Machine learning and oil price point and density forecasting

• Published in: Energy economics 2021-10, Vol.102, p.105494, Article 105494
• Main Authors: Costa, Alexandre Bonnet R., Ferreira, Pedro Cavalcanti G., Gaglianone, Wagner P., Guillén, Osmani Teixeira C., Issler, João Victor, Lin, Yihao
• Format: Article
• Language: English
• Subjects: Big Data; Commodity prices; Density; Econometrics; Energy economics; Forecasting; Learning algorithms; Machine learning; Macroeconomics; Mathematical models; Oil; Petroleum; Prices; Pricing; Random walk; Regression analysis; Regularization; Statistical analysis; Trees
• ISSN: 0140-9883; 1873-6181
• DOI: 10.1016/j.eneco.2021.105494

The purpose of this paper is to explore machine learning techniques to forecast the oil price. In the era of big data, we investigate whether new automated tools can improve over traditional approaches in terms of forecast accuracy. Oil price point and density forecasts are built from 23 methods, including regression trees (random forest, quantile regression forest, xgboost), regularization procedures (elastic net, lasso, ridge), standard econometric models and forecast combinations, besides the structural factor model of Schwartz and Smith (2000). The database contains 315 macroeconomic and financial variables, used to build high-dimensional models. To evaluate the predictive power of each method, an extensive pseudo out-of-sample forecasting exercise is built, in monthly and quarterly frequencies, with horizons from one month up to five years. Overall, the results indicate a good performance of the machine learning methods in the short-run. Up to six months, lasso-based models, oil future prices, VECM and the Schwartz–Smith model provide the best forecasts. At longer horizons, forecast combinations also become relevant. In several cases, the accuracy gains in respect to the random walk forecast are statistically significant and reach two-digit figures, in percentage terms, using the R2 out-of-sample statistic; an expressive achievement compared to the previous literature. •This paper studies several machine learning techniques to forecast the oil prices.•Random forest, xgboost, lasso, ridge, elastic net, factor models, among others.•Our monthly and quarterly data cover 315 variables from 1991 to 2020.•Automated tools can improve the oil price forecast accuracy over usual approaches.•Many methods beat the random walk: R2 out of sample can reach 42% one month ahead.