An extended evaluation framework for neural network publications in sales forecasting
AIA'06 Proceedings of the 24th IASTED international conference on Artificial intelligence and applications
| Hi-index | 0.00 |
The air transport industry firmly relies on forecastingmethods for supporting management decisions. However,optimistic forecasting has resulted in serious problems tothe Brazilian industry in last years. In this paper, modelsbased on artificial neural networks are developed for theair transport passenger demand forecasting. It is foundthat neural processing can outperform the traditionaleconometric approach used in this field and canaccurately generalise the learnt time series behaviour,even in practical conditions, where a small number ofdata points is available. Feeding the input nodes of theneural estimator with pre-processed data, the forecastingerror is evaluated to be smaller than 0.6%.