Introducing the Synergy Based Approach for Forecasting the Crude Oil Prices with Traditional and Machine Learning Econometric Models

Year 2026, Volume: 17 Issue: 2, 18 - 33, 23.02.2026

Arslan Munir Turk , Saud Ahmed Khan , Muhammad Aamir , Zahanat Hussain

https://doi.org/10.33818/ier.1702860

https://izlik.org/JA37NW77TD

Abstract

Crude oil plays a pivotal role in the global economy, influencing inflation, trade
balances, and energy security. Accurate forecasting of crude oil prices is therefore essential for
policymakers and market participants. This study proposes a hybrid forecasting framework that
synergizes conventional econometric methods with machine learning (ML) techniques. . First, the
time series is decomposed using Ensemble Empirical Mode Decomposition (EEMD) to isolate
intrinsic mode functions (IMFs). These components are then classified into deterministic and
stochastic elements via spectral analysis. Second, traditional models such as ARIMA and GARCH
are applied to the relevant IMFs, while advanced ML models (LSTM and XGBoost) are fitted to
both original and residual series. Finally, a synergy model combines econometric and ML outputs,
with Bayesian optimization applied for hyperparameter tuning. . Model performance is assessed
using key error metrics such as Mean Absolute Error (MAE), Root Mean Squared Error (RMSE),
and Mean Absolute Percentage Error (MAPE). The findings suggest that hybrid models integrating
conventional econometric methods with machine learning approaches, optimized through
Bayesian techniques, achieve superior forecasting accuracy compared to standalone models.
Additionally, the Diebold-Mariano (DM) test confirms that these synergy-based models offer the
most reliable predictions for crude oil prices.

