WIAS Preprint No. 2530, (2018)

Optimal stopping via deeply boosted backward regression



Authors

  • Belomestny, Denis
  • Schoenmakers, John G. M.
    ORCID: 0000-0002-4389-8266
  • Spokoiny, Vladimir
    ORCID: 0000-0002-2040-3427
  • Tavyrikov, Yuri

2010 Mathematics Subject Classification

  • 60G40 65C05 62J02

Keywords

  • Optimal stopping, nonlinear regression, deep learning

DOI

10.20347/WIAS.PREPRINT.2530

Abstract

In this note we propose a new approach towards solving numerically optimal stopping problems via boosted regression based Monte Carlo algorithms. The main idea of the method is to boost standard linear regression algorithms in each backward induction step by adding new basis functions based on previously estimated continuation values. The proposed methodology is illustrated by several numerical examples from finance.

Download Documents