{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T16:25:17Z","timestamp":1782923117615,"version":"3.54.5"},"reference-count":58,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2022,7,29]],"date-time":"2022-07-29T00:00:00Z","timestamp":1659052800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Axioms"],"abstract":"<jats:p>Financial institutions, investors, central banks and relevant corporations need an efficient and reliable forecasting approach for determining the future of crude oil price in an effort to reach optimal decisions under market volatility. This paper presents an innovative research framework for precisely predicting crude oil price movements and interpreting the predictions. First, it compares six advanced machine learning (ML) models, including two state-of-the-art methods: extreme gradient boosting (XGB) and the light gradient boosting machine (LGBM). Second, it selects novel data, including user search big data, digital currencies and data on the COVID-19 epidemic. The empirical results suggest that LGBM outperforms other alternative ML models. Finally, it proposes an interpretable framework for facilitating decision making to interpret the prediction results of complex ML models and for verifying the importance of various features affecting crude oil price. The results of this paper provide practical guidance for participants in the crude oil market.<\/jats:p>","DOI":"10.3390\/axioms11080374","type":"journal-article","created":{"date-parts":[[2022,7,31]],"date-time":"2022-07-31T21:49:02Z","timestamp":1659304142000},"page":"374","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["An Explainable Machine Learning Framework for Forecasting Crude Oil Price during the COVID-19 Pandemic"],"prefix":"10.3390","volume":"11","author":[{"given":"Xinran","family":"Gao","sequence":"first","affiliation":[{"name":"School of Statistics and Mathematics, Zhejiang Gongshang University, Hangzhou 310018, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junwei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Business, Guilin University of Electronic Technology, Guilin 541214, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liping","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Management, University of Science and Technology of China, Hefei 230026, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,7,29]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Kumeka, T.T., Uzoma-Nwosu, D.C., and David-Wayas, M.O. (2022). The effects of COVID-19 on the interrelationship among oil price, stock prices and exchange rates in selected oil exporting economies. Resour. Policy, 77.","DOI":"10.1016\/j.resourpol.2022.102744"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"775","DOI":"10.1016\/j.jclepro.2019.04.393","article-title":"A decomposition\u2013integration model with dynamic fuzzy reconstruction for crude oil price prediction and the implications for sustainable development","volume":"229","author":"Chai","year":"2019","journal-title":"J. Clean. Prod."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"665","DOI":"10.1016\/j.ijforecast.2018.03.009","article-title":"Crude oil price forecasting based on internet concern using an extreme learning machine","volume":"34","author":"Wang","year":"2018","journal-title":"Int. J. Forecast."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Guliyev, H., and Mustafayev, E. (2022). Predicting the changes in the WTI crude oil price dynamics using machine learning models. Resour. Policy, 77.","DOI":"10.1016\/j.resourpol.2022.102664"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Shehabi, M. (2022). Modeling long-term impacts of the COVID-19 pandemic and oil price declines on Gulf oil economies. Econ. Model., 112.","DOI":"10.1016\/j.econmod.2022.105849"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Kaymak, \u00d6.\u00d6., and Kaymak, Y. (2022). Prediction of crude oil price in COVID-19 outbreak using real data. Chaos Solitons Fractals, 158.","DOI":"10.1016\/j.chaos.2022.111990"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Degiannakis, S., and Filis, G. (2022). Oil price volatility forecasts: What do investors need to know?. J. Int. Money Financ., 123.","DOI":"10.1016\/j.jimonfin.2021.102594"},{"key":"ref_8","first-page":"14","article-title":"The Performance of Hybrid ARIMA-GARCH Modeling and Forecasting Oil Price","volume":"8","author":"Dritsaki","year":"2018","journal-title":"Int. J. Energy Econ. Policy"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.iref.2019.10.014","article-title":"Forecasting oil price volatility using high-frequency data: New evidence","volume":"66","author":"Chen","year":"2020","journal-title":"Int. Rev. Econ. Financ."