Forecasting Monthly Tourism Demand Using Enhanced Backpropagation Neural Network
- PDF / 2,020,980 Bytes
- 30 Pages / 439.37 x 666.142 pts Page_size
- 34 Downloads / 253 Views
Forecasting Monthly Tourism Demand Using Enhanced Backpropagation Neural Network Lin Wang1 · Binrong Wu1 · Qing Zhu2 · Yu-Rong Zeng3 Accepted: 3 October 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract 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. Keywords Tourism demand · Time series forecasting · Backpropagation neural network · Improved chaotic particle swarm optimization
1 Introduction The tourism industry has undergone extensive development worldwide over the past several decades. The development of the tourism industry has stimulated that of related industries, such as entertainment, transportation, catering, retailing, and infrastructure. Thus,
B
Yu-Rong Zeng [email protected] Lin Wang [email protected] Binrong Wu [email protected] Qing Zhu [email protected]
1
School of Management, Huazhong University of Science and Technology, Wuhan 430074, China
2
International Business School, Shaanxi Normal University, Xi’an 710000, China
3
Hubei University of Economics, Wuhan 430205, China
123
L. Wang et al.
governments and businesses require the accurate forecasting of tourism demand to plan tourism-related investments. In particular, superior and accurate methods for tourism demand forecasting are required in regions and countries wherein tourism income accounts for a large proportion of the GDP. The literature presents numerous studies on tourism demand forecasting. Wu et al. [1] reviewed 171 articles on hotel and tourism demand modeling and forecasting published over the years of 2007–2015. Song et al. [2] reviewed 211 key papers published between 1968 and 2018, which can help us better understand how the methods of tourism demand forecasting have evolved over time. Popular time-series forecasting models that have been applied in previous studies can be categorized as econometric, time-series and emerging artificial intelligence (AI) techniques. In recent years, traditionally widely used econometric methods including autoregressive distributed lag models (ADLMs or ARDL) and the error correction models (ECMs), time-varying parameter (TVP) models and vector autoregressive (VAR) mod
Data Loading...
