人民币汇率的双成分混合波动率模型

Two-component hybrid volatility models on CNY exchange rates

汇率波动性预测在金融和计算领域一直受到广泛关注,然而由于缺乏可以捕捉汇率波动动态变化的预测模型,高频汇率的波动率预测至今没有得到彻底的研究.文章提出了基于神经网络的双成分混合汇率波动率模型,该模型利用低通Hodrick-Prescott滤波器将已实现波动率分解为长期分量和短期分量,使用自回归神经网络模拟长期分量,一阶自回归过程模拟短期分量,通过实证分析确定自回归神经网络参数(10个隐神经元和四阶滞后输入神经元),以6种主要高频率汇率(英镑/人民币,美元/人民币,澳元/人民币,欧元/人民币,日元/人民币,和瑞士法郎/人民币),在5 h(d)、20 h(d)、100 h(d)、200 h(d)、360 h(d)和500 h(d)的预测区间构建1 h和1 d已实现波动率,并与双成分GARCH模型、EGARCH模型、四阶滞后自回归神经网络模型3个基准模型进行对比,分析模型的预测性能,实验评估表明,提出的混合预测模型在所有预测的范围内均显著地优于传统人民币汇率波动模型.

Volatility forecasting attracts extensive attentions in both finance and computation areas.However,high frequency CNY exchange rates with main stream currencies have not been thoroughly studied due to the lack of the dedicated forecasting model that can capture the dynamics of CNY rates.This paper fills the knowledge gap by,firstly,proposing a two-component hybrid volatility model based on a neural network,which is composed of a low-pass filter,the machine-learning algorithm,and the traditional autoregressive model,and secondly,studying the forecasting performance thoroughly using the one-hour and one-day realized volatility constructed from high frequency rates of six major rates:GBP/CNY,USD/CNY,AUD/CNY,EUR/CNY,JPY/CNY,and CHF/CNY.The predicting results are compared with component GARCH,EGARCH and neural network only models.The experimental evaluations show that our proposed model outperforms the traditional models in CNY forecasting volatility significantly and consistently across all forecasting horizons.