文章基本信息

标题：American option pricing with machine learning An extension of the Longstaff-Schwartz method
本地全文：下载
作者：Jingying Lin ; Caio Almeida
期刊名称：Brazilian Review of Finance
印刷版ISSN：1984-5146
出版年度：2021
卷号：19
期号：3
页码：85-109
DOI：10.12660/rbfin.v19n3.2021.83815
语种：English
出版社：Link to the Brazilian Society of Finance
摘要：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.
关键词：Option pricing; Machine learning; Monte Carlo simulation; Support vector regression; Classification and regression trees