基于ARMA-GARCH模型和马尔科夫链的人民币汇率预测  

RMB Exchange Rate Prediction Based on ARMA-GARCH Model and Markov Chain

作　　者：李振源 许学军[1] 

机构地区：[1]上海理工大学管理学院,上海

出　　处：《理论数学》2024年第6期362-372,共11页Pure Mathematics

摘　　要：本文构建人民币汇率的ARMA-GARCH模型,又引入马尔可夫链模型,试图探寻我国在岸人民币汇率的规律。从ARMA-GARCH(1,1)模型提取标准误差与马尔可夫链预测的汇率涨跌幅均值结合,对短期内汇率变化范围进行预测,可以预测7个交易日内的汇率上限,但存在精度问题需要后续研究改进。This paper presents an ARMA-GARCH model of the RMB exchange rate and subsequently introduces a Markov chain model with the objective of exploring the pattern of China’s onshore RMB exchange rate. The standard error extracted from the ARMA-GARCH(1,1) model is combined with the mean value of the exchange rate rise and fall predicted by the Markov chain to predict the range of exchange rate changes in the short term. It is possible to predict the upper limit of the exchange rate within seven trading days. However, subsequent research is required to improve the accuracy of this prediction.

关 键 词：人民币汇率 ARMA-GARCH 马尔可夫链 

分 类 号：F83[经济管理—金融学]