English

Deep Neural Network Algorithms for Parabolic PIDEs and Applications in Insurance Mathematics

Numerical Analysis 2021-09-27 v2 Numerical Analysis Probability Computational Finance Machine Learning

Abstract

In recent years a large literature on deep learning based methods for the numerical solution partial differential equations has emerged; results for integro-differential equations on the other hand are scarce. In this paper we study deep neural network algorithms for solving linear and semilinear parabolic partial integro-differential equations with boundary conditions in high dimension. To show the viability of our approach we discuss several case studies from insurance and finance.

Keywords

Cite

@article{arxiv.2109.11403,
  title  = {Deep Neural Network Algorithms for Parabolic PIDEs and Applications in Insurance Mathematics},
  author = {Rüdiger Frey and Verena Köck},
  journal= {arXiv preprint arXiv:2109.11403},
  year   = {2021}
}

Comments

24 pages