Forecasting Monthly Tourism Demand Using Enhanced Backpropagation Neural Network

• DOI: 10.1007/s11063-020-10363-z
• Publication Date: 2020-10-22T05:02:53Z
• Authors: Lin Wang; Binrong Wu; Qing Zhu; Yu-Rong Zeng
• Keywords: Backpropagation; Initialization; Sigmoid function

The accurate forecasting of monthly tourism demand can improve tourism policies and planning. However, the complex nonlinear characteristics of monthly tourism demand complicate forecasting. This study proposes a novel approach named ICPSO-BPNN that combines improved chaotic particle swarm optimization (ICPSO) with backpropagation neural network (BPNN) to forecast monthly tourism demand. ICPSO with chaotic initialization and two search strategies, sigmoid-like inertia weight, and linear acceleration coefficients is utilized to search for the appropriate initial connection weights and thresholds necessary to improve the performance of BPNN. Two comparative real-life examples and one extended example are adopted to verify the superiority of the proposed ICPSO-BPNN. Results show ICPSO-BPNN outperforms that of the basic BPNN, autoregressive integrated moving average model, support vector regression, and other popular existing models.