Deep Learning-Based Least Square Forward-Backward Stochastic Differential Equation Solver for High-Dimensional Derivative Pricing

We propose a new forward-backward stochastic differential equation solver for high-dimensional derivatives pricing problems by combining deep learning solver with least square regression technique widely used in the least square Monte Carlo method for the valuation of American options. Our numerical experiments demonstrate the efficiency and accuracy of our least square backward deep neural network solver and its capability to provide accurate prices for complex early exercise derivatives such as callable yield notes. Our method can serve as a generic numerical solver for pricing derivatives across various asset groups, in particular, as an efficient means for pricing high-dimensional derivatives with early exercises features.

[1]  Maziar Raissi,et al.  Forward-Backward Stochastic Neural Networks: Deep Learning of High-dimensional Partial Differential Equations , 2018, ArXiv.

[2]  G. N. Mil’shtejn.  Approximate Integration of Stochastic Differential Equations , 1975 .

[3]  Wim Schoutens,et al.  Machine learning for quantitative finance: fast derivative pricing, hedging and fitting , 2018, Quantitative Finance.

[4]  Sunil Kumar,et al.  Optimizations in financial engineering: The Least-Squares Monte Carlo method of Longstaff and Schwartz , 2008, 2008 IEEE International Symposium on Parallel and Distributed Processing.

[5]  Francis A. Longstaff,et al.  Valuing American Options by Simulation: A Simple Least-Squares Approach , 2001 .

[6]  P. Glasserman,et al.  A Sotchastic Mesh Method for Pricing High-Dimensional American Options , 2004 .

[7]  Agus Sudjianto,et al.  Deep Learning-Based BSDE Solver for Libor Market Model with Applications to Bermudan Swaption Pricing and Hedging , 2018, 1807.06622.

[8]  Yuh-Dauh Lyuu,et al.  Accelerating the least-square Monte Carlo method with parallel computing , 2015, The Journal of Supercomputing.

[9]  Konstantinos Spiliopoulos,et al.  Stochastic Gradient Descent in Continuous Time , 2016, SIAM J. Financial Math..

[10]  Seunggyu Lee,et al.  A practical finite difference method for the three-dimensional Black-Scholes equation , 2016, Eur. J. Oper. Res..

[11]  Akihiko Takahashi,et al.  Asymptotic Expansion as Prior Knowledge in Deep Learning Method for High dimensional BSDEs , 2017, Asia-Pacific Financial Markets.

[12]  Sebastian Becker,et al.  Solving stochastic differential equations and Kolmogorov equations by means of deep learning , 2018, ArXiv.

[13]  A. Krzyżak,et al.  PRICING OF HIGH‐DIMENSIONAL AMERICAN OPTIONS BY NEURAL NETWORKS , 2010 .

[14]  Jérôme Barraquand,et al.  Numerical Valuation of High Dimensional Multivariate American Securities , 1995, Journal of Financial and Quantitative Analysis.

[15]  Justin A. Sirignano,et al.  DGM: A deep learning algorithm for solving partial differential equations , 2017, J. Comput. Phys..

[16]  Lars Stentoft.  Assessing the Least Squares Monte-Carlo Approach to American Option Valuation , 2004 .

[17]  Manuel Moreno,et al.  On the Robustness of Least-Squares Monte Carlo (LSM) for Pricing American Derivatives , 2007 .

[18]  Ali Al-Aradi,et al.  Solving Nonlinear and High-Dimensional Partial Differential Equations via Deep Learning , 2018, 1811.08782.

[19]  E Weinan,et al.  Deep Learning-Based Numerical Methods for High-Dimensional Parabolic Partial Differential Equations and Backward Stochastic Differential Equations , 2017, Communications in Mathematics and Statistics.

[20]  Arnulf Jentzen,et al.  Solving high-dimensional partial differential equations using deep learning , 2017, Proceedings of the National Academy of Sciences.