Effective tourist volume forecasting supported by PCA and improved BPNN using Baidu index. (October 2018)

• Record Type: Journal Article
• Authors: Li, Shaowen; Chen, Tao; Wang, Lin; Ming, Chenghan
• Is Part Of: Tourism management. Volume 68(2018)
• Page Start: 116
• Page End: 126
• Publication Date: 2018-10
• Subjects: Tourist volume forecasting -- Principal component analysis -- Baidu index -- Back-propagation neural network -- Adaptive differential evolution; Tourism -- Periodicals; 338.4791
• DOI: 10.1016/j.tourman.2018.03.006
• Languages: English
• ISSNs: 0261-5177

Abstract

Abstract: The precise forecasting of tourist volume is a very challenging task. This paper aims to propose an effective model named PCA-ADE-BPNN for forecasting tourist volume based on Baidu index. The principal component analysis (PCA), a dimensional reduction, is employed to decorrelate the input data before training a back propagation neural network (BPNN) architecture, and the adaptive differential evolution algorithm (ADE) is for getting global optimization of BP network's weight values and threshold values to enhance the forecasting performance of BPNN. The PCA-ADE-BPNN model is a new combination of a dimensional reduction algorithm, an optimization algorithm, and a neural network. The validity of this model is demonstrated by conducting case studies of Beijing City and Hainan Province, China. The results indicate the proposed PCA-ADE-BPNN always outperforms other models in terms of forecasting accuracies. Therefore, the proposed PCA-ADE-BPNN is a potential candidate for the effective forecasting of tourist volume. Highlights: Proposed PCA-ADE-BPNN is a new combination of dimensionality reduction, optimization algorithm and neural network. ADE helps find suitable global initial connection weights and thresholds of BPNN. Principal component analysis can decorrelate the input data effectively. The effectiveness of PCA-ADE-BPNN is demonstrated by two empirical studies.