Journal of Computational Finance

Toward a unified implementation of regression Monte Carlo algorithms

Mike Ludkovski

  • We introduce a computational template for employing the machine learning paradigm for optimal stopping problems, implemented in the companion R package.
  • The mlOSP template nests many extant algorithms and proposes new variants for simulation design, as well as several novel regression modules.
  • We present a fully documented and reproducible benchmarking suite of 9 instances of Bermudan option pricing compared across 10 different solvers.
  • We treat an extension to multiple-stopping problems, including swing option pricing.

We introduce mlOSP, a computational template for machine learning for optimal stopping problems, which is implemented in the R statistical environment and publicly available via a GitHub repository. mlOSP presents a unified numerical implementation of regression Monte Carlo (RMC) approaches to optimal stopping, providing a state-of-the-art, open-source, reproducible and transparent platform. Highlighting the modular nature of the platform, we present multiple novel variants of RMC algorithms, both in terms of constructing simulation designs for training the regressors and in terms of machine learning regression modules. Further, mlOSP nests most of the existing RMC schemes, allowing for a consistent and verifiable benchmarking of extant algorithms. The paper contains extensive R code snippets and figures and serves as a vignette of the underlying software package.

Sorry, our subscription options are not loading right now

Please try again later. Get in touch with our customer services team if this issue persists.

New to View our subscription options

You need to sign in to use this feature. If you don’t have a account, please register for a trial.

Sign in
You are currently on corporate access.

To use this feature you will need an individual account. If you have one already please sign in.

Sign in.

Alternatively you can request an individual account here