Management of Tourism Resources and Demand Based on Neural Networks

Accurate prediction for inbound tourism demand is important for development and implement of Chinese inbound tourism strategy. It has positive significance. BP neural network as a common traditional machine learning methods is widely used in travel demand forecasting model. However, BP neural network suffers from several drawbacks, such as over fitting, difficulties in setting parameters and local minima problem. Hence the performance of BP neural network is very unstable in practical applications. This paper combines an advanced machine learning paradigm named ensemble learning with BP neural network to build neural network ensemble for tourism demand prediction. The state-of-art methods for predictive modeling used in tourism research include traditional statistical methods, soft computing methods, and artificial intelligence methods. Note that artificial intelligence methods, which were introduced to tourism research in 1990s, have greatly improved the predictive accuracy of modeling methods. This study conducts tourism demand modeling of three important tourist source countries of US, Britain and Australia. The results show that, neural network ensemble significantly improves the predictive accuracy over traditional statistical methods and traditional machine learning methods including single BP neural network. Such method provides a better choice for more accurate predictive modeling for tourism demand of China.