The Application of Structured Feedforward Neural Networks to the Modelling of the Daily Series of Currency in Circulation

0339930 - ÚI 2010 RIV DE eng C - Konferenční příspěvek (zahraniční konf.)
Hlaváček, M. - Čada, J. - Hakl, František
The Application of Structured Feedforward Neural Networks to the Modelling of the Daily Series of Currency in Circulation.
Advances in Natural Computation. Berlin: Springer, 2005 - (Wang, L.; Chen, K.; Ong, Y.), s. 1234-1246. Lecture Notes in Computer Science, 3610. ISBN 3-540-28323-4.
[International Conference ICNC 2005 /1./. Changsha (CN), 27.08.2005-29.08.2005]
Grant CEP: GA MŠMT(CZ) 1M0567
Výzkumný záměr: CEZ:AV0Z10300504
Klíčová slova: neural networks * currency in circulation * prediction * ARIMA
Kód oboru RIV: BA - Obecná matematika

The paper introduces feedforward structured neural network model and discusses its applicability to the forecasting of the currency in circulation. The forecasting performance of the new neural network model is compared with an ARIMA model. The results indicates that the performance of the neural network model is slightly better.
Trvalý link: http://hdl.handle.net/11104/0183299