Carbon price forecasting with a novel hybrid ARIMA and least squares support vector machines methodology

Abstract

In general, due to inherently high complexity, carbon prices simultaneously contain linear and nonlinear patterns. Although the traditional autoregressive integrated moving average (ARIMA) model has been one of the most popular linear models in time series forecasting, the ARIMA model cannot capture nonlinear patterns. The least squares support vector machine (LSSVM), a novel neural network technique, has been successfully applied in solving nonlinear regression estimation problems. Therefore, we propose a novel hybrid methodology that exploits the unique strength of the ARIMA and LSSVM models in forecasting carbon prices. Additionally, particle swarm optimization (PSO) is used to find the optimal parameters of LSSVM in order to improve the prediction accuracy. For verification and testing, two main future carbon prices under the EU ETS were used to examine the forecasting ability of the proposed hybrid methodology. The empirical results obtained demonstrate the appeal of the proposed hybrid methodology for carbon price forecasting.