Publicação
Applying the artificial neural network methodology for forecasting the tourism time series
| Resumo: | This paper aims to develop models and apply them to sensitivity studies in order to predict demand. It provides a deeper understanding of the tourism sector in Northern Portugal and contributes to already existing econometric studies by using the Artificial Neural Networks methodology. This work's focus is on the treatment, analysis, and modelling of time series representing “Monthly Guest Nights in Hotels” in Northern Portugal recorded between January 1987 and December 2005. The model used 4 neurons in the hidden layer with the logistic activation function and was trained using the Resilient Backpropagation algorithm. Each time series forecast depended on 12 preceding values. The analysis of the output forecast data of the selected ANN model showed a reasonably close result compared to the target data. |
|---|---|
| Autores principais: | Fernandes, Paula Odete |
| Outros Autores: | Teixeira, João Paulo |
| Assunto: | Artificial neural networks Time series forecasts Tourism Backpropagation Feedforward Training |
| Ano: | 2008 |
| País: | Portugal |
| Tipo de documento: | comunicação em conferência |
| Tipo de acesso: | acesso aberto |
| Instituição associada: | Instituto Politécnico de Bragança |
| Idioma: | inglês |
| Origem: | Biblioteca Digital do IPB |
| Resumo: | This paper aims to develop models and apply them to sensitivity studies in order to predict demand. It provides a deeper understanding of the tourism sector in Northern Portugal and contributes to already existing econometric studies by using the Artificial Neural Networks methodology. This work's focus is on the treatment, analysis, and modelling of time series representing “Monthly Guest Nights in Hotels” in Northern Portugal recorded between January 1987 and December 2005. The model used 4 neurons in the hidden layer with the logistic activation function and was trained using the Resilient Backpropagation algorithm. Each time series forecast depended on 12 preceding values. The analysis of the output forecast data of the selected ANN model showed a reasonably close result compared to the target data. |
|---|