“…It should be noted that most statistical approaches are based on probabilistic forecasts, and the distribution of forecast values is helpful for risk management (Cabrera and Schulz, 2017). On the other hand, machine learning techniques have attracted attention in recent years, such as support vector machine (SVM); (Chen et al, 2017;Jiang et al, 2018;Yang et al, 2019); neural networks (He, 2017;Guo et al, 2018b;Kong et al, 2018;Bedi and Toshniwal, 2019;Wang et al, 2019), gradient boosting (Zhang et al, 2019), and hybrids of multiple forecasting techniques (Miswan et al, 2016;Liu et al, 2017;de Oliveira and Cyrino Oliveira, 2018;Haq and Ni, 2019). These techniques capture complex nonlinear structures; therefore, high forecast accuracies are expected.…”