Uso de modelos de Machine Learning em Asset Pricing: Um estudo do cross section de retornos brasileiro
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Tipo de documento: | Dissertação |
Idioma: | por |
Título da fonte: | Repositório Institucional do FGV (FGV Repositório Digital) |
Texto Completo: | https://hdl.handle.net/10438/32352 |
Resumo: | Este trabalho busca investigar se os modelos de machine learning, Least Absolute Shrinkage and Selection Operator (LASSO) e Principal Component Regression (PCR) sao capazes de contribuir para a explicação do cross section de retornos para o mercado brasileiro. Para o estudo foram coletados dados da bolsa de valores oficial do Brasil, a B3, de maio de 2012 até maio de 2021, selecionando 16 fatores e características, documentados na literatura como variáveis explicativas para retornos mensais de portfolios. O desempenho de cada modelo foi avaliado por meio do coeficiente de determinação R², dentro e fora da amostra. Os resultados obtidos sugerem que os modelos utilizados apresentaram elevado poder de explicação para os portfolios avaliados. |
id |
FGV_fd121be44f30ca2105a506c2c784c79f |
---|---|
oai_identifier_str |
oai:repositorio.fgv.br:10438/32352 |
network_acronym_str |
FGV |
network_name_str |
Repositório Institucional do FGV (FGV Repositório Digital) |
repository_id_str |
3974 |
spelling |
Cardoso, Gabriel BrumEscolas::EPGEFreire, Gustavo Bulhões Carvalho da PazFernandes, MarceloIachan, Felipe Saraiva2022-08-12T13:39:23Z2022-08-12T13:39:23Z2022-04-25https://hdl.handle.net/10438/32352Este trabalho busca investigar se os modelos de machine learning, Least Absolute Shrinkage and Selection Operator (LASSO) e Principal Component Regression (PCR) sao capazes de contribuir para a explicação do cross section de retornos para o mercado brasileiro. Para o estudo foram coletados dados da bolsa de valores oficial do Brasil, a B3, de maio de 2012 até maio de 2021, selecionando 16 fatores e características, documentados na literatura como variáveis explicativas para retornos mensais de portfolios. O desempenho de cada modelo foi avaliado por meio do coeficiente de determinação R², dentro e fora da amostra. Os resultados obtidos sugerem que os modelos utilizados apresentaram elevado poder de explicação para os portfolios avaliados.This paper investigates whether the use of machine learning, Least Absolute Shrinkage and Selection Operator (LASSO), and Principal Component Regression (PCR) are capable to im- prove on the explanation power of the cross-section returns to Brazilian markets. We collected data from the official Brazilian stock market, B3, from May 2012 to May 2021, selecting 15 factors and characteristics well known in the international literature as an explanatory variable for portfolios' monthly returns. Each model was evaluated using the coefficient of determination, R², inside the sample and out of the sample. Our results suggest that the models used were able to show a high explanatory power for the evaluated portfolios.porAsset PricingLASSOMachine LearningPrincipal ComponentRetornosModelo de precificação de ativosAprendizado do computadorAnálise de componentes principaisMercado de açõesEstudos transversaisUso de modelos de Machine Learning em Asset Pricing: Um estudo do cross section de retornos brasileiroinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesis2022-04-25info:eu-repo/semantics/openAccessreponame:Repositório Institucional do FGV (FGV Repositório Digital)instname:Fundação Getulio Vargas (FGV)instacron:FGVLICENSElicense.txtlicense.txttext/plain; charset=utf-84707https://repositorio.fgv.br/bitstreams/05bb2d8e-5a8a-4ff5-9e4e-fc6738ae5bfb/downloaddfb340242cced38a6cca06c627998fa1MD54ORIGINALPDFPDFapplication/pdf5113975https://repositorio.fgv.br/bitstreams/713a6467-9889-4d60-91ea-b5949d012870/download533e1446b66d3a2773134935feb4ad7eMD53TEXTDissertação Mestrado Gabriel Brum Cardoso EPGE.pdf.txtDissertação Mestrado Gabriel Brum Cardoso EPGE.pdf.txtExtracted texttext/plain3013https://repositorio.fgv.br/bitstreams/2578d3c4-9281-4cc6-a0ab-6db32d6e8936/download590263782ef576d91373333c2cf90b7fMD57PDF.txtPDF.txtExtracted texttext/plain3013https://repositorio.fgv.br/bitstreams/e317d220-a1e2-4c53-a592-7d7c286c930c/download590263782ef576d91373333c2cf90b7fMD59THUMBNAILDissertação Mestrado Gabriel Brum Cardoso EPGE.pdf.jpgDissertação Mestrado Gabriel Brum Cardoso EPGE.pdf.jpgGenerated Thumbnailimage/jpeg3403https://repositorio.fgv.br/bitstreams/22ca97b7-d9be-4f22-9178-fcdd74ee5703/download1f9970dffc91a25e74bdd05cb6422cd1MD58PDF.jpgPDF.jpgGenerated Thumbnailimage/jpeg3403https://repositorio.fgv.br/bitstreams/046eeab6-2ae3-4ec7-8ead-f27683ac8e5b/download1f9970dffc91a25e74bdd05cb6422cd1MD51010438/323522024-07-08 18:39:06.582open.accessoai:repositorio.fgv.br:10438/32352https://repositorio.fgv.brRepositório InstitucionalPRIhttp://bibliotecadigital.fgv.br/dspace-oai/requestopendoar:39742024-07-08T18:39:06Repositório Institucional do FGV (FGV Repositório Digital) - Fundação Getulio Vargas (FGV)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 |
