Forecasting Of Tourism Demand Based On Multiple Models In Fujian Province

Tourism demand modeling and forecasting have become nowadays a hot topic in tourism research. So far, many investigators have dedicated to the relevant studies and a lot of models and methods have been used. Many researchers have claimed that their own model can obtained accurate predicting results. However, if their predictions are compared with the actual developing data, it can be found that a considerable part of the research results are not optimistic. Which model can eventually suitable for tourism demand forecasting? Many researchers fall into a heavy fog.Based on statistical data available in various official yearbooks, five forecasting models such as correlation and regression analysis model, dynamic trend forecast model, GM (1,1) model, grey metabolizing model and GM-Markov combination model were constructed and applied to predict the domestic and inbound tourism (including three major sources of tourists) demand in Fujian Province respectively. Through the test of predicting results, it was found that the correlation and regression prediction model was not suitable for tourism demand forecast in Fujian Province. The grey metabolizing model could slightly reduce the forecasting errors in comparison with the GM (1,1) model. The best favorable predicting model was GM-Markov combination model. The dynamic trend forecast model and grey series models were suitable for both domestic and whole inbound tourism demand forecasting, but not all these models were appropriate for the prediction of inbound foreign tourists and tourists from Taiwan, Hong Kong and Macao.The analysis demonstrates that there exists not universal suitable forecasting model in the field of tourism demand forecasting. Each model has its own performance characteristics and the scope of application. It will show different prediction accuracy if the selected data sequences or analyzing objects are different. Therefore, building different forecasting models for different tourism demands is the key to solve the problem.