Comparison of Artificial Neural Network Architectures in the Task of Tourism Time Series Forecast
The authors have been developing several models
based on artificial neural networks, linear regression models, Box-
Jenkins methodology and ARIMA models to predict the time series
of tourism. The time series consist in the “Monthly Number of Guest
Nights in the Hotels" of one region. Several comparisons between the
different type models have been experimented as well as the features
used at the entrance of the models. The Artificial Neural Network
(ANN) models have always had their performance at the top of the
best models. Usually the feed-forward architecture was used due to
their huge application and results. In this paper the author made a
comparison between different architectures of the ANNs using
simply the same input. Therefore, the traditional feed-forward
architecture, the cascade forwards, a recurrent Elman architecture and
a radial based architecture were discussed and compared based on the
task of predicting the mentioned time series.
[1] Witt, Stephen F. and Witt, Christine A.. Forecasting tourism demand: a
review of empirical research. International Journal of Forecasting. N.º
11, pp.447/475, 1995.
[2] Wong, K. F.. Introduction: Tourism Forecasting State of the Art.
Journal of Travel and Tourism Marketing; N.º 13 (1/2), pp.1/3. 2002.
[3] Fernandes, Paula Odete. Modelling, Prediction and Behaviour Analysis
of Tourism Demand in the North of Portugal. Ph.D. Thesis in Applied
Economy and Regional Analysis. Valladolid University - Spain.. 2005.
[4] Yu, Gongmei and Schwartz, Zvi. Forecasting Short Time-Series
Tourism Demand with Artificial Intelligence Models. Journal of Travel
Research. N.º 45, pp. 194/203, 2006.
[5] Dolgner, R. & Costa, A.. Turismo, Sustentabilidade e Flexibilidade
Laboral. 16º Congresso da APDR Universidade da Madeira, Funchal,
pp. 801-818. 2010.
[6] Ministério da Economia e da Inova├º├úo. Plano Estratégico Nacional do
Turismo - Para o desenvolvimento do Turismo em Portugal. Lisboa.
2006.
[7] WTO; United Nations World Tourism Organization, Tourism Market
Trends. [online]. UNWTO, 2006. Available in URL:
http://www.unwto.org 02/2011.
[8] Thawornwong, S. and Enke, D.. The adaptive selection of financial and
economic variables for use with artificial neural networks.
Neurocomputing. N.º6, pp. 205/232. 2004.
[9] Hill, T.; O-connor, M. and Remus, W.. Neural network models for time
series forecasts. Management Science. Vol. 42 (7), pp. 1082/1092. 1996.
[10] Hansen, J. V., Mcdonald, J. B. and Nelson, R. D.. Time series prediction
with genetic-algorithm designed neural networks: an empirical
comparison with modern statistical models. ComputlIntell. N.º15, pp.
171/184. 1999.
[11] Fernandes, P. and Teixeira, J.. A new approach to modelling and
forecasting monthly overnights in the Northern Region of Portugal.
Proceedings of the 15th International Finance Conference (CD-ROM);
Université de Cergy; Hammamet, Medina, Tun├¡sia. 2007.
[12] Fernandes, Paula O.; Teixeira, João Paulo - Applying the artificial
neural network methodology to tourism time series forecasting. In 5th
International Scientific Conference in ÔÇÿBusiness and Management.
Vilnius, Lithuania. ISBN 978-9955-28-267-9. 2008.
[13] Teixeira, J. P. & Fernandes, P. O. A Insolação como Parâmetro de
Entrada em Modelo Baseado em Redes Neuronais para Previsão da
Série Temporal do Turismo. CLME- 2011, Maputo.
[14] INE. Anuário Estatístico da Região Norte 2010. Instituto Nacional de
Estatística, Lisboa. 2011.
[15] Bishop, C. M.. Neural Networks for pattern recognition. Oxford
University Press. Oxford. London. 1995.
[16] Haykin, Simon. Neural Networks. A comprehensive foundation. New
Jersey, Prentice Hall. 1999.
[17] Rumelhart, D. E. and McClelland, J. L.. Parallel Distributed
Processing: Explorations in the Microstructure of Cognition. Volume 1:
Foundations. The Massachusetts Institute of Technology Press,
Cambridge. 1986.
[18] Hagan, M. T. and Menhaj, M.. Training feedforward networks with the
Marquardt algorithm, IEEE Transactions on Neural Networks, vol. 5, nº
6, pp.989-993. 1994.
[19] Donald Marquardt. An Algorithm for Least-Squares Estimation of
Nonlinear Parameters. SIAM Journal on Applied Mathematics 11 (2):
431-441. 1963.
[20] Riedmiller, M. and Braun, H.. A direct adaptive method for faster
backpropagation learning: The RPROP algorithm. Proceedings of the
IEEE International Conference on Neural Networks. 1993.
[21] Demuth, H. and Beale, M.. Neural Network Toolbox, for use with
Matlab - User-s Guide, version 4, by the Math Works. 2000.
[22] Fernandes, Paula O.; Teixeira, João Paulo - New approach of the ann
methodology for forecasting time series: use of time index. In
International Conference on Tourism Development and Management.
Kos, Greece. 2011.
[23] Fernandes, Paula O.; Monte, Ana Paula; Teixeira, João Paulo - Previsão
da procura turística utilizando um modelo não linear. In XIII Congreso
Internacional de Investigaci├│n en Ciencias Administrativas. Mexico.
2009.
[1] Witt, Stephen F. and Witt, Christine A.. Forecasting tourism demand: a
review of empirical research. International Journal of Forecasting. N.º
11, pp.447/475, 1995.
