主管:中国科学院
主办:中国优选法统筹法与经济数学研究会
   中国科学院科技战略咨询研究院

中国管理科学 ›› 2008, Vol. 16 ›› Issue (3): 125-130.

• 论文 • 上一篇    下一篇

基于人工智能的隐含波动率的敏感度的研究

张鸿彦   

  1. 东南大学系统工程研究所, 江苏南京210096
  • 收稿日期:2007-01-12 修回日期:2008-05-10 出版日期:2008-06-30 发布日期:2008-06-30
  • 作者简介:张鸿彦(1972- ),男(汉族),江苏南通人,东南大学经济管理学院,系统工程专业博士研究生,研究方向:金融工程.

Study on the Sensitivity of Implied volatility Based on Artificial Intelligence

ZHANG Hong-yan   

  1. Institute of System Engineering, Southeast University, Nanjing 210096, China
  • Received:2007-01-12 Revised:2008-05-10 Online:2008-06-30 Published:2008-06-30

摘要: 隐含波动率是指在市场中观察的期权价格所蕴涵的波动率。不同种类的期权价格对波动率的敏感度不同,本文建立了小波神经网络和遗传算法相结合的模型,将期权按钱性进行分类,提出了加权的隐含波动率作为神经网络的输入变量,通过遗传算法来求取不同种类期权的隐含波动率的最优权重。在香港衍生品市场的实证中表明,本文所提出的模型要优于传统的Black-Scholes模型和其它在本文中提到的神经网络模型。

关键词: 期权定价, 人工智能, Black-Scholes模型, 钱性, 隐含波动率

Abstract: Implied volatility is the volatility implied by an option price observed in the market.The sensitivity of the volatility among varied kinds of option price ise different.In this work,we build hybrid forecasting models combining wavelet neural network with genetic algorithm.Using these models,option partition according to moneyness is applied and weighted implied volatility measures are regarded as input of the neural network.The genetic algorithm is used to determine the optimal weight of the implied volatility among different kinds of option.Case study on Hong Kong derivative market shows that these hybrid models are better than the conventional Black-Scholes model and the other neural network models adopted in this work.

Key words: option pricing, artificial intelligence, Black-Scholes model, moneyness, implied volatility

中图分类号: