Visitors quantity is regarded as the important economic indicator of weighing a country or regional tourism economic development, how to correctly and effectively predict regional visitors quantity according to relevant influencing factors is essential to the development of tourism economy. This paper firstly introduce several common prediction method principle, then according to the characteristics of visitors quantity, build combined prediction model based on neural network, Use fitting value got in front of three kinds of prediction method as input samples, use the corresponding to the actual value as the output samples, training the network learning, Amplify neural network to identify the weight of every prediction method, reduce subjective factors in the prediction process. The result shows that the method is feasible and effective, the results is accurate.
