Deep neural network framework based on backward stochastic differential equations for pricing and hedging American options in high dimensions

References

• Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., Kudlur, M., Levenberg, J., Monga, R., Moore, S., Murray, D.G., Steiner, B., Tucker, P., Vasudevan, V., Warden, P., Wicke, M., Yu, Y., Zheng, X. and Google Brain, Tensorflow: A system for large-scale machine learning. In Proceedings of the OSDI, Savannah, GA, USA, Vol. 16, pp. 265–283, 2016.
   Google Scholar
• Achdou, Y. and Pironneau, O., Computational methods for option pricing. In Frontiers in Applied Mathematics, Vol. 30, 2005 (Society for Industrial and Applied Mathematics (SIAM): Philadelphia, PA).
   Google Scholar
• Beck, C., E, W. and Jentzen, A., Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations. J. Nonlinear Sci., 2019, 29, 1563–1619. doi: 10.1007/s00332-018-9525-3
   Web of Science ®Google Scholar
• Becker, S., Cheridito, P. and Jentzen, A., Deep optimal stopping. J. Mach. Learn. Res., 2019a, 20, 1–25.
   Web of Science ®Google Scholar
• Becker, S., Cheridito, P., Jentzen, A. and Welti, T., Solving high-dimensional optimal stopping problems using deep learning. Preprint, 2019b. arXiv:1908.01602.
   Google Scholar
• Bouchard, B. and Warin, X., Monte-Carlo valuation of American options: Facts and new algorithms to improve existing methods. In Numerical Methods in Finance, Vol. 12 of Springer proc. math., pp. 215–255, 2012 (Springer: Heidelberg).
   Google Scholar
• Broadie, M. and Glasserman, P., Estimating security price derivatives using simulation. Manage. Sci., 1996, 42, 269–285. doi: 10.1287/mnsc.42.2.269
   Web of Science ®Google Scholar
• Broadie, M. and Glasserman, P., Pricing American-style securities using simulation. J. Econom. Dynam. Control, 1997, 21, 1323–1352. Computational financial modelling. doi: 10.1016/S0165-1889(97)00029-8
   Web of Science ®Google Scholar
• Broadie, M. and Glasserman, P., A stochastic mesh method for pricing high-dimensional American options. J. Comput. Finance, 2004, 7, 35–72. doi: 10.21314/JCF.2004.117
   Google Scholar
• Duffy, D.J., Finite Difference Methods in Financial Engineering, Wiley finance series, 2006 (John Wiley & Sons, Ltd.: Chichester). A partial differential equation approach, With 1 CD-ROM (Windows, Macintosh and UNIX).
   Google Scholar
• E, W., Han, J. and Jentzen, A., Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations. Commun. Math. Stat., 2017, 5, 349–380. doi: 10.1007/s40304-017-0117-6
   Web of Science ®Google Scholar
• El Karoui, N., Peng, S. and Quenez, M.C., Backward stochastic differential equations in finance. Math. Finance, 1997, 7, 1–71. doi: 10.1111/1467-9965.00022
   Web of Science ®Google Scholar
• Firth, N.P., High dimensional American options. PhD Thesis, University of Oxford, 2005.
   Google Scholar
• Forsyth, P.A. and Vetzal, K.R., Quadratic convergence for valuing American options using a penalty method. SIAM J. Sci. Comput., 2002, 23, 2095–2122. doi: 10.1137/S1064827500382324
   Web of Science ®Google Scholar
• Forsyth, P., An introduction to computational finance without agonizing pain, 2017.
   Google Scholar
• Fujii, M., Takahashi, A. and Takahashi, M., Asymptotic expansion as prior knowledge in deep learning method for high dimensional BSDEs. Preprint, 2017. arXiv:1710.07030.
   Google Scholar
• Glasserman, P., Monte Carlo Methods in Financial Engineering, Applications of mathematics (New York) Vol. 53, 2004 (Springer-Verlag: New York). Stochastic Modelling and Applied Probability.
   Google Scholar
• Goodfellow, I., Bengio, Y. and Courville, A., Deep Learning, Adaptive computation and machine learning, 2016 (MIT Press: Cambridge, MA).
