol. 11, no. 7, pp. 524-528, 2020.

S. Russell and P. Norvig, Artificial Intelegence A Modern Approach Third Edition, Upper Saddle River: Prentice Hall, 2010.

M. I. Jordan and T. M. Mitchell, "Machine Learning: Trends, Perspectives, and Prospects," Science (AAAS), vol. 349, no. 6245, pp. 255-269, 2015.

R. P. Masini, M. C. Medeiros and E. F. Mendes, "Machine Learning Advances for Time Series Forecasting," Journal of Economic Surveys, vol. 37, no. 1, pp. 76-111, 2023.

I. Goodfellow, Y. Bengio and A. Courville, Deep Learning, Cambridge: The Mit Press, 2017.

K. Gajamannage, D. I. Jayathilake, Y. Park and E. M. Bollt, "Recurrent neural networks for dynamincal systems: Applications to ordinary differential equations, collective motion, and hydrological modelling," Chaos, vol. 33, no. 1, pp. 1-18, 2023.

Furizal, A. B. Fawait, H. Maghfiroh, A. Ma'arif, A. A. Firdaus and I. Suwarno, "Long Short-Term Memory vs Gated Recurrent Unit: A Literature Review on the Performance of Deep Learning Methods in Temperature Time Series Forecasting," International Journal of Robotics and Control Systems, vol. 4, no. 3, pp. 1506-1526, 2024.

S. Sukirman, Beton Aspal Campuran Panas, Bandung: Institut Teknologi Bandung, 2016.

D. L. Hoffman and R. H. Rasche, "Assessing Forecast Performance In A Cointegrated System," Journal of Applied Ecomentrics, vol. 11, no. 5, pp. 495-517, 1996.

B. Abraham and J. Ledolter, "Forecasting Functions Implied by Autoregressive Integrated Moving Average Models and Other Related Forecast Procedures," International Statistical Review, vol. 54, no. 1, pp. 51- 66, 1986.

W. K. Li, S. Ling and M. McAleer, "Recent Theoretical Result For Time Series Models With Garch Errors," Journal of Economic Surveys, vol. 16, no. 3, pp. 245-269, 2002.

S. A. Oke, "A Literature Review on Artificial Intelligence," International Journal of Information and Management Science, vol. 19, no. 4, pp. 535-570, 2008.

S. S. Shwartz, Understanding Machine Learning From Theory to Algorithms, New York: Cambridge University Press, 2014.

I. H. Sarker, "Machine Learning: Algorithms, Real-World Applicatations and Resarch Directions," SN Computer Science, vol. 2, no. 3, p. 160, 2021.

Y. LeCun, Y. Bengio and G. Hinton, "Deep Learning," Nature, vol. 521, no. 7553, pp. 436-444, 2015.

S. Haykin, Neural Network and Learning Machines Third Edition, Upper Saddle River: Prentice Hall, 2009.

X. Glorot and Y. Bengio, "Understanding The Difficulty of Training Deep Feedforward Neural Network," Journal of Machine Learning Research, vol. 9, pp. 249-256, 2010.

A. M. Schafer and H.-G. Zimmermann, "Recurrent Neural Networks are Universal Approximators," International Journal of Neural Systems, vol. 17, no. 4, pp. 253-263, 2007.

W. H. Greene, Fifth Edition Econometric Analysis, Upper Saddle River: Prentice Hall, 2002.

A. A. Linkon, I. R. Noman, M. R. Islam, J. C. Bortty, K. K. Bishnu, A. Islam, R. Hasan and M. Abdullah, "Evalution of Feature Transformation and Machine Learning Models on Early Detection of Diabetes Melitus," IEEE Access, vol. 12, pp. 165425-165440, 2024.

E. Haque, S. Tabassum and E. Hossain, "A Comparative Analysis of Deep Neural Networks for Hourly Temparature Foreceasting," IEEE Access, vol. 9, pp. 160646-160660, 2021.

D. T. Larose and C. D. Larose, Data Mining and Predictive Analystics, Hoboken: John Wiley & Sons, Inc., 2015.

M. S. Brown, Data Mining For Dummies, Hoboken: John Wiley & Sons, Inc., 2014.

D. S. Shafer and Z. Zhiyi, Beginning Statistics, Washington, D.C: 2011, 2011.

P. Y. Chen and P. M. Popovich, Correlation Parametic and Nonparametic Measures`, Thousand Oaks: Sage Publications, 2002.

F. Chollet, Deep Learning with Python, Shelter Islan: Manning Publications Co., 2018.

D. Chicco, M. J. Warrens and G. Jurman, "The Coefficient of Determination R-Squared is More Informative than SMAPE, MAE, MAPE, MSE, and RMSE in Regression Analysis Evaluation," PeerJ Computer Science, vol. 7, pp. 1-24, 2021.

R. B. R. Putra and H. , "Multivariate Time Series Forecasting pada Penjualan Barang Retail dengan Recurrent Neural Network," Jurnal Inovtek Polbeng - Seri Informatika, vol. 7, no. 1, pp. 71-82, 2022.

O. Anacleto, C. Queen and C. J. Albers, "Multivariate Forecasting of Road Traffic Flows in the Presence of Heteroscedasticity and Measurement Errors," Journal of the Royal Statistical Society Series C: Applied Statistics, vol. 63, no. 2, pp. 251-270, 2013.

P. R. Vlachas, W. Byeon, Z. Y. Wan, T. P. Sapsis and P. Koumoutsakos, "Data-Driven Forecasting of High-Dimnesional Chaotic Systems with Long- Short Term Memory Networks," Proceedings of the Royal Society A: Mathematical, Physical and Engineering Science, vol. 474, no. 2213, 2018.

G. P. Zhang, "Time series forecasting using a hybrid ARIMA and neural network model," Neurocomputing, vol. 50, pp. 159-175, 2003.

H. Shi, M. Xu and R. Li, "Deep Learning for Household Load Forecasting - A Novel Pooling Deep RNN," IEEE Transactions on Smart Grids, vol. 9, no. 5, pp. 5271-5280, 2018.