Forecasting Exchange Rates Using Feedforward and Recurrent Neural Networks
In this paper we investigate the out-of-sample forecasting ability of feedforward and recurrent neural networks based on empirical foreign exchange rate data. A two-step procedure is proposed to construct suitable networks, in which networks are selected based on the predictive stochastic complexity (PSC) criterion, and the selected networks are estimated using both recursive Newton algorithms and the method of nonlinear least squares. Our results show that PSC is a sensible criterion for selecting networks and for certain exchange rate series, some selected network models have significant market timing ability and/or significantly lower out-of-sample prediction error relative to the random walk model. Copyright 1995 by John Wiley & Sons, Ltd.
Volume (Year): 10 (1995)
Issue (Month): 4 (Oct.-Dec.)
|Contact details of provider:|| Web page: http://www.interscience.wiley.com/jpages/0883-7252/|
|Order Information:|| Web: http://www3.interscience.wiley.com/jcatalog/subscribe.jsp?issn=0883-7252 Email: |
When requesting a correction, please mention this item's handle: RePEc:jae:japmet:v:10:y:1995:i:4:p:347-64. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Wiley-Blackwell Digital Licensing)or (Christopher F. Baum)
If references are entirely missing, you can add them using this form.