利用互联网搜索关注度预测期权隐含波动率变动:基于人工神经网络的分析

李星毅, 刘彦初, 朱书尚

系统工程理论与实践 ›› 2023, Vol. 43 ›› Issue (7) : 2055-2071.

PDF(1477 KB)
中国科学院数学与系统科学研究院期刊网
PDF(1477 KB)
系统工程理论与实践 ›› 2023, Vol. 43 ›› Issue (7) : 2055-2071. DOI: 10.12011/SETP2022-2020
论文

利用互联网搜索关注度预测期权隐含波动率变动:基于人工神经网络的分析

    李星毅1,2, 刘彦初3, 朱书尚1
作者信息 +

Using internet search attention to predict the change of option implied volatility: Analysis based on artificial neural network

    LI Xingyi1,2, LIU Yanchu3, ZHU Shushang1
Author information +
文章历史 +

摘要

本文运用人工神经网络方法, 研究互联网搜索对期权隐含波动率的影响. 基于标普500指数看涨期权, 本文首先建立了一个揭示期权隐含波动率变化与指数收益率、期权Delta和期权剩余有效期之间关系的人工神经网络模型, 结果显示此模型的估计精度比Hull和White (2017)提出的解析模型提升了约15%, 比Cao、Chen和Hull (2020)提出的神经网络模型提升了约40%. 接着, 本文引入25个互联网搜索关注度指标, 将它们集成一个谷歌趋势指数并作为度量互联网搜索关注度的综合指标. 最后, 将该谷歌趋势指数的变化率加入到前述人工神经网络模型, 从互联网搜索关注度的角度探究期权隐含波动率的动态特征, 新的模型进一步提升了约30%的估计精度.

Abstract

In this paper, we use the artificial neural network (ANN) method to investigate the effect of internet searches on the implied volatility of options. Based on the S&P 500 index call options, we establish an ANN model that reveals the relationship between the change of option implied volatility and the index return, option delta, and option maturity. The results show that the estimation accuracy of this model is 15% higher than that of the analytical model proposed by Hull and White (2017). This model is also 40% better than the neural network model of Cao, Chen, and Hull (2020). Then, we introduce 25 indicators of internet search attention, integrate them into a Google trends index (GTX), and use it as a comprehensive index to measure internet search attention. Finally, the change rate of the GTX is added to the ANN model mentioned above to explore the dynamic characteristics of option implied volatility from the perspective of internet search attention. The new model further improves the estimation accuracy by 30%.

关键词

隐含波动率 / 深度学习 / 人工神经网络 / 互联网搜索关注度 / 谷歌趋势

Key words

implied volatility / deep learning / artificial neural network / internet search attention / Google trends

引用本文

EndNote

Ris (Procite)

Bibtex

导出引用
李星毅 , 刘彦初 , 朱书尚. 利用互联网搜索关注度预测期权隐含波动率变动:基于人工神经网络的分析. 系统工程理论与实践, 2023, 43(7): 2055-2071 https://doi.org/10.12011/SETP2022-2020
LI Xingyi , LIU Yanchu , ZHU Shushang. Using internet search attention to predict the change of option implied volatility: Analysis based on artificial neural network. Systems Engineering - Theory & Practice, 2023, 43(7): 2055-2071 https://doi.org/10.12011/SETP2022-2020
中图分类号： F830   

