Gated deep neural networks for implied volatility surfaces

This paper presents a framework of developing neural networks to predict implied volatility surfaces. It can incorporate the related properties from existing mathematical models and empirical findings, including no static arbitrage, limiting boundaries, asymptotic slope and volatility smile. These properties are also satisfied empirically in our experiments with the option data on the S&P 500 index over 20 years. The developed neural network model outperforms the widely used surface stochastic volatility inspired (SSVI) model and other benchmarked neural network models on the mean average percentage error in both in-sample and out-of-sample datasets. This study has two major contributions. First, it contributes to the recent use of machine learning in finance, and an accurate deep learning implied volatility surface prediction model is obtained. Second, it provides the methodological guidance on how to seamlessly combine data-driven models with domain knowledge in the development of machine learning applications.

[1]  Vladimir Vapnik,et al.  The Nature of Statistical Learning , 1995 .

[2]  P. Carr,et al.  A New Simple Approach for Constructing Implied Volatility Surfaces , 2011 .

[3]  Tetsuya Shimokawa,et al.  Agent-Based Approach to Option Pricing Anomalies , 2009, IEEE Transactions on Evolutionary Computation.

[4]  Jim Gatheral,et al.  Arbitrage-free SVI volatility surfaces , 2012, 1204.0646.

[5]  Yu Zheng,et al.  Gated Neural Networks for Option Pricing: Rationality by Design , 2017, AAAI.

[6]  Ting Liu,et al.  Generating and Exploiting Large-scale Pseudo Training Data for Zero Pronoun Resolution , 2016, ACL.

[7]  Kumar Muthuraman,et al.  American Options Under Stochastic Volatility , 2007, Oper. Res..

[8]  P. Carr,et al.  Stochastic Skew in Currency Options , 2004 .

[9]  Kirti Sharma,et al.  Performance Comparison of Machine Learning Platforms , 2019, INFORMS J. Comput..

[10]  Steven Kou,et al.  A Jump Diffusion Model for Option Pricing , 2001, Manag. Sci..

[11]  Yu Zheng.  Machine learning and option implied information , 2017 .

[12]  P. Samuelson.  Proof that Properly Anticipated Prices Fluctuate Randomly , 2015 .

[13]  Alex Weissensteiner,et al.  A $Q$ -Learning Approach to Derive Optimal Consumption and Investment Strategies , 2008, IEEE Transactions on Neural Networks.

[14]  G. Lewicki,et al.  Approximation by Superpositions of a Sigmoidal Function , 2003 .

[15]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[16]  Francesco Audrino,et al.  Semi-parametric forecasts of the implied volatility surface using regression trees , 2010, Stat. Comput..

[17]  T. Andersen,et al.  Short-Term Market Risks Implied by Weekly Options , 2017 .

[18]  Jim Gatheral,et al.  A parsimonious arbitrage-free implied volatility parameterization with application to the valuation of volatility derivatives , 2004 .

[19]  Valeriy V. Gavrishchaka,et al.  Boosting-Based Frameworks in Financial Modeling: Application to Symbolic Volatility Forecasting , 2006 .

[20]  Andrey Itkin,et al.  To sigmoid-based functional description of the volatility smile , 2014, 1407.0256.

[21]  Terrence Hendershott,et al.  Call for Papers—Special Issue of Information Systems Research Fintech – Innovating the Financial Industry Through Emerging Information Technologies , 2017 .

[22]  Nikola Gradojevic,et al.  Option Pricing With Modular Neural Networks , 2009, IEEE Transactions on Neural Networks.

[23]  Wanmo Kang,et al.  Exact Simulation of the Wishart Multidimensional Stochastic Volatility Model , 2013, Oper. Res..

[24]  Judy A. Franklin,et al.  Recurrent Neural Networks for Music Computation , 2006, INFORMS J. Comput..

[25]  Varghese S. Jacob,et al.  An Improved Augmented Neural-Network Approach for Scheduling Problems , 2006, INFORMS J. Comput..

[26]  Hong Luo,et al.  The term structure of implied dividend yields and expected returns , 2015 .

[27]  Olvi L. Mangasarian,et al.  Mathematical Programming in Neural Networks , 1993, INFORMS J. Comput..

[28]  M. Bianchetti,et al.  Everything You Always Wanted to Know About Multiple Interest Rate Curve Bootstrapping but Were Afraid to Ask , 2013 .

[29]  Cristian Homescu.  Implied Volatility Surface: Construction Methodologies and Characteristics , 2011, 1107.1834.

[30]  S. Sundaresan.  Continuous-Time Methods in Finance: A Review and an Assessment , 2000 .

[31]  Kate Smith-Miles,et al.  Neural Networks for Combinatorial Optimization: A Review of More Than a Decade of Research , 1999, INFORMS J. Comput..

[32]  R. Bliss,et al.  Option-Implied Risk Aversion Estimates , 2004 .

[33]  Rama Cont,et al.  Dynamics of implied volatility surfaces , 2002 .

[34]  Desheng Dash Wu,et al.  A Decision Support Approach for Online Stock Forum Sentiment Analysis , 2014, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[35]  Yaser S. Abu-Mostafa,et al.  A Method for Learning From Hints , 1992, NIPS.

[36]  R. C. Merton,et al.  Option pricing when underlying stock returns are discontinuous , 1976 .

[37]  Louis-François Pau,et al.  Artificial Intelligence and Financial Services , 1991, IEEE Trans. Knowl. Data Eng..

[38]  Kyungmin Kim,et al.  Face Generation for Low-Shot Learning Using Generative Adversarial Networks , 2017, 2017 IEEE International Conference on Computer Vision Workshops (ICCVW).

[39]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[40]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[41]  Akihiko Takahashi,et al.  Pricing Average and Spread Options Under Local-Stochastic Volatility Jump-Diffusion Models , 2018, Math. Oper. Res..

[42]  Sylvain Corlay,et al.  B-Spline Techniques for Volatility Modeling , 2013 .

[43]  Jim Gatheral,et al.  Valuation of volatility derivatives as an inverse problem , 2005 .

[44]  Linda Salchenberger,et al.  A neural network model for estimating option prices , 1993, Applied Intelligence.

[45]  Roger Lee.  THE MOMENT FORMULA FOR IMPLIED VOLATILITY AT EXTREME STRIKES , 2004 .

[46]  F. Black,et al.  The Pricing of Options and Corporate Liabilities , 1973, Journal of Political Economy.

[47]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[48]  Cheng Wang,et al.  Stable local volatility function calibration using spline kernel , 2013, Comput. Optim. Appl..

[49]  Santosh S. Vempala,et al.  An Efficient Re-Scaled Perceptron Algorithm for Conic Systems , 2006, Math. Oper. Res..

[50]  Kurt Hornik,et al.  Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.

[51]  Linda Salchenberger,et al.  Using neural networks to forecast the S & P 100 implied volatility , 1996, Neurocomputing.

[52]  Paul G. Harrald,et al.  Evolving artificial neural networks to combine financial forecasts , 1997, IEEE Trans. Evol. Comput..

[53]  S. Heston.  A Closed-Form Solution for Options with Stochastic Volatility with Applications to Bond and Currency Options , 1993 .

[54]  Archil Gulisashvili,et al.  Analytically Tractable Stochastic Stock Price Models , 2012 .

[55]  A. Kotzé,et al.  Arbitrage-Free Implied Volatility Surfaces for Options on Single Stock Futures , 2013 .