Journal Articles Monte Carlo Methods and Applications Year : 2021

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 well-known Longstaff and Schwartz algorithm when the standard least-square 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.
Fichier principal
Vignette du fichier
ls-nn.pdf (303.75 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-02183587 , version 1 (15-07-2019)
hal-02183587 , version 2 (10-12-2019)
hal-02183587 , version 3 (27-11-2020)

Identifiers

Cite

Bernard Lapeyre, Jérôme Lelong. Neural network regression for Bermudan option pricing. Monte Carlo Methods and Applications, 2021, 27 (3), pp.227-247. ⟨10.1515/mcma-2021-2091⟩. ⟨hal-02183587v3⟩
905 View
1827 Download

Altmetric

Share

More