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Duan, H., and Liu, Y. (2021). Research on a grey prediction model based on energy prices and its applications. Comput. Ind. Eng., 162.","DOI":"10.1016\/j.cie.2021.107729"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"584","DOI":"10.1080\/07474938.2021.1889202","article-title":"Forecasting crude oil price intervals and return volatility via autoregressive conditional interval models","volume":"40","author":"He","year":"2021","journal-title":"Econom. Rev."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"338","DOI":"10.1080\/07350015.2014.949342","article-title":"Forecasting the real price of oil in a changing world: A forecast combination approach","volume":"33","author":"Baumeister","year":"2015","journal-title":"J. Bus. Econ. Stat."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1016\/j.eneco.2017.05.023","article-title":"A deep learning ensemble approach for crude oil price forecasting","volume":"66","author":"Zhao","year":"2017","journal-title":"Energy Econ."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Zolfaghari, M., Ghoddusi, H., and Faghihian, F. (2020). Volatility spillovers for energy prices: A diagonal BEKK approach. Energy Econ., 92.","DOI":"10.1016\/j.eneco.2020.104965"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Gkillas, K., Gupta, R., and Pierdzioch, C. (2020). Forecasting realized oil-price volatility: The role of financial stress and asymmetric loss. J. Int. Money Financ., 104.","DOI":"10.1016\/j.jimonfin.2020.102137"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Mokni, K., Hammoudeh, S., Ajmi, A.N., and Youssef, M. (2020). Does economic policy uncertainty drive the dynamic connectedness between oil price shocks and gold price?. Resour. Policy, 69.","DOI":"10.1016\/j.resourpol.2020.101819"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Morema, K., and Bonga-Bonga, L. (2020). The impact of oil and gold price fluctuations on the South African equity market: Volatility spillovers and financial policy implications. Resour. Policy, 68.","DOI":"10.1016\/j.resourpol.2020.101740"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1007\/s40565-018-0395-3","article-title":"Month ahead average daily electricity price profile forecasting based on a hybrid nonlinear regression and SVM model: An ERCOT case study","volume":"6","author":"Ma","year":"2018","journal-title":"J. Mod. Power Syst. Clean Energy"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"274","DOI":"10.1016\/j.eneco.2018.10.015","article-title":"Interval decomposition ensemble approach for crude oil price forecasting","volume":"76","author":"Sun","year":"2018","journal-title":"Energy Econ."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"649","DOI":"10.1016\/j.eneco.2015.02.018","article-title":"A novel hybrid method for crude oil price forecasting","volume":"49","author":"Zhang","year":"2015","journal-title":"Energy Econ."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Jabeur, S.B., Khalfaoui, R., and Arfi, W.B. (2021). The effect of green energy, global environmental indexes, and stock markets in predicting oil price crashes: Evidence from explainable machine learning. J. Environ. Manag., 298.","DOI":"10.1016\/j.jenvman.2021.113511"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1504\/IJOGCT.2019.098458","article-title":"Oil price prediction using a supervised neural network","volume":"20","author":"Khashman","year":"2019","journal-title":"Int. J. Oil Gas Coal Technol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1142\/S0219622015400015","article-title":"A novel CEEMD-based EELM ensemble learning paradigm for crude oil price forecasting","volume":"14","author":"Tang","year":"2015","journal-title":"Int. J. Inf. Technol. Decis. Mak."