Keywords

EEMD , Spectral Analysis , ARIMA , LSTM , XGBOOST , Hybrid Econometric Models

Project Number

1

References

• Assaad, M. , R. Boné and H. Cardot (2008). "A New Boosting Algorithm for Improved Time-Series Forecasting with Recurrent Neural Networks." Information Fusion 9(1):41-55.
• Bergstra, J. S., R. Bardenet, Y. Bengio and B. Kégl (2011). "Algorithms for Hyper-Parameter Optimization." Advances in Neural Information Processing Systems 24.
• Box, G. E, G. M. Jenkins, G. C. Reinsel and G. M. Ljung (2015) "Time Series Analysis: Forecasting and Control 5th Edition." Journal of Time Series Analysis, 712.
• Cai, X. , D. Li , J. Zhang and Z. Wu (2025) "MA-EMD: Aligned Empirical Decomposition for Multivariate Time-series Forecasting." Expert Systems with Applications 267. Eşidir , K. A. , Y. E. Gur and V. Yoğunlu (n.d). "Estimating Monthly New Car Sales in Turkey with Artificial Neural Networks (ANN) and ARIMA Models." Pamukkale University Journal of Business Research 9(2):260-277. Eşidir, K. A. and Y. E. Gur. (2023) "Turkish Plastic Industry Import Estimate With Artificial Neural Networks." Akademik Hassasiyetler 10(23):91-114. Eşidir, K. A. , Y. E. Gür , V. Yogunlu and M. Çubuk (2022) "Estimating Monthly New Car Sales in Turkey with Artificial Neural Networks (ANN) and ARIMA Models." Üniversitesi İşletme Araştırmaları Dergisi 9(2):260-277.
• Fernández, F G and J. E. Sicre (2008) "On the Use of Empirical Mode Decomposition for Detecting Deterministic Dynamics." Physica D: Nonlinear Phenomena 237(5):685-701.
• Firoozabadi, S. S. , M. Ansari and F. Vasheghanifarahani (2024). "Crude Oil Trend Prediction During COVID-19: Machine Learning with Randomized Search and Bayesian Optimization." European Journal of Business and Management Research 9(3):6-13.
• Frazier, P. I. (2018). "A Tutorial on Bayesian Optimization." arXiv preprint arXiv 930. Golyandina, N. and A. Korobeynikov (2014). "Basic Singular Spectrum Analysis and forecasting with R." Computational Statistics & Data Analysis 71:934-954. Greff, K. , S. van Steenkiste and J. Schmidh. (2012). "On the Binding Problem in Artificial Neural Networks." arXiv preprint arXiv 208.
• Guo , Y. , J. Si, Y. Wang, F. Hanif, S. Li, M. Wu, M. Xu and J. Mi (2025). "Ensemble-Empirical-Mode-Decomposition (EEMD) on SWH Prediction: The Effect of Decomposed IMFs, Continuous Prediction Duration, and Data-driven Models." Ocean Engineering 324. Harvey, A. C. and P. H. J. Todd (2012). "Forecasting Economic Time Series with Structural and Box-Jenkins Models: A Case Study." Journal of Business & Economic Statistics 299-307.
• Hochreiter, S. and J. Schmidhuber (1997). "Long Short-Term Memory." Neural computation 9(8):1735-1780.
• Huang, N. E and Z. Wu (2007). "A Review on Hilbert-Huang Transform: Method and Its Applications To Geophysical Studies." Reviews of Geophysics 1-23.
• Hyndman, R.J. and A.B. Koehler (2006). "Another Look at Measures of Forecast Accuracy." International Journal of Forecasting 22(4):679–688.
• Hyndman, R.J., and G. Athanasopoulos (2018). Forecasting: Principles and Practice. OTEXTS.
• Kourentzes, N. , D. K. Barrow and S. F. Crone (2014). "Neural Network Ensemble Operators for Time Series Forecasting." Expert Systems with Applications 4235-4244. Lipton, Z. C. (2018). "The Mythos of Model Interpretability: In Machine Learning, The Concept of Interpretability is Both Important and Slippery." Queue 31-57.
• Makridakis, S. , E. Spiliotis and V. Assimakopoulos (2018). "Statistical and Machine Learning Forecasting methods: Concerns and Ways Forward." PloS one 13(03). Makridakis, S., E. Spiliotis and V. Assimakopoulos (2018). "Statistical and Machine Learning forecasting methods: Concerns and ways forward." PLOS ONE 13(3):e0194889.
• Malakouti, S. M., F. Karimi, H. Abdollahi, M. B. Menhaj, A. A. Suratgar and M. H. Moradi (2024). "Advanced Techniques for Wind Energy Production Forecasting: Leveraging Multi-layer Perceptron+ Bayesian Optimization, Ensemble Learning, and CNN-LSTM Models." Case Studies in Chemical and Environmental Engineering 10:100881.
• Mullainathan, S. and J. Spiess (2017). "Machine Learning: An Applied Econometric Approach." Journal of Economic Perspectives 31:87-107. Nasir, J. , M. Aamir, Z. Ul Haq, S. Khan, M. Y. Amin and M. Naeem (2023). "A New Approach for Forecasting Crude Oil Prices based on Stochastic and Deterministic Influences of LMD Using ARIMA and LSTM Models." IEEE 14322-14339.
• Niu, Z. , G. Zhong and H. Yu (2021). "A Review on the Attention Mechanism of Deep Learning." Neurocomputing 48-62. Olaniyan, J., D. Olaniyan, I. C. Obagbuwa , B. M. Esiefarienrhe, A. A. Adebiyi and O. P. Bernard (2024). "Intelligent Financial Forecasting with Granger Causality and Correlation Analysis Using Bayesian Optimization and Long Short-Term Memory." Electronics 13(22):4408.
• Özer, Ö. and W. Wei (2006). "Strategic Commitments for an Optimal Capacity Decision under Asymmetric Forecast Information." Management Science 1238-1257.
• Panagiotelis, A., P. Gamakumara, G. Athanasopoulos and R. J. Hyndman (2023). "Probabilistic Forecast Reconciliation: Properties, Evaluation and Score Optimisation." European Journal of Operational Research 306(02):693-704.
• Roushangar, K. and F. Alizadeh (2018). "Entropy-based Analysis and Regionalization of Annual Precipitation Variation in Iran During 1960–2010 Using Ensemble Empirical Mode Decomposition." Journal of Hydroinformatics 20 (2):468-485. Shafiq, M. S., T A Cheema, A A Khawaja and R k. (2019). "IMF Selection Using Energy and Dominant Frequency Features for Improved EEMD-based Signal Classification,” IEEE Access." 7: 45185-45197.
• Shahriari, B., K. Swersky, Z. Wang, R. P Adams and N. de Freitas (n.d). "Taking the Human Out of the Loop: A Review of Bayesian Optimization." Proceedings of the IEEE 104(1):148-175.
• Siami-Namini, S. , N. Tavakoli and A. S. Nami (2018). "A Comparison of ARIMA and LSTM in Forecasting Time Series." 17th IEEE International Conference on Machine learning and Applications (ICMLA). IEEE. 1394-1401.
• Snoek, J., H. Larochelle and R. P Adams (2012). "Practical Bayesian Optimization of Machine Learning Algorithms." Advances in Neural Information Processing Systems 25.
• Stock, J. H and M.W. Watson (2015). Introduction to Econometrics (3rd Updated Edition). https://swh.princeton.edu/~mwatson/Stock- Watson_3u/Students/RTC/Stock_Watson_3U_AnswersToReviewTheConcepts.pdf.
• Torres, M.E., M.A. Colominas, G. Schlotthauer and P. Flandrin (2011). "A Complete Ensemble Empirical Mode Decomposition with Adaptive Noise." IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 4144-4147.
• Umebayashi,K., M. Kobayashi and M.López-Benitez (2017) "Efficient Time Domain Deterministic-Stochastic Model of Spectrum Usage." IEEE Transactions on Wireless Communications 17(3):1518-1527.
• Wu , Z. and N. E Huang (2009). "Ensemble Empirical Mode Decomposition: A Noise-Assisted Data Analysis Method." Advances in Adaptive Data Analysis 01:1-41. Xiong, X. , X. Guo, P. Zeng, R. Zou and X. Wang (2022). "A Short-Term Wind Power Forecast Method via XGBoost Hyper-Parameters Optimization." Frontiers in Energy Research 155.
• Zhang, G Peter (2003). "Time Series Forecasting Using a Hybrid ARIMA and Neural Network Model." Neurocomputing 50:159-175.
• Zhao, H. , Y. Wang, X. Li, P. Guo and H. Lin (2023). "Prediction of Maximum Tunnel Uplift Caused by Overlying Excavation Using XGBoost Algorithm with Bayesian Optimization." Applied Sciences 13 (17): 9726.