00000nam##2200000za#4500 9.615455 CaOODSP 20211126112847 ta 150406|2000||||xxc||||| f|0| 0 eng|d 0-662-29766-0 1192-5434 CaOODSP eng n-cn--- FB3-2/100-23E Bank of Canada. The application of artificial neural networks to exchange rate forecasting : the role of market microstructure variables / by Nikola Gradojevic and Jing Yang. Ottawa - Ontario : Bank of Canada 2000. v, 27p. : figs., graphs, tables ; 28 cm. Working paper 1192-5434 100-23 "Artificial neural networks (ANN) are employed for high-frequency Canada/U.S. dollar exchange rate forecasting."--Abstract. "This paper examines whether introducing a market microstructure variable (that is, order flow) into a set of daily observations of macroeconomic variables (interest rate, crude oil price) together with an ANN technique can explain Canada/U.S. dollar exchange rate movement better than linear and random walk models. Two statistics are used to compare models: root-mean squared error (RMSE) and the percentage of correctly predicted exchange rate changes (PERC)."--Introduction. Bibliography. Artificial neural networks (ANN) are employed for high-frequency Canada/U.S. dollar exchange rate forecasting.--Abstract This paper examines whether introducing a market microstructure variable (that is, order flow) into a set of daily observations of macroeconomic variables (interest rate, crude oil price) together with an ANN technique can explain Canada/U.S. dollar exchange rate movement better than linear and random walk models. Two statistics are used to compare models: root-mean squared error (RMSE) and the percentage of correctly predicted exchange rate changes (PERC).--Introduction Résumés en français Softcover 01-01 2001-01-05 Exchange rates gcpds Currency gcpds Gradojevic, Nikola Yang, Jing The application of artificial neural networks to exchange rate forecasting : (CaOODSP)9.571563 Working paper, 1192-5434 100-23 (CaOODSP)9.514622