000	00000nam##2200000za#4500
001	9.614702
003	CaOODSP
005	20211126112847
007	ta
008	150406|1999||||xxc|||||     f|0| 0 eng|d
020	|a0-662-27537-3
022	|a1192-5434
040	|aCaOODSP|beng
043	|an-cn---
086	1 |aFB3-2/99-3E
110	2 |aBank of Canada.
245	10|aForecasting GDP growth using artificial neural networks / |cby Greg Tkacz and Sarah Hu.
260	|aOttawa - Ontario : |bBank of Canada |c1999.
300	|a24p. : |bgraphs, references, tables ; |c28 cm.
490	1 |aWorking paper|x1192-5434|v99-3
500	|a"In this paper, the authors wish to determine whether the forecasting performance of such variables can be improved using neural network models. The main findings are that, at the 1-quarter forecasting horizon, neural networks yield no significant forecast improvements. At the 4-quarter horizon, however, the improved forecast accuracy is statistically significant. The root mean squared forecast errors of the best neural network models are about 15 to 19 per cent lower than their linear model counterparts. The improved forecast accuracy may be capturing more fundamental non-linearities between financial variables and real output growth at the longer horizon."--Abstract.
520	3 |aIn this paper, the authors wish to determine whether the forecasting performance of such variables can be improved using neural network models. The main findings are that, at the 1-quarter forecasting horizon, neural networks yield no significant forecast improvements. At the 4-quarter horizon, however, the improved forecast accuracy is statistically significant. The root mean squared forecast errors of the best neural network models are about 15 to 19 per cent lower than their linear model counterparts. The improved forecast accuracy may be capturing more fundamental non-linearities between financial variables and real output growth at the longer horizon.--Abstract
546	|aRésumés en français
563	|aSoftcover
590	|a99-12|b1999-03-26
690	07|aGross national product|2gcpds
690	07|aForecasting|2gcpds
690	07|aModels|2gcpds
720	1 |aTkacz, Greg
720	1 |aHu, Sarah
776	0#|tForecasting GDP growth using artificial neural networks / |w(CaOODSP)9.571705
830	#0|aWorking paper,|x1192-5434|v99-3|w(CaOODSP)9.514622
986	|a99-3