   Google Scholar
• Han, J., Jentzen, A. and E, W., Solving high-dimensional partial differential equations using deep learning. Proc. Natl. Acad. Sci. USA, 2018, 115, 8505–8510. doi: 10.1073/pnas.1718942115
   PubMed Web of Science ®Google Scholar
• Haugh, M.B. and Kogan, L., Pricing American options: A duality approach. Oper. Res., 2004, 52, 258–270. doi: 10.1287/opre.1030.0070
   Web of Science ®Google Scholar
• He, C., Kennedy, J.S., Coleman, T.F., Forsyth, P.A., Li, Y. and Vetzal, K.R., Calibration and hedging under jump diffusion. Rev. Deriv. Res., 2006, 9, 1–35. doi: 10.1007/s11147-006-9003-1
   Google Scholar
• He, K., Zhang, X., Ren, S. and Sun, J., Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, pp. 770–778, 2016.
   Google Scholar
• Heston, S. and Zhou, G., On the rate of convergence of discrete-time contingent claims. Math. Finance, 2000, 10, 53–75. doi: 10.1111/1467-9965.00080
   Web of Science ®Google Scholar
• Hull, J.C., Options Futures and Other Derivatives, 2003 (Pearson/Prentice Hall: Upper Saddle River, NJ).
   Google Scholar
• Huré, C., Pham, H. and Warin, X., Some machine learning schemes for high-dimensional nonlinear PDEs. Preprint, 2019. arXiv:1902.01599.
   Google Scholar
• Kennedy, J.S., Forsyth, P.A. and Vetzal, K.R., Dynamic hedging under jump diffusion with transaction costs. Oper. Res., 2009, 57, 541–559. doi: 10.1287/opre.1080.0598
   Web of Science ®Google Scholar
• Kingma, D.P. and Ba, J., Adam: A method for stochastic optimization. Preprint, 2014. arXiv:1412.6980.
   Google Scholar
• Kohler, M., A review on regression-based Monte Carlo methods for pricing American options. In Recent Developments in Applied Probability and Statistics, pp. 37–58, 2010 (Springer: Berlin, Heidelberg).
   Google Scholar
• Kohler, M., Krzyżak, A. and Todorovic, N., Pricing of high-dimensional American options by neural networks. Math. Finance, 2010, 20, 383–410. doi: 10.1111/j.1467-9965.2010.00404.x
   Web of Science ®Google Scholar
• Leentvaar, C.C.W., Pricing multi-asset options with sparse grids, 2008.
   Google Scholar
• Longstaff, F.A. and Schwartz, E.S., Valuing American options by simulation: A simple least-squares approach. Rev. Financ. Stud., 2001, 14, 113–147. doi: 10.1093/rfs/14.1.113
   Web of Science ®Google Scholar
• Murphy, K.P., Machine Learning: A Probabilistic Perspective, 2012 (MIT Press: Cambridge, MA).
   Google Scholar
• Sirignano, J. and Spiliopoulos, K., DGM: A deep learning algorithm for solving partial differential equations. J. Comput. Phys., 2018, 375, 1339–1364. doi: 10.1016/j.jcp.2018.08.029
   Web of Science ®Google Scholar
• Sola, J. and Sevilla, J., Importance of input data normalization for the application of neural networks to complex industrial problems. IEEE Trans. Nucl. Sci., 1997, 44, 1464–1468. doi: 10.1109/23.589532
   Web of Science ®Google Scholar
• Stentoft, L., Convergence of the least squares Monte Carlo approach to American option valuation. Manage. Sci., 2004, 50, 1193–1203. doi: 10.1287/mnsc.1030.0155
   Web of Science ®Google Scholar
• Thom, H., Longstaff Schwartz pricing of Bermudan options and their Greeks, 2009.
   Google Scholar
• Tsitsiklis, J.N. and Van Roy, B., Optimal stopping of Markov processes: Hilbert space theory, approximation algorithms, and an application to pricing high-dimensional financial derivatives. IEEE Trans. Automat. Control, 1999, 44, 1840–1851. doi: 10.1109/9.793723
   Web of Science ®Google Scholar