A paired neural network model for tourist arrival forecasting

Yuan Yao, Yi Cao, Xuemei Ding, Jia Zhai, Junxiu Liu, Yuling Luo, Shuai Ma, Kailin Zou

Research output: Contribution to journalArticle

7 Citations (Scopus)
4 Downloads (Pure)

Abstract

Tourist arrival and tourist demand forecasting are a crucial issue in tourism economy and the community economic development as well. Tourist demand forecasting has attracted much attention from tourism academics as well as industries. In recent year, it attracts increasing attention in the computational literature as advances in machine learning method allow us to construct models that significantly improve the precision of tourism prediction. In this paper, we draw upon both strands of the literature and propose a novel paired neural network model. The tourist arrival data is decomposed by two low-pass filters into long-term trend and short-term seasonal components, which are then modelled by a pair of autoregressive neural network models as a parallel structure. The proposed model is evaluated by the tourist arrival data to United States from twelve source markets. The empirical studies show that our proposed paired neural network model outperforming the selected benchmark model across all error measures and over different horizons.
Original languageEnglish
Pages (from-to)588-614
Number of pages27
JournalExpert Systems with Applications
Volume114
Early online date14 Aug 2018
DOIs
Publication statusPublished - 30 Dec 2018

Fingerprint

Network model
Neural networks
Tourists
Tourism
Demand forecasting
Benchmark
Machine learning
Prediction
Economic development
Empirical study
Filter
Learning methods
Industry

Keywords

  • forecasting
  • tourism demand
  • structural neural network
  • low-pass filter

Cite this

Yao, Yuan ; Cao, Yi ; Ding, Xuemei ; Zhai, Jia ; Liu, Junxiu ; Luo, Yuling ; Ma, Shuai ; Zou, Kailin. / A paired neural network model for tourist arrival forecasting. In: Expert Systems with Applications. 2018 ; Vol. 114. pp. 588-614.
@article{53c7e349bd254f369a86e4ab25761881,
title = "A paired neural network model for tourist arrival forecasting",
abstract = "Tourist arrival and tourist demand forecasting are a crucial issue in tourism economy and the community economic development as well. Tourist demand forecasting has attracted much attention from tourism academics as well as industries. In recent year, it attracts increasing attention in the computational literature as advances in machine learning method allow us to construct models that significantly improve the precision of tourism prediction. In this paper, we draw upon both strands of the literature and propose a novel paired neural network model. The tourist arrival data is decomposed by two low-pass filters into long-term trend and short-term seasonal components, which are then modelled by a pair of autoregressive neural network models as a parallel structure. The proposed model is evaluated by the tourist arrival data to United States from twelve source markets. The empirical studies show that our proposed paired neural network model outperforming the selected benchmark model across all error measures and over different horizons.",
keywords = "forecasting, tourism demand, structural neural network, low-pass filter",
author = "Yuan Yao and Yi Cao and Xuemei Ding and Jia Zhai and Junxiu Liu and Yuling Luo and Shuai Ma and Kailin Zou",
year = "2018",
month = "12",
day = "30",
doi = "10.1016/j.eswa.2018.08.025",
language = "English",
volume = "114",
pages = "588--614",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier",

}

A paired neural network model for tourist arrival forecasting. / Yao, Yuan; Cao, Yi; Ding, Xuemei; Zhai, Jia; Liu, Junxiu; Luo, Yuling; Ma, Shuai; Zou, Kailin.

In: Expert Systems with Applications, Vol. 114, 30.12.2018, p. 588-614.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A paired neural network model for tourist arrival forecasting

AU - Yao, Yuan

AU - Cao, Yi

AU - Ding, Xuemei

AU - Zhai, Jia

AU - Liu, Junxiu

AU - Luo, Yuling

AU - Ma, Shuai

AU - Zou, Kailin

PY - 2018/12/30

Y1 - 2018/12/30

N2 - Tourist arrival and tourist demand forecasting are a crucial issue in tourism economy and the community economic development as well. Tourist demand forecasting has attracted much attention from tourism academics as well as industries. In recent year, it attracts increasing attention in the computational literature as advances in machine learning method allow us to construct models that significantly improve the precision of tourism prediction. In this paper, we draw upon both strands of the literature and propose a novel paired neural network model. The tourist arrival data is decomposed by two low-pass filters into long-term trend and short-term seasonal components, which are then modelled by a pair of autoregressive neural network models as a parallel structure. The proposed model is evaluated by the tourist arrival data to United States from twelve source markets. The empirical studies show that our proposed paired neural network model outperforming the selected benchmark model across all error measures and over different horizons.

AB - Tourist arrival and tourist demand forecasting are a crucial issue in tourism economy and the community economic development as well. Tourist demand forecasting has attracted much attention from tourism academics as well as industries. In recent year, it attracts increasing attention in the computational literature as advances in machine learning method allow us to construct models that significantly improve the precision of tourism prediction. In this paper, we draw upon both strands of the literature and propose a novel paired neural network model. The tourist arrival data is decomposed by two low-pass filters into long-term trend and short-term seasonal components, which are then modelled by a pair of autoregressive neural network models as a parallel structure. The proposed model is evaluated by the tourist arrival data to United States from twelve source markets. The empirical studies show that our proposed paired neural network model outperforming the selected benchmark model across all error measures and over different horizons.

KW - forecasting

KW - tourism demand

KW - structural neural network

KW - low-pass filter

U2 - 10.1016/j.eswa.2018.08.025

DO - 10.1016/j.eswa.2018.08.025

M3 - Article

VL - 114

SP - 588

EP - 614

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

ER -