Air passenger forecasting by using a hybrid seasonal decomposition and least squares support vector regression approach

In this study, a hybrid approach based on seasonal decomposition (SD) and least squares support vector regression (LSSVR) model is proposed for air passenger forecasting. In the formulation of the proposed hybrid approach, the air passenger time series are first decomposed into three components: trend-cycle component, seasonal factor and irregular component. Then the LSSVR model is used to predict the components independently and these prediction results of the components are combined as an aggregated output. Empirical analysis shows that the proposed hybrid approach is better than other benchmark models, indicating that it is a promising tool to predict complex time series with high volatility and irregularity.