A Comparative Study of Artificial Neural Network (ANN) and Support Vector Regression (SVR) on Forecasting: A Review

Abstract

Forecasting outcomes of the any systems is required for the good understanding and optimal management of the fluxes occurring in system operations. Many machine learning approaches are used to predict the output of the systems and generate forecasting models. The aim of this paper is to give the overview of a lot of describes forecasting methodologies that used Artificial Neural Network (ANN) and Support Vector Regression (SVR) under diversity of the dataset and understanding the performance of each method. To improve the prediction performance the authors proposed depending on some performance indicators as The Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and coefficient of determination R².