dc.title.por.fl_str_mv |
Uso de modelos de Machine Learning em Asset Pricing: Um estudo do cross section de retornos brasileiro |
title |
Uso de modelos de Machine Learning em Asset Pricing: Um estudo do cross section de retornos brasileiro |
spellingShingle |
Uso de modelos de Machine Learning em Asset Pricing: Um estudo do cross section de retornos brasileiro Cardoso, Gabriel Brum Asset Pricing LASSO Machine Learning Principal Component Retornos Modelo de precificação de ativos Aprendizado do computador Análise de componentes principais Mercado de ações Estudos transversais |
title_short |
Uso de modelos de Machine Learning em Asset Pricing: Um estudo do cross section de retornos brasileiro |
title_full |
Uso de modelos de Machine Learning em Asset Pricing: Um estudo do cross section de retornos brasileiro |
title_fullStr |
Uso de modelos de Machine Learning em Asset Pricing: Um estudo do cross section de retornos brasileiro |
title_full_unstemmed |
Uso de modelos de Machine Learning em Asset Pricing: Um estudo do cross section de retornos brasileiro |
title_sort |
Uso de modelos de Machine Learning em Asset Pricing: Um estudo do cross section de retornos brasileiro |
author |
Cardoso, Gabriel Brum |
author_facet |
Cardoso, Gabriel Brum |
author_role |
author |
dc.contributor.unidadefgv.por.fl_str_mv |
Escolas::EPGE |
dc.contributor.member.none.fl_str_mv |
Freire, Gustavo Bulhões Carvalho da Paz Fernandes, Marcelo |
dc.contributor.author.fl_str_mv |
Cardoso, Gabriel Brum |
dc.contributor.advisor1.fl_str_mv |
Iachan, Felipe Saraiva |
contributor_str_mv |
Iachan, Felipe Saraiva |
dc.subject.eng.fl_str_mv |
Asset Pricing LASSO Machine Learning Principal Component |
topic |
Asset Pricing LASSO Machine Learning Principal Component Retornos Modelo de precificação de ativos Aprendizado do computador Análise de componentes principais Mercado de ações Estudos transversais |
dc.subject.por.fl_str_mv |
Retornos |
dc.subject.bibliodata.por.fl_str_mv |
Modelo de precificação de ativos Aprendizado do computador Análise de componentes principais Mercado de ações Estudos transversais |
description |
Este trabalho busca investigar se os modelos de machine learning, Least Absolute Shrinkage and Selection Operator (LASSO) e Principal Component Regression (PCR) sao capazes de contribuir para a explicação do cross section de retornos para o mercado brasileiro. Para o estudo foram coletados dados da bolsa de valores oficial do Brasil, a B3, de maio de 2012 até maio de 2021, selecionando 16 fatores e características, documentados na literatura como variáveis explicativas para retornos mensais de portfolios. O desempenho de cada modelo foi avaliado por meio do coeficiente de determinação R², dentro e fora da amostra. Os resultados obtidos sugerem que os modelos utilizados apresentaram elevado poder de explicação para os portfolios avaliados. |
publishDate |
2022 |
dc.date.accessioned.fl_str_mv |
2022-08-12T13:39:23Z |
dc.date.available.fl_str_mv |
2022-08-12T13:39:23Z |
dc.date.issued.fl_str_mv |
2022-04-25 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://hdl.handle.net/10438/32352 |
url |
https://hdl.handle.net/10438/32352 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional do FGV (FGV Repositório Digital) instname:Fundação Getulio Vargas (FGV) instacron:FGV |
instname_str |
Fundação Getulio Vargas (FGV) |
instacron_str |
FGV |
institution |
FGV |
reponame_str |
Repositório Institucional do FGV (FGV Repositório Digital) |
collection |
Repositório Institucional do FGV (FGV Repositório Digital) |
bitstream.url.fl_str_mv |
https://repositorio.fgv.br/bitstreams/05bb2d8e-5a8a-4ff5-9e4e-fc6738ae5bfb/download https://repositorio.fgv.br/bitstreams/713a6467-9889-4d60-91ea-b5949d012870/download https://repositorio.fgv.br/bitstreams/2578d3c4-9281-4cc6-a0ab-6db32d6e8936/download https://repositorio.fgv.br/bitstreams/e317d220-a1e2-4c53-a592-7d7c286c930c/download https://repositorio.fgv.br/bitstreams/22ca97b7-d9be-4f22-9178-fcdd74ee5703/download https://repositorio.fgv.br/bitstreams/046eeab6-2ae3-4ec7-8ead-f27683ac8e5b/download |
bitstream.checksum.fl_str_mv |
dfb340242cced38a6cca06c627998fa1 533e1446b66d3a2773134935feb4ad7e 590263782ef576d91373333c2cf90b7f 590263782ef576d91373333c2cf90b7f 1f9970dffc91a25e74bdd05cb6422cd1 1f9970dffc91a25e74bdd05cb6422cd1 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional do FGV (FGV Repositório Digital) - Fundação Getulio Vargas (FGV) |
repository.mail.fl_str_mv |
|
_version_ |
1810023615670779904 |