Forecasting tourism demand for Thua Thien Hue based on artificial neural networks
PDF (Vietnamese)

Keywords

Tourism demand forecasting
time-series data
artificial neural networks
tourist arrivals to Thua Thien Hue Dự báo nhu cầu du lịch
dữ liệu chuỗi thời gian
mạng nơ-ron nhân tạo
dữ liệu du khách đến Thừa Thiên Huế

Abstract

Accurate tourism demand forecasting for a destination plays a vital role in advising policymakers to plan and devise strategies related to investments in facilities, infrastructure improvements and services development. There are many different approaches in tourism demand forecasting, in which the one based on time-series data has attracted the most attention due to the unstructured nature of the particular data type. Neural networks have been evaluated as a predictive method specifically suited to this type of unstructured data. This paper examines the usage of neural networks, including MLP, RBF and ELN, to forecast tourism demand using time-series data in Thua Thien Hue. The analysis and comparison based on simulation show that the RBF network gives the best forecast result with the lowest MSE, RMSE, MAE and MAPE. This result is not only consistent with previous studies but also further confirms that the spatial conversion from nonlinear to linear of the hidden layer makes RBF powerful for the non-structural data.

https://doi.org/10.26459/hueunijed.v130i5A.6152
PDF (Vietnamese)

References

  1. M. Cuhadar, I. Cogurcu, and C. Kukrer, (2014), Modelling and Forecasting Cruise Tourism Demand to Izmir by Different Artificial Neural Network Architectures, International Journal of Business and Social Research, 4(3), 12–28, doi: 10.18533/ijbsr.v4i3.431.
  2. H.-C. Huang and C.- I Hou, (2017), Tourism Demand Forecasting Model Using Neural Network, Int. J. Comput. Sci. Inf. Technol., 9(2), 19–29, doi: 10.5121/ijcsit.2017.9202.
  3. M. E. Nor, A. I. M. Nurul, and M. S. Rusiman, (2018), A Hybrid Approach on Tourism Demand Forecasting, J. Phys. Conf. Ser., 995(1), doi: 10.1088/1742-6596/995/1/012034.
  4. Y. Yu, Y. Wang, S. Gao, and Z. Tang, (2017), Statistical Modeling and Prediction for Tourism Economy Using Dendritic Neural Network, Comput. Intell. Neurosci., 1–9, doi: 10.1155/2017/7436948.
  5. P. O. Fernandes, J. P. Teixeira, J. M. Ferreira, and S. G. Azevedo, (2011), Forecasting Tourism Demand with Artificial Neural Networks, Tour. Manag. Stud., 2009–2011.
  6. C. J. Lin, H. F. Chen, and T. S. Lee, (2011), Forecasting Tourism Demand Using Time Series, Artificial Neural Networks and Multivariate Adaptive Regression Splines:Evidence from Taiwan, Int. J. Bus. Adm., 2(2), doi: 10.5430/ijba.v2n2p14.
  7. J. P. Teixeira and P. O. Fernandes, (2014), Forecasting of a Non-Seasonal Tourism Time Series with ANN, in 1st International Work-Conference on Time Series (ITISE), 1–11.
  8. O. Claveria, E. Monte, and S. Torra, (2013), Tourism Demand Forecasting with Different Neural Networks Models, SSRN Electron. J., doi: 10.2139/ssrn.2507362.
  9. J. P. Teixeira and P. O. Fernandes, (2014), Forecasting of a Non-Seasonal Tourism Time Series with ANN, in International work-conference on Time Series – ETISE 2014, 1–11.
  10. M. Akin, A novel approach to model selection in tourism demand modeling, (2015), Tour. Manag., 48, 64–72, doi: 10.1016/j.tourman.2014.11.004.
  11. O. Claveria, E. Monte, and S. Torra, (2015), Tourism Demand Forecasting with Neural Network Models: Different Ways of Treating Information, Int. J. Tour. Res., 17(5), 492–500, doi: 10.1002/jtr.2016.
  12. H. A. Constantino, P. O. Fernandes, and J. P. Teixeira, (2016), Tourism demand modelling and forecasting with artificial neural network models: The Mozambique case study, Tékhne, 14(2), 113–124, doi: 10.1016/j.tekhne.2016.04.006.
  13. S. Cankurt and A. Subasi, (2016), Tourism demand modelling and forecasting using data mining techniques in multivariate time series: a case study in Turkey, Turkish J. Electr. Eng. Comput. Sci., 24, 3388–3404, doi: 10.3906/elk-1311-134.
  14. A. Koutras, A. Panagopoulos, and I. A. Nikas, (2017), Forecasting Tourism Demand Using Linear and Nonlinear Prediction Models, Acad. Tur. Innov. Journa, 9(1), 85–98.
  15. A. Mavrommati and A. Karakitsiou, (2018), Machine learning methods in tourism demand forecasting: some evidence from Greece, MIBES Trans., 11(1), 92–105.
  16. E. S. Silva, H. Hassani, S. Heravi, and X. Huang, (2019), Forecasting tourism demand with denoised neural networks, Ann. Tour. Res., 74, no. October 2018, 134–154, doi: 10.1016/j.annals.2018.11.006.
  17. M. Gregorić and T. Baldigara, (2020), Artificial neural networks in modelling seasonal tourism demand – case study of Croatia, Zb. Veleučilišta u Rijeci, 8(1), 19–39, doi: 10.31784/zvr.8.1.2.
  18. https://sdl.thuathienhue.gov.vn/ (accessed at 14:00 March 20, 2020).
  19. A. Shrestha and A. Mahmood, (2019), Review of Deep Learning Algorithms and Architectures, in IEEE Access, 7, pp. 53040-53065, doi: 10.1109/ACCESS.2019.2912200.
  20. Elman, (1990), J.L. Finding structure in time, Cogn. Sci., 14, 179–211.
  21. C. Hamzacebi, (2008), Improving artificial neural networks’ performance in seasonal time series forecasting, Information Sciences, 178, 4550–4559.
  22. R.K. Klimberg, G.P. Sillup, K.J. Boyle and V. Tavva, (2010), Forecasting performance measures – what are their practical meaning?, Advances in Business and Management Forecasting, 7, 137–147, Emerald Group Publishing Limited, Bingley.
Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Copyright (c) 2021 Array