基于人工神经网络和随机游走模型的汇率预测

由于金融数据具有随机性特征，使得建模和预测变得极其困难.提出一种组合预测方法，即假定任何金融时序数据由线性和非线性两部分组成，将其中线性部分的数据通过随机游走(RW)模型进行模拟，剩余的非线性残差部分由前馈神经网络(FANN)和诶尔曼神经网络(EANN)协同处理.从实证结果可知，该组合方法相比单独使用RW、FANN或EANN模型有更高的预测精度.

Exchange Rate Forecast Based on Artificial Neural Network and Random Walk Model

The random characteristics of financial time series make the task of modeling and forecasting extremely difficult.In this paper, we proposed a combination methodology benefiting from the strengths of both RW and ANN models, which assumes that any financial time series consist of a linear part and a nonlinear part. The linear part of a financial dataset is processed through the RW model, and the remaining nonlinear residuals are processed using an ensemble of FANN and EANN models. The empirical results demonstrate that our combination method achieves reasonably better forecasting accuracies than each of RW, FANN and EANN models in isolation.