American option pricing with machine learning: An extension of the Longstaff-Schwartz method

Authors

  • Jingying Lin Princeton University
  • Caio Almeida Princeton University

DOI:

https://doi.org/10.12660/rbfin.v19n3.2021.83815

Keywords:

Option pricing, Machine learning, Monte Carlo simulation, Support vector regression, Classification and regression trees

Abstract

Pricing American options accurately is of great theoretical and practical importance. We propose using machine learning methods, including support vector regression and classification and regression trees. These more advanced techniques extend the traditional Longstaff-Schwartz approach, replacing the OLS regression step in the Monte Carlo simulation. We apply our approach to both simulated data and market data from the S&P 500 Index option market in 2019. Our results suggest that support vector regression can be an alternative to the existing OLS-based pricing method, requiring fewer simulations and reducing the vulnerability to misspecification of basis functions.

Downloads

Published

2021-09-30

Issue

Vol. 19 No. 3 (2021): July-September

Section

Articles

License

Authors that publish in the Brazilian Review of Finance agree with the following terms: Authors maintain their moral rights and grant to Review the copyright and the first publication right with their work simultaneously licensed under a Creative Commons Attribution 3.0 License that allows the total or partial copy of the work, including for commercial use, and sharing of the work with recognition of its authors and the initial publication in this journal. Authors are allowed to take additional contracts separately for non-exclusive distribution of the paper published in this journal (eg, in institutional repositories or to publish as a book chapter), with recognition of its authors and the initial publication in this journal. Authors are permitted and encouraged to post their work online (eg, in institutional repositories or on their website) at any point before or during the submission process, as this can lead to productive exchanges, as well as increase the impact and citation of the published work. The contents of the signed articles are the sole responsibility of the authors, remains their responsibility even after the transfer of the copyright. The Review reserves the right to make normative, spelling and grammar changes in the original article in order to maintain the linguistic standards, but will follow the style of the authors. RBFin also reserves the right to translate the article into another language. RBFin may impose a copyright transfer form as a condition for publishing the article.