Forecasting exchange rates using feedforward and recurrent neural networks
基于外汇汇率数据，测试前馈和递归神经网络的样本外预测能力，提出两步法构建网络，发现某些网络模型在择时和预测误差上优于随机游走模型。
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.