基于非参数核回归模型的隐含波动率预测
Implied volatility forecast based on nonparametric regression model

采用非参数核回归的方法，以市场上的期权数据为分析对象，将隐含波动率看作是与执行价格、剩余期限相关的函数，对其进行建模. 构建双窗宽Nadaraya-Watson高斯核回归模型和Parzen-窗均匀核回归模型，与已有的参数模型和Bourke模型进行实验对比. 实验结果表明，Parzen-窗均匀核回归模型的隐含波动率预测精度更高、效果更好，大样本的情况下优点更显著.
It is generally believed that the implied volatility is significantly correlated with strike price and time-to-maturity. This paper is mainly based on non-parametric kernel regression model to illustrate the implied volatility of stock option in terms of building two new models of the implied volatility，the double window Nadaraya-Watson Gaussian kernel regression model and Parzen window uniform kernel regression model. After experimentally compared these two models with the parametric model and the Bourke model，the result shows that the Parzen window uniform kernel regression model has better forecasting ability，especially when dealing with a large number of datasets