Tourism time series forecast

In this chapter four combinations of input features and the feedforward, cascade forward and recurrent architectures are compared for the task of forecast tourism time series. The input features of the ANNs consist in the combination of the previous 12 months, the index time modeled by two nodes used to the year and month and one input with the daily hours of sunshine (insolation duration). The index time features associated to the previous twelve values of the time series proved its relevance in this forecast task. The insolation variable can improved results with some architectures, namely the cascade forward architecture. Finally, the experimented ANN models/architectures produced a mean absolute percentage error between 4 and 6%, proving the ability of the ANN models based to forecast this time series. Besides, the feedforward architecture behaved better considering validation and test sets, with 4.2% percentage error in test set.

[1]  João Paulo Teixeira,et al.  New approach of the ann methodology for forecasting time series: use of time index , 2009 .

[2]  Haiyan Song,et al.  Introduction: Tourism Forecasting: State of the Art , 2002 .

[3]  Diana Sommer.  Modelling And Analysis Of Enterprise Information Systems , 2016 .

[4]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[5]  Michael Y. Hu,et al.  Forecasting with artificial neural networks: The state of the art , 1997 .

[6]  I A Basheer,et al.  Artificial neural networks: fundamentals, computing, design, and application. , 2000, Journal of microbiological methods.

[7]  João Paulo Teixeira,et al.  A new approach to modelling and forecasting monthly overnights in the Northern Region of Portugal , 2007 .

[8]  James B. McDonald,et al.  Time Series Prediction With Genetic‐Algorithm Designed Neural Networks: An Empirical Comparison With Modern Statistical Models , 1999, Comput. Intell..

[9]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[10]  Youakim Badr,et al.  Collaborative Business and Enterprise Urbanization: Towards a Production-Oriented Urbanization Strategy , 2009, Int. J. Enterp. Inf. Syst..

[11]  Angappa Gunasekaran,et al.  Uncertainty in ERP-Controlled Manufacturing Systems , 2005, Int. J. Enterp. Inf. Syst..

[12]  C. Witt,et al.  Forecasting tourism demand: A review of empirical research , 1995 .

[13]  Madjid Tavana.  Competition, Strategy, and Modern Enterprise Information Systems , 2012 .

[14]  Zvi Schwartz,et al.  Forecasting Short Time-Series Tourism Demand with Artificial Intelligence Models , 2006 .

[15]  João Paulo Teixeira,et al.  A Insolação como parâmetro de entrada em modelo baseado em redes neuronais para previsão de série temporal do turismo , 2011 .

[16]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[17]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[18]  David Enke,et al.  The adaptive selection of financial and economic variables for use with artificial neural networks , 2004, Neurocomputing.

[19]  Martin A. Riedmiller,et al.  A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.

[20]  João Paulo Teixeira,et al.  Modelling tourism demand: a comparative study between artificial neural networks and the Box-Jenkins methodology , 2008 .

[21]  Timothy L. Urban,et al.  A neural network approach to mutual fund net asset value forecasting , 1996 .

[22]  William Remus,et al.  Neural Network Models for Time Series Forecasts , 1996 .

[23]  Paula O. Fernandes,et al.  Previsão da procura turística utilizando um modelo não linear , 2009 .

[24]  John Snyder,et al.  Using a neural network to forecast visitor behavior , 1996 .