Neural network regression for Bermudan option pricing
Abstract
The pricing of Bermudan options amounts to solving a dynamic programming principle, in which the main difficulty, especially in high dimension, comes from the conditional expectation involved in the computation of the continuation value. These conditional expectations are classically computed by regression techniques on a finite dimensional vector space. In this work, we study neural networks approximations of conditional expectations. We prove the convergence of the wellknown Longstaff and Schwartz algorithm when the standard leastsquare regression is replaced by a neural network approximation. We illustrate the numerical efficiency of neural networks as an alternative to standard regression methods for approximating conditional expectations on several numerical examples.
 Publication:

arXiv eprints
 Pub Date:
 July 2019
 arXiv:
 arXiv:1907.06474
 Bibcode:
 2019arXiv190706474L
 Keywords:

 Mathematics  Probability;
 Quantitative Finance  Computational Finance