Forecasting Exchange Rates Using Feedforward and Recurrent Neural Networks
Chung-Ming Kuan; Tung Liu
Journal of Applied Econometrics, Vol. 10, No. 4. (Oct. - Dec., 1995),
pp. 347-364.
Abstract
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 mean squared prediction error relative to the random walk
model.