Utilize este identificador para referenciar este registo: http://hdl.handle.net/10198/9717
Título: Tourism time series forecast - different ANN architectures with time index input
Autor: Teixeira, João Paulo
Fernandes, Paula O.
Palavras-chave: Artificial neural network architectures
Time series forecast
Tourism
Data: 2012
Editora: Elsevier
Citação: Teixeira, João Paulo; Fernandes, Paula O. (2012) - Tourism time series forecast - different ANN architectures with time index input. Procedia Technology. Elsevier. p. 445-454
Resumo: Tourism demand is usually characterized by the time series of the “Monthly Number of Guest Nights in the Hotels”. Considering the increasing importance of this sector of activity, the prediction tools became even more relevant for public and private organizations management. Artificial Neural Networks (ANN) are a competitive model compared to other methodologies such the ARIMA time series models or linear models. In this paper the feedforward, cascade forward and recurrent architectures are compared. The input of the ANNs consists of the previous 12 months and two nodes used to the year and month. The three architectures produced a mean absolute percentage error between 4 and 6%, but the feedforward architecture behaved better considering validation and test sets, with 4,2% error.
Peer review: yes
URI: http://hdl.handle.net/10198/9717
DOI: 10.1016/j.protcy.2012.09.049
Aparece nas colecções:DE - Artigos em Revistas Indexados ao ISI/Scopus

Ficheiros deste registo:
Ficheiro Descrição TamanhoFormato 
Procedia_2012.pdf254,74 kBAdobe PDFVer/Abrir    Acesso Restrito. Solicitar cópia ao autor!


FacebookTwitterDeliciousLinkedInDiggGoogle BookmarksMySpace
Formato BibTex MendeleyEndnote Degois 

Todos os registos no repositório estão protegidos por leis de copyright, com todos os direitos reservados.