参考文献

[1] Black F, Scholes M. The pricing of options and corporate liabilities[J]. Journal of Political Economy, 1973, 81(3): 637-654.
[2] Black F. Studies of stock price volatility changes[C]// Business and Economics Section of the American Statistical Association, 1976, 177-181.
[3] Christie A. The stochastic behavior of common stock variances: Value, leverage, and interest rate effects[J]. Journal of Financial Economics, 1982, 10(4): 407-432.
[4] Cont R, da Fonseca J. Dynamics of implied volatility surfaces[J]. Quantitative Finance, 2002, 2(1): 45-60.
[5] Poulsen R, Schenk-Hoppé K R, Ewald C O. Risk minimization in stochastic volatility models: Model risk and empirical performance[J]. Quantitative Finance, 2009, 9(6): 693-704.
[6] Hull J, White A. Optimal delta hedging for options[J]. Journal of Banking and Finance, 2017, 82: 180-190.
[7] Hutchinson J M, Lo A W, Poggio T. A nonparametric approach to pricing and hedging derivative securities via learning networks[J]. Journal of Finance, 1994, 49(3): 851-889.
[8] McCulloch W S, Pitts W. A logical calculus of the ideas immanent in nervous activity[J]. The Bulletin of Mathematical Biophysics, 1943, 5(4): 115-133.
[9] Culkin R, Das S R. Machine learning in finance: The case of deep learning for option pricing[J]. Journal of Investment Management, 2017, 15(4): 92-100.
[10] Nian K, Coleman T F, Li Y. Learning minimum variance discrete hedging directly from the market[J]. Quantitative Finance, 2018, 18(7): 1115-1128.
[11] Buehler H, Gonon L, Teichmann J, et al. Deep hedging[J]. Quantitative Finance, 2019, 19(8): 1271-1291.
[12] Ruf J, Wang W. Hedging with linear regressions and neural networks[J]. Journal of Business and Economic Statistics, 2021: 1-13. doi: 10.1080/07350015.2021.1931241.
[13] Gu S, Kelly B, Xiu D. Autoencoder asset pricing models[J]. Journal of Econometrics, 2021, 222(1): 429-450.
[14] Jakubik J, Nazemi A, Geyer-Schulz A, et al. Incorporating financial news for forecasting Bitcoin prices based on long short-term memory networks[J]. Quantitative Finance, 2023, 23(2): 335-349.
[15] Avramov D, Cheng S, Metzker L. Machine learning vs. economic restrictions: Evidence from stock return predictability[J]. Management Science, 2023, 69(5): 2587-2619.
[16] Cao J, Chen J, Hull J. A neural network approach to understanding implied volatility movements[J]. Quantitative Finance, 2020, 20(9): 1405-1413.
[17] 张鸿彦. 基于人工智能的隐含波动率的敏感度的研究[J]. 中国管理科学, 2008, 16(3): 125-130. Zhang Y H. Study on the sensitivity of implied volatility based on artificial intelligence[J]. Chinese Journal of Management Science, 2008, 16(3): 125-130.
[18] 郑振龙, 汪饶思行. 隐含波动率曲面的建模与预测[J]. 当代财经, 2017(3): 48-60. Zheng Z L, Wang R S X. Modeling and forecasting of implied volatility surface[J]. Contemporary Finance & Economics, 2017(3): 48-60.
[19] 马天星,吴卫星. 基于机器学习算法的金融期权波动率预测[J]. 学海, 2018, 5: 201-209. Ma T X, Wu W X. Prediction of financial option volatility based on machine learning algorithms[J]. Academia Bimestris, 2018, 5: 201-209.
[20] 陈蓉, 赵永杰. 隐含波动率曲面的预测研究: 来自中国台湾市场的证据[J]. 系统工程理论与实践, 2017, 37(8): 1949-1962. Chen R, Zhao Y J. Forecasting implied volatility surface: Evidence from Taiwan China market[J]. Systems Engineering-Theory & Practice, 2017, 37(8): 1949-1962.
[21] 李志勇, 余湄, 汪寿阳. 方差风险溢价和收益率预测:来自上证50ETF期权市场的证据[J]. 系统工程理论与实践, 2022, 42(2): 306-319. Li Z Y, Yu M, Wang S Y. Variance risk premiums and return predictability: Evidence from SSE 50ETF options[J]. Systems Engineering-Theory & Practice. 2022, 42(2): 306-319.
[22] 余湄, 程志勇, 邓军, 等. 一个新的期权定价方法: 基于混合次分数布朗运动的新视角[J]. 系统工程理论与实践. 2021, 41(11): 2761-2776. Yu M, Cheng Z Y, Deng J, et al. A new option pricing method: Based on the perspective of sub-mixed fractional Brownian motion[J]. Systems Engineering-Theory & Practice, 2021, 41(11): 2761-2776.
[23] Da Z, Engelberg J, Gao P. In search of attention[J]. The Journal of Finance, 2011, 66(5): 1461-1499.
[24] Bontempi M E, Golinelli R, Squadrani M. A new index of uncertainty based on internet searches: A friend or foe of other indicators?[R]. Dipartimento Di Scienze Economiche, Working Paper, 2016: 1062.
[25] D'Amuri F, Marcucci J. The predictive power of Google searches in forecasting US unemployment[J]. International Journal of Forecasting, 2017, 33(4): 801-816.
[26] Choi D, Gao Z, Jiang W. Attention to global warming[J]. The Review of Financial Studies, 2020, 33(3): 1112-1145.
[27] Aslanidis N, Bariviera A F, López ó G. The link between cryptocurrencies and Google trends attention[J]. Finance Research Letters, 2022, 47: No.102654.
[28] Lyócsa Š, Plíhal T. Russia's ruble during the onset of the Russian invasion of Ukraine in early 2022: The role of implied volatility and attention[J]. Finance Research Letters, 2022, 48: 102995.
[29] 熊熊, 许克维, 沈德华. 投资者情绪与期货市场功能——基于沪深300股指期货的研究[J]. 系统工程理论与实践, 2020, 40(9): 2252-2268. Xiong X, Xu K W, Shen D H. Investor sentiment and futures market functions: Evidence from CSI300 index futures market[J]. Systems Engineering-Theory & Practice, 2020, 40(9): 2252-2268.
[30] 王晓丹, 尚维, 汪寿阳. 互联网新闻媒体报道对我国股市的影响分析[J]. 系统工程理论与实践, 2019, 39(12): 3038-3047. Wang X D, Shang W, Wang S Y. The effects of online news on the Chinese stock market[J]. Systems Engineering-Theory & Practice, 2019, 39(12): 3038-3047.
[31] Hornik K. Approximation capabilities of multilayer feedforward networks[J]. Neural Networks, 1991, 4(2): 251-257.
[32] Telgarsky M. Benefits of depth in neural networks[C]// 29th Annual Conference on Learning Theory, 2016, 49: 1517-1539.
[33] Hull J. Machine learning in business: An introduction to the world of data science[M]. GFS Press, 2021.
[34] Glorot X, Bengio Y. Understanding the difficulty of training deep feed forward neural networks[C]// Thirteenth International Conference on Artificial Intelligence and Statistics, 2010, 9: 249-256.
[35] Gu S, Kelly B, Xiu D. Empirical asset pricing via machine learning[J]. The Review of Financial Studies, 2020, 33(5): 2223-2273.
[36] Reddi S J, Kale S, Kumar S. On the convergence of adam and beyond[C]// On the Convergence of Adam and Beyond, 2019.
[37] Masters D, Luschi C. Revisiting small batch training for deep neural networks[J]. arXiv Preprint, 1804.07612, 2018.
[38] Srivastava N, Hinton G, Krizhevsky A, et al. Dropout: A simple way to prevent neural networks from overfitting[J]. The Journal of Machine Learning Research, 2014, 15(1): 1929-1958.

基金

国家自然科学基金重大项目(71991474); 国家自然科学基金创新研究群体项目(71721001); 国家自然科学基金面上项目(72271249); 国家留学基金(202106380104)
PDF(1477 KB)

Accesses

Citation

Detail
段落导航
相关文章

/

〈 〉