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Wu, Q., and Lin, H. (2019). Daily urban air quality index forecasting based on variational mode decomposition, sample entropy and LSTM neural network. Sustain. Cities Soc., 50.","DOI":"10.1016\/j.scs.2019.101657"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Saghi, F., and Jahangoshai Rezaee, M. (2021). Integrating Wavelet Decomposition and Fuzzy Transformation for Improving the Accuracy of Forecasting Crude Oil Price. Comput. Econ., 1\u201333.","DOI":"10.1007\/s10614-021-10219-1"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Jabeur, S.B., Mefteh-Wali, S., and Viviani, J.L. (2021). Forecasting gold price with the XGB algorithm and SHAP interaction values. Ann. Oper. Res., 1\u201321.","DOI":"10.1007\/s10479-021-04187-w"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1586","DOI":"10.1109\/TKDE.2019.2912815","article-title":"Reliable accuracy estimates from k-fold cross validation","volume":"32","author":"Wong","year":"2019","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Naeem, M.A., Hasan, M., Arif, M., Balli, F., and Shahzad, S.J.H. (2020). Time and frequency domain quantile coherence of emerging stock markets with gold and oil price. Phys. A Stat. Mech. Its Appl., 553.","DOI":"10.1016\/j.physa.2020.124235"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Das, D., Le Roux, C.L., Jana, R.K., and Dutta, A. (2020). Does Bitcoin hedge crude oil implied volatility and structural shocks? A comparison with gold, commodity and the US Dollar. Financ. Res. Lett., 36.","DOI":"10.1016\/j.frl.2019.101335"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Lin, B., and Su, T. (2020). Does oil price have similar effects on the exchange rates of BRICS?. Int. Rev. Financ. Anal., 69.","DOI":"10.1016\/j.irfa.2020.101461"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Lin, A., Shang, P., Feng, G., and Zhong, B. (2020). Application of empirical mode decomposition combined with k-nearest neighbors approach in financial time series forecasting. Fluct. Noise Lett., 11.","DOI":"10.1142\/S0219477512500186"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1016\/j.physa.2017.02.072","article-title":"Multidimensional k-nearest neighbor model based on EEMD for financial time series forecasting","volume":"477","author":"Zhang","year":"2017","journal-title":"Phys. A Stat. Mech. Its Appl."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1690","DOI":"10.1073\/pnas.1800256115","article-title":"Classification and interaction in random forests","volume":"115","author":"Denisko","year":"2018","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1007\/s11269-020-02704-3","article-title":"Ensemble Boosting and Bagging Based Machine Learning Models for Groundwater Potential Prediction","volume":"35","author":"Mosavi","year":"2021","journal-title":"Water Resour. Manag."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/j.eswa.2014.07.040","article-title":"Predicting stock and stock price index movement using trend deterministic data preparation and machine learning techniques","volume":"42","author":"Patel","year":"2015","journal-title":"Expert Syst. Appl."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1016\/j.eswa.2017.04.006","article-title":"Machine learning models and bankruptcy prediction","volume":"83","author":"Barboza","year":"2017","journal-title":"Expert Syst. Appl."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"689","DOI":"10.1016\/j.ejor.2016.10.031","article-title":"Deep neural networks, gradient-boosted trees, random forests: Statistical arbitrage on the S&P 500","volume":"259","author":"Krauss","year":"2017","journal-title":"Eur. J. Oper. Res."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). XGB: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, NY, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Zheng, H., Yuan, J., and Chen, L. (2017). Short-term load forecasting using EMD-LSTM neural networks with a XGB algorithm for feature importance evaluation. Energies, 10.","DOI":"10.3390\/en10081168"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1016\/j.enconman.2018.02.087","article-title":"Comparison of Support Vector Machine and Extreme Gradient Boosting for predicting daily global solar radiation using temperature and precipitation in humid subtropical climates: A case study in China","volume":"164","author":"Fan","year":"2018","journal-title":"Energy Convers. Manag."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Parsa, A.B., Movahedi, A., Taghipour, H., Derrible, S., and Mohammadian, A.K. (2020). Toward safer highways, application of XGB and SHAP for real-time accident detection and feature analysis. Accid. Anal. Prev., 136.","DOI":"10.1016\/j.aap.2019.105405"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1016\/j.eswa.2017.02.017","article-title":"A boosted decision tree approach using Bayesian hyper-parameter optimization for credit scoring","volume":"78","author":"Xia","year":"2017","journal-title":"Expert Syst. Appl."