东北大学学报(社会科学版) ›› 2015, Vol. 17 ›› Issue (1): 32-37.DOI: 10.15936/j.cnki.10083758.2015.01.006

• 经济与管理研究 • 上一篇    下一篇

基于NARX网络的人民币汇率预测研究

王楠,侯铁珊   

  1. (大连理工大学经济学院,辽宁大连116024)
  • 收稿日期:2015-06-12 修回日期:2015-06-12 出版日期:2015-01-25 发布日期:2015-06-12
  • 通讯作者: 王楠
  • 作者简介:王楠(1981),女(满族),辽宁沈阳人,大连理工大学博士研究生,主要从事国际贸易研究;侯铁珊(1944),男,黑龙江哈尔滨人,大连理工大学教授,博士生导师,主要从事国际贸易研究。
  • 基金资助:
    国家自然科学基金资助项目(71172136);教育部人文社会科学研究资助项目(10YJC630401);中央高校基本科研业务费专项资助项目(DUT13RW433)。

Research of RMB Exchange Rate Forecasting Based on the NARX Model

Wang Nan, HOU Tie-shan   

  1. (School of Economics, Dalian University of Technology, Dalian 116024, China)
  • Received:2015-06-12 Revised:2015-06-12 Online:2015-01-25 Published:2015-06-12
  • Contact: -
  • About author:-
  • Supported by:
    -

摘要: 针对目前人民币汇率的自身特点,新的汇率预测模型既要关注汇率理论的定性研究,又要关注历史走势的定量研究,还要注重政策出台时对汇率的影响。采用非线性自回归神经网络NARX网络,对人民币汇率进行了预测,并使用无本金交割远期外汇NDF作为NARX网络的外部输入,以此来改善预测模型在面对突发政策和消息时的预测性能。通过实证检验发现,引入了NDF的NARX网络,在推广性能上远远优于没有NDF参与的NAR网络,并且在训练数据选择时,选择更大范围、包含影响汇率变化事件的历史数值会很大程度上影响网络的推广性能。

关键词: NARX网络, 人民币, 汇率预测

Abstract: Based on the characteristics of the current RMB exchange rate, a new forecasting model should take into account the qualitative studies of exchange rate theories, the quantitative research of historical tendencies and the impact elicited by policy issuing. The nonlinear auto regressive model with exogenous inputs, NARX for short, was adopted to forecast RMB exchange rate, and the non-deliverable forward exchange rate, known as NDF, was selected as an external input of the NARX model to improve the forecasting performance in face of sudden policy and news. By empirical testing, it was found that the NARX model with NDF performs much better than the NARX model without NDF. Moreover, selecting the training data from a wide range and with the historical values impacting exchange rate tends to affect the models generalization performance to a large extent.

Key words: NARX model, RMB, exchange rate forecasting

中图分类号: