PREDIKSI PRODUKSI MINYAK MENTAH DI AMERIKA SERIKAT MENGGUNAKAN REGRESI POLINOMIAL
DOI:
https://doi.org/10.53026/prosidingsntem.v5i1.701Keywords:
polynomial regression, forecasting, crude oil production, model selection, time seriesAbstract
Prediksi produksi minyak mentah merupakan aspek kritis dalam perencanaan energi nasional. Penelitian ini mengembangkan dan membandingkan 10 model regresi polinomial (derajat 1-10) untuk memprediksi produksi minyak mentah Amerika Serikat lima tahun ke depan (2025-2030). Data historis dari Januari 1920 hingga Juli 2025 (1.267 titik data) digunakan dengan chronological data splitting (80:20) untuk validasi model realistis. Evaluasi sistematis menggunakan RMSE, MAPE, dan R² menunjukkan model polinomial derajat 5 optimal dengan Test R²=0,307, Test RMSE=2.519,25, dan Test MAPE=20,00%, dengan overfitting gap terkontrol. Model ini memprediksi pertumbuhan produksi 53,04% (dari 11.861 menjadi 18.146 ribu barel/hari) selama lima tahun. Regresi polinomial derajat optimal memberikan keseimbangan baik antara akurasi training dan generalisasi testing, bisa digunakan untuk peramalan tren jangka panjang energi mineral. Namun, prediksi bersifat ekstrapolatif tanpa faktor fundamental (harga, kebijakan, dan faktor lainnya) yang dapat mengubah trajectory. Model dapat diintegrasikan dengan analisis fundamental untuk perencanaan infrastruktur energi yang lebih robust.
References
International Energy Agency, "World Energy Outlook 2023," IEA, Paris, 2023. [Online]. Available: https://www.iea.org/reports/world-energy-outlook-2023
U.S. Energy Information Administration, "Annual Energy Outlook 2023," EIA, 2023. [Online]. Available: https://www.eia.gov/outlooks/aeo/
T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning, 2nd ed. New York: Springer, 2017. [Online]. Available: https://hastie.su.domains/ElemStatLearn/
C. M. Bishop, Pattern Recognition and Machine Learning. New York: Springer, 2006. [Online]. Available: https://www.microsoft.com/en-us/research/uploads/prod/2006/01/Bishop-Pattern-Recognition-and-Machine-Learning-2006.pdf
S. Raschka, "Model Evaluation, Model Selection, and Algorithm Selection in Machine Learning," arXiv preprint arXiv:1811.12808, 2018. [Online]. Available: https://arxiv.org/abs/1811.12808
M. Kuhn and K. Johnson, Applied Predictive Modeling. New York: Springer, 2013. [Online]. Available: https://link.springer.com/book/10.1007/978-1-4614-6849-3
U.S. Energy Information Administration, "U.S. Field Production of Crude Oil," 2024. [Online]. Available: https://www.eia.gov/dnav/pet/hist/LeafHandler.ashx?n=PET&s=MCRFPUS2&f=M
F. Pedregosa et al., "Scikit-learn: Machine Learning in Python," Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011. [Online]. Available: https://jmlr.org/papers/v12/pedregosa11a.html
A. Géron, Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 3rd ed. O'Reilly Media, 2022. [Online]. Available: https://github.com/ageron/handson-ml3
J. Brownlee, "A Gentle Introduction to Polynomial Regression," Machine Learning Mastery, 2020. [Online]. Available: https://machinelearningmastery.com/polynomial-features-transforms-formachine-learning/
S. Makridakis, E. Spiliotis, and V. Assimakopoulos, "Statistical and machine learning forecasting methods: Concerns and ways forward," PLOS ONE, vol. 13, no. 5, p. e0194889, 2018.
Downloads
Published
Conference Proceedings Volume
Section
License
Copyright (c) 2025 Prosiding Seminar Nasional Teknologi Energi dan Mineral
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
