Forecasting China's inbound tourist arrivals using a state space model

Abstract

© Published under licence by IOP Publishing Ltd. The inbound tourism is one of the most important economic activities in China. Forecasting inbound demand is immensely helpful for policymakers and operators. The aim of this study is to evaluate the forecasting results of inbound tourist arrivals in China from six main tourist source markets: South Korea, Japan, the USA, Malaysia, Singapore and Canada, obtained from a state space model. The accuracy of forecasting results will be compared with the fixed linear regression, and ARIMA models, based on MAPE and RMSE. Empirical results suggest that all the variables have time varying character in six cases. And the income level has the most significant effect on tourist arrivals, followed by the substituted price in competitive countries. The price in China has the least impact on inbound tourist arrivals to China. And the accuracy of forecasting indicates that the state space approach performs better than the linear regression and ARIMA models for longer time frames.