This study employed artificial neural network (ANN), support vector regression and random forest regression approaches for forecasting. ANNs are a type of machine learning model that consists of three layers, which are connected by neurons that have weights and biases. Random forest (RF) is a collection of decision tree-based machine learning models, which are used for regression and classification. The decision trees are identified by varying the covariates during the training process and are selected based on the best performance.
