经济数学2016，Vol.33Issue(1)：30-35,6.
基于人工神经网络和随机游走模型的汇率预测∗
Exchange Rate Forecast Based on Artificial Neural Network and Random Walk Model
摘要
Abstract
The random characteristics of financial time series make the task of modeling and forecasting extremely diffi-cult.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 pro-cessed 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.关键词
诶尔曼神经网络/人工神经网络/随机游走模型/组合预测/金融时间序列Key words
EANN/artificial neural network/random walk model/combination forecast/financial time series分类
管理科学引用本文复制引用
洪嘉灏,李雄英,王斌会..基于人工神经网络和随机游走模型的汇率预测∗[J].经济数学,2016,33(1):30-35,6.基金项目
中央高校基本科研业务费专项资金项目(11614801) （11614801）
广东省省部产学研结合项目(2011A090200044) （2011A090200044）