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Busari, G.A., and Lim, D.H. (2021). Crude oil price prediction: A comparison between AdaBoost-LSTM and AdaBoost-GRU for improving forecasting performance. Comput. Chem. Eng., 155.","DOI":"10.1016\/j.compchemeng.2021.107513"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1016\/j.ijforecast.2021.06.006","article-title":"Crude oil price forecasting incorporating news text","volume":"38","author":"Bai","year":"2022","journal-title":"Int. J. Forecast."},{"key":"ref_45","unstructured":"Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T.-Y. (2017, January 4\u20139). LGBM: A highly efficient gradient boosting decision tree. Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Wen, X., Xie, Y., Wu, L., and Jiang, L. (2021). Quantifying and comparing the effects of key risk factors on various types of roadway segment crashes with LGBM and SHAP. Accid. Anal. Prev., 159.","DOI":"10.1016\/j.aap.2021.106261"},{"key":"ref_47","unstructured":"Dorogush, A.V., Ershov, V., and Gulin, A. (2018). CatBoost: Gradient boosting with categorical features support. arXiv."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40537-020-00369-8","article-title":"CatBoost for big data: An interdisciplinary review","volume":"7","author":"Hancock","year":"2020","journal-title":"J. Big Data"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1016\/j.ijpe.2018.05.019","article-title":"Another look at forecast selection and combination: Evidence from forecast pooling","volume":"209","author":"Kourentzes","year":"2019","journal-title":"Int. J. Prod. Econ."},{"key":"ref_50","unstructured":"Lundberg, S.M., and Lee, S.I. (2017, January 4\u20139). A unified approach to interpreting model predictions. Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat. Mach. Intell."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Guo, H., Zhuang, X., Chen, P., Alajlan, N., and Rabczuk, T. (2022). Stochastic deep collocation method based on neural architecture search and transfer learning for heterogeneous porous media. Eng. Comput., 1\u201326.","DOI":"10.1007\/s00366-021-01586-2"},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Guo, H., Zhuang, X., Chen, P., Alajlan, N., and Rabczuk, T. (2022). Analysis of three-dimensional potential problems in non-homogeneous media with physics-informed deep collocation method using material transfer learning and sensitivity analysis. Eng. Comput., 1\u201322.","DOI":"10.1007\/s00366-022-01633-6"},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1016\/j.eneco.2016.02.001","article-title":"Does the S&P500 index lead the crude oil dynamics? A complexity-based approach","volume":"56","author":"Kyrtsou","year":"2016","journal-title":"Energy Econ."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"6076","DOI":"10.1080\/00036846.2019.1645289","article-title":"Safe havens in the face of Presidential election uncertainty: A comparison between Bitcoin, oil and precious metals","volume":"51","author":"Bouoiyour","year":"2019","journal-title":"Appl. Econ."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"787","DOI":"10.1016\/j.eneco.2018.07.007","article-title":"Is Bitcoin a hedge, a safe haven or a diversifier for oil price movements? A comparison with gold","volume":"74","author":"Selmi","year":"2018","journal-title":"Energy Econ."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1111\/infi.12384","article-title":"Identifying oil price shocks and their consequences: The role of expectations in the crude oil market","volume":"24","author":"Fueki","year":"2021","journal-title":"Int. Financ."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"485","DOI":"10.1016\/j.eneco.2014.05.015","article-title":"Effect of inventory announcements on crude oil price volatility","volume":"46","author":"Bu","year":"2014","journal-title":"Energy Econ."}],"container-title":["Axioms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-1680\/11\/8\/374\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T23:59:01Z","timestamp":1760140741000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-1680\/11\/8\/374"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,29]]},"references-count":58,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2022,8]]}},"alternative-id":["axioms11080374"],"URL":"https:\/\/doi.org\/10.3390\/axioms11080374","relation":{},"ISSN":["2075-1680"],"issn-type":[{"value":"2075-1680","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,29]]}}}