A Catboost-Driven Framework For Monthly Crude Oil Price Forecasting
Keywords:
Crude Oil Price Forecasting, CatBoost Regressor, Machine Learning, Time Series Forecasting, Feature Engineering, Gradient Boosting, Energy Analytics, Predictive Modeling, Artificial IntelligenceAbstract
Crude oil prices play a crucial role in the global economy, influencing energy markets, transportation costs, industrial production, and financial investments. Accurate forecasting of crude oil prices enables governments, policymakers, investors, and energy organizations to make informed strategic decisions under dynamic market conditions. This study presents a CatBoost-driven framework for forecasting monthly crude oil prices using historical market data collected from 1983 to 2025. The proposed framework incorporates comprehensive data preprocessing and feature engineering techniques, including lag variables, rolling mean, rolling standard deviation, seasonal encoding using sine and cosine transformations, and monthly price change indicators to effectively capture temporal dependencies and nonlinear market behavior. The CatBoost Regressor is employed due to its ability to model complex relationships while minimizing overfitting through ordered boosting. The performance of the proposed model is evaluated using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Coefficient of Determination (R² Score). Experimental results demonstrate that the proposed framework achieves accurate and reliable forecasting performance with strong generalization capability and computational efficiency. The findings indicate that the CatBoost-based approach provides an effective and scalable solution for monthly crude oil price forecasting and can serve as a valuable decision-support tool for stakeholders in the energy and financial sectors.
References
[1]. G. Wu and Y.-J. Zhang, “Does China factor matter? An econometric analysis of international crude oil prices,” Energy Policy, vol. 72, pp. 78–86, Sep. 2014.
[2]. H. Mohammadi and L. Su, “International evidence on crude oil price dynamics: Applications of ARIMA-GARCH models,” Energy Economics, vol. 32, no. 5, pp. 1001–1008, May 2010.
[3]. H. Xie, X. Zhang, and S. Wang, “The more the better: Forecasting oil price with decomposition-based vector autoregressive model,” International Journal of Energy Statistics, vol. 1, no. 1, pp. 45–53, Mar. 2013.
[4]. T. Yao and Y.-J. Zhang, “Forecasting crude oil prices with the Google Index,” Energy Procedia, vol. 105, pp. 3772–3776, May 2017.
[5]. T. Klein and T. Walther, “Oil price volatility forecast with mixture memory GARCH,” Energy Economics, vol. 58, pp. 46–58, Aug. 2016.
[6]. S. Bekiros, R. Gupta, and A. Paccagnini, “Oil price forecastability and economic uncertainty,” Economics Letters, vol. 132, pp. 125–128, Jul. 2015.
[7]. H. Chiroma, S. Abdulkareem, and T. Herawan, “Evolutionary neural network model for West Texas Intermediate crude oil price prediction,” Applied Energy, vol. 142, pp. 266–273, Mar. 2015.
[8]. J. Baruník and B. Malinská, “Forecasting the term structure of crude oil futures prices with neural networks,” Applied Energy, vol. 164, pp. 366–379, Feb. 2016.
[9]. L. Fan, S. Pan, Z. Li, and H. Li, “An ICA-based support vector regression scheme for forecasting crude oil prices,” Technological Forecasting and Social Change, vol. 112, pp. 245–253, Nov. 2016.
[10]. M. M. Mostafa and A. A. El-Masry, “Oil price forecasting using gene expression programming and artificial neural networks,” Economic Modelling, vol. 54, pp. 40–53, Apr. 2016.
[11]. S. Gao and Y. Lei, “A new approach for crude oil price prediction based on stream learning,” Geoscience Frontiers, vol. 8, no. 1, pp. 183–187, Jan. 2017.
[12]. S. Peng, R. Chen, B. Yu, M. Xiang, X. Lin, and E. Liu, “Daily natural gas load forecasting based on the combination of long short-term memory, local mean decomposition, and wavelet threshold denoising algorithm,” Journal of Natural Gas Science and Engineering, vol. 95, Art. no. 104175, Nov. 2021.
[13]. Y. Lu, Y. Bai, L. Tang, W. Wan, and Y. Ma, “Secondary factor-induced wind speed time-series prediction using self-adaptive interval type-2 fuzzy sets with error correction,” SSRN Electronic Journal, 2021.
[14]. R. Li, Y. Hu, J. Heng, and X. Chen, “A novel multiscale forecasting model for crude oil price time series,” Technological Forecasting and Social Change, vol. 173, Art. no. 121181, Dec. 2021.
[15]. [15] H. He, M. Sun, X. Li, and I. A. Mensah, “A novel crude oil price trend prediction method: Machine learning classification algorithm based on multi-modal data features,” Energy, vol. 244, Art. no. 122706, Apr. 2022.
[16]. M. D. Zainlabuddin and N. Sharma, “Security enhancement in data propagation for wireless network,” Revista GEINTEC – Gestão, Inovação e Tecnologias, vol. 11, no. 4, pp. 4110–4119, Aug. 2021.
[17]. M. S. Uddin and M. D. Zainlabuddin, “Secure video processing and watermark embedding using Shamir secret rule,” International Journal of Artificial Intelligence and Computer Electronics, vol. 2, no. 1, pp. 25–31, Mar. 2026.
[18]. Performance Analysis of Wireless Sensor Networks for Smart Monitoring Applications. (2016). International Journal of Humanities and Information Technology, 1(04), 10-29. https://doi.org/10.21590/ijhit.01.04.04
[19]. L.K.Suresh Kumar , Mohammed Abdul Bari , “Zero-Day Attack Detection In Multi-Tenant Cloud Environments Using Variational Autoencoders ,” International Journal of Applied Mathematics, ISSN: 1311-1728 (printed version); ISSN: 1314-8060 (on-line version)Volume 38 No. 3s, 2025.
[20]. Sannidhanam, A. H. (2020). Comparative Analysis of Cloud Computing Architectures for Enterprise Applications. SAMRIDDHI : A Journal of Physical Sciences, Engineering and Technology, 12(02), 169-180. https://doi.org/10.18090//samriddhi.v12i02.16
[21]. Event Streaming Architectures for High-Volume Transaction Processing. (2022). International Journal of Advance Industrial Engineering, 10(01), 1-8. https://doi.org/10.14741/
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Authors
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
