dc.creatorLin, Jingying
dc.creatorAlmeida, Caio
dc.date2021-09-30
dc.date.accessioned2022-11-03T21:00:15Z
dc.date.available2022-11-03T21:00:15Z
dc.identifierhttps://bibliotecadigital.fgv.br/ojs/index.php/rbfin/article/view/83815
dc.identifier.urihttps://repositorioslatinoamericanos.uchile.cl/handle/2250/5044678
dc.descriptionPricing 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.en-US
dc.formatapplication/pdf
dc.languageeng
dc.publisherLociedade Brasileira de Finançasen-US
dc.relationhttps://bibliotecadigital.fgv.br/ojs/index.php/rbfin/article/view/83815/80239
dc.rightsCopyright (c) 2021 Revista Brasileira de Finançaspt-BR
dc.sourceBrazilian Review of Finance; Vol. 19 No. 3 (2021): July-September; 85-109en-US
dc.sourceRevista Brasileira de Finanças; v. 19 n. 3 (2021): Julho-Setembro; 85-109pt-BR
dc.source1984-5146
dc.source1679-0731
dc.subjectOption pricingen-US
dc.subjectMachine learningen-US
dc.subjectMonte Carlo simulationen-US
dc.subjectSupport vector regressionen-US
dc.subjectClassification and regression treesen-US
dc.subjectC52en-US
dc.subjectG13en-US
dc.titleAmerican option pricing with machine learning: An extension of the Longstaff-Schwartz methoden-US
dc.typeinfo:eu-repo/semantics/article
dc.typeinfo:eu-repo/semantics/publishedVersion
dc.typeDouble blind reviewed articlesen-US
dc.typeAvaliado por Parespt-BR


Este ítem pertenece a la siguiente institución