[2] Wong, K. F.. Introduction: Tourism Forecasting State of the Art.
Journal of Travel and Tourism Marketing; N.º 13 (1/2), pp.1/3. 2002.
[3] Fernandes, Paula Odete. Modelling, Prediction and Behaviour Analysis
of Tourism Demand in the North of Portugal. Ph.D. Thesis in Applied
Economy and Regional Analysis. Valladolid University - Spain.. 2005.
[4] Yu, Gongmei and Schwartz, Zvi. Forecasting Short Time-Series
Tourism Demand with Artificial Intelligence Models. Journal of Travel
Research. N.º 45, pp. 194/203, 2006.
[5] Dolgner, R. & Costa, A.. Turismo, Sustentabilidade e Flexibilidade
Laboral. 16º Congresso da APDR Universidade da Madeira, Funchal,
pp. 801-818. 2010.
[6] Ministério da Economia e da Inova├º├úo. Plano Estratégico Nacional do
Turismo - Para o desenvolvimento do Turismo em Portugal. Lisboa.
2006.
[7] WTO; United Nations World Tourism Organization, Tourism Market
Trends. [online]. UNWTO, 2006. Available in URL:
http://www.unwto.org 02/2011.
[8] Thawornwong, S. and Enke, D.. The adaptive selection of financial and
economic variables for use with artificial neural networks.
Neurocomputing. N.º6, pp. 205/232. 2004.
[9] Hill, T.; O-connor, M. and Remus, W.. Neural network models for time
series forecasts. Management Science. Vol. 42 (7), pp. 1082/1092. 1996.
[10] Hansen, J. V., Mcdonald, J. B. and Nelson, R. D.. Time series prediction
with genetic-algorithm designed neural networks: an empirical
comparison with modern statistical models. ComputlIntell. N.º15, pp.
171/184. 1999.
[11] Fernandes, P. and Teixeira, J.. A new approach to modelling and
forecasting monthly overnights in the Northern Region of Portugal.
Proceedings of the 15th International Finance Conference (CD-ROM);
Université de Cergy; Hammamet, Medina, Tun├¡sia. 2007.
[12] Fernandes, Paula O.; Teixeira, João Paulo - Applying the artificial
neural network methodology to tourism time series forecasting. In 5th
International Scientific Conference in ÔÇÿBusiness and Management.
Vilnius, Lithuania. ISBN 978-9955-28-267-9. 2008.
[13] Teixeira, J. P. & Fernandes, P. O. A Insolação como Parâmetro de
Entrada em Modelo Baseado em Redes Neuronais para Previsão da
Série Temporal do Turismo. CLME- 2011, Maputo.
[14] INE. Anuário Estatístico da Região Norte 2010. Instituto Nacional de
Estatística, Lisboa. 2011.
[15] Bishop, C. M.. Neural Networks for pattern recognition. Oxford
University Press. Oxford. London. 1995.
[16] Haykin, Simon. Neural Networks. A comprehensive foundation. New
Jersey, Prentice Hall. 1999.
[17] Rumelhart, D. E. and McClelland, J. L.. Parallel Distributed
Processing: Explorations in the Microstructure of Cognition. Volume 1:
Foundations. The Massachusetts Institute of Technology Press,
Cambridge. 1986.
[18] Hagan, M. T. and Menhaj, M.. Training feedforward networks with the
Marquardt algorithm, IEEE Transactions on Neural Networks, vol. 5, nº
6, pp.989-993. 1994.
[19] Donald Marquardt. An Algorithm for Least-Squares Estimation of
Nonlinear Parameters. SIAM Journal on Applied Mathematics 11 (2):
431-441. 1963.
[20] Riedmiller, M. and Braun, H.. A direct adaptive method for faster
backpropagation learning: The RPROP algorithm. Proceedings of the
IEEE International Conference on Neural Networks. 1993.
[21] Demuth, H. and Beale, M.. Neural Network Toolbox, for use with
Matlab - User-s Guide, version 4, by the Math Works. 2000.
[22] Fernandes, Paula O.; Teixeira, João Paulo - New approach of the ann
methodology for forecasting time series: use of time index. In
International Conference on Tourism Development and Management.
Kos, Greece. 2011.
[23] Fernandes, Paula O.; Monte, Ana Paula; Teixeira, João Paulo - Previsão
da procura turística utilizando um modelo não linear. In XIII Congreso
Internacional de Investigaci├│n en Ciencias Administrativas. Mexico.
2009.
@article{"International Journal of Information, Control and Computer Sciences:58572", author = "João Paulo Teixeira and Paula Odete Fernandes", title = "Comparison of Artificial Neural Network Architectures in the Task of Tourism Time Series Forecast", abstract = "The authors have been developing several models
based on artificial neural networks, linear regression models, Box-
Jenkins methodology and ARIMA models to predict the time series
of tourism. The time series consist in the “Monthly Number of Guest
Nights in the Hotels" of one region. Several comparisons between the
different type models have been experimented as well as the features
used at the entrance of the models. The Artificial Neural Network
(ANN) models have always had their performance at the top of the
best models. Usually the feed-forward architecture was used due to
their huge application and results. In this paper the author made a
comparison between different architectures of the ANNs using
simply the same input. Therefore, the traditional feed-forward
architecture, the cascade forwards, a recurrent Elman architecture and
a radial based architecture were discussed and compared based on the
task of predicting the mentioned time series.", keywords = "Artificial Neural Network Architectures, time series
forecast, tourism.", volume = "6", number = "6", pages = "798-6", }
