00000nam##2200000za#4500 9.614702 CaOODSP 20211126112847 ta 150406|1999||||xxc||||| f|0| 0 eng|d 0-662-27537-3 1192-5434 CaOODSP eng n-cn--- FB3-2/99-3E Bank of Canada. Forecasting GDP growth using artificial neural networks / by Greg Tkacz and Sarah Hu. Ottawa - Ontario : Bank of Canada 1999. 24p. : graphs, references, tables ; 28 cm. Working paper 1192-5434 99-3 "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. 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 Résumés en français Softcover 99-12 1999-03-26 Gross national product gcpds Forecasting gcpds Models gcpds Tkacz, Greg Hu, Sarah Forecasting GDP growth using artificial neural networks / (CaOODSP)9.571705 Working paper, 1192-5434 99-3 (CaOODSP)9.514622 99-3