A paired neural network model for tourist arrival forecasting

Tourist arrival and tourist demand forecasting are a crucial issue in tourism economy and the community economic development as well. Tourist demand forecasting has attracted much attention from tourism academics as well as industries. In recent year, it attracts increasing attention in the computational literature as advances in machine learning method allow us to construct models that significantly improve the precision of tourism prediction. In this paper, we draw upon both strands of the literature and propose a novel paired neural network model. The tourist arrival data is decomposed by two low-pass filters into long-term trend and short-term seasonal components, which are then modelled by a pair of autoregressive neural network models as a parallel structure. The proposed model is evaluated by the tourist arrival data to United States from twelve source markets. The empirical studies show that our proposed paired neural network model outperforming the selected benchmark model across all error measures and over different horizons.