DocumentCode
1803663
Title
Forecasting airline seat show rates with neural networks
Author
Wu, Kai T. ; Lin, Frank C.
Author_Institution
Dept. of Math. & Comput. Sci., Maryland Univ, Princess Anne, MD, USA
Volume
6
fYear
1999
fDate
36342
Firstpage
3974
Abstract
Using data supplied by US Airways, a multivariate, externally recurrent neural network is trained using the backpropagation paradigm. Extrapolation of the network to make predictions in the 8 hours and 1 hour booked rate and show rate attained an accuracy of 98%. We have demonstrated that the neural network paradigm can be applied to obtain an optimal management strategy
Keywords
backpropagation; extrapolation; recurrent neural nets; travel industry; US Airways; airline seat forecasting; backpropagation; extrapolation; management; recurrent neural network; Backpropagation; Computer science; Economic forecasting; Equations; Extrapolation; Inventory control; Inventory management; Neural networks; Predictive models; Recurrent neural networks;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 1999. IJCNN '99. International Joint Conference on
Conference_Location
Washington, DC
ISSN
1098-7576
Print_ISBN
0-7803-5529-6
Type
conf
DOI
10.1109/IJCNN.1999.830793
Filename
830793
Link To Document