Previsão de retornos intradiários através de regressões usando funções-núcleo
Autor(a) principal: | |
---|---|
Data de Publicação: | 2009 |
Tipo de documento: | Artigo |
Idioma: | por |
Título da fonte: | Repositório Institucional do FGV (FGV Repositório Digital) |
Texto Completo: | http://hdl.handle.net/10438/2662 |
Resumo: | The contributions of this paper are twofold. First we discuss and apply a method for the evaluation of non linear regressions in forecasting intraday returns of Brazilian stocks, in order to maximize the return of a simulated trading portfolio. Second, Kernel regressions associated with Nearest Neighbors sample partitioning are carried out. Some independent variables are technical indicators, which parameters are optimized in-the-sample. The results are positive as a trading strategy and outperformed by a small difference the linear autoregression benchmark model in a quartile per quartile analysis |
id |
FGV_c096e6814a7e9c2763a09e0678446e99 |
---|---|
oai_identifier_str |
oai:repositorio.fgv.br:10438/2662 |
network_acronym_str |
FGV |
network_name_str |
Repositório Institucional do FGV (FGV Repositório Digital) |
repository_id_str |
3974 |
spelling |
Pereira, Pedro L. VallsEscolas::EESP2009-06-10T14:21:11Z2009-06-10T14:21:11Z2009-06-10http://hdl.handle.net/10438/2662The contributions of this paper are twofold. First we discuss and apply a method for the evaluation of non linear regressions in forecasting intraday returns of Brazilian stocks, in order to maximize the return of a simulated trading portfolio. Second, Kernel regressions associated with Nearest Neighbors sample partitioning are carried out. Some independent variables are technical indicators, which parameters are optimized in-the-sample. The results are positive as a trading strategy and outperformed by a small difference the linear autoregression benchmark model in a quartile per quartile analysisAs contribuições deste artigo são duas. A primeira, um método de avaliação de regressões não lineares para a previsão de retornos intradiários de ações no mercado brasileiro é discutido e aplicado, com o objetivo de maximizar o retorno de um portfólio simulado de compras e vendas. A segunda, regressões usando funções-núcleo associadas ao particionamento da amostra por vizinhos mais próximos são realizadas. Algumas variáveis independentes utilizadas são indicadores técnicos, cujos parâmetros são otimizados dentro da amostra de estimação. Os resultados alcançados são positivos e superam, em uma análise quartil a quartil, os resultados produzidos por um modelo benchmark de autorregressão linearporTextos para discussão ; 178Intraday returnsKernel regressionNearest neighborsTechnical indicatorsModelos econométricosEconomiaEconomiaPrevisão de retornos intradiários através de regressões usando funções-núcleoinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlereponame:Repositório Institucional do FGV (FGV Repositório Digital)instname:Fundação Getulio Vargas (FGV)instacron:FGVinfo:eu-repo/semantics/openAccessORIGINALTD 178 Pedro Valls.pdfTD 178 Pedro Valls.pdfapplication/pdf289084https://repositorio.fgv.br/bitstreams/46c0242d-e55b-4515-ba99-9684d736a0db/downloadce4bab97bef53b76c4bb1c9c85728ac0MD51LICENSElicense.txtlicense.txttext/plain; charset=utf-81838https://repositorio.fgv.br/bitstreams/33b8a35f-9219-41e9-a943-353ec8bbeac3/download42edde7bb90bf0beec39df2db7fd37f4MD52TEXTTD 178 Pedro Valls.pdf.txtTD 178 Pedro Valls.pdf.txtExtracted texttext/plain72133https://repositorio.fgv.br/bitstreams/0b9a05dc-bd37-4a12-bef6-f0bb37f8ff1b/download92311783686aee55a39e9d27c43fc1e8MD57THUMBNAILTD 178 Pedro Valls.pdf.jpgTD 178 Pedro Valls.pdf.jpgGenerated Thumbnailimage/jpeg3732https://repositorio.fgv.br/bitstreams/cdbcfa55-179b-4e56-9671-4c51c8b8175f/downloadd3078c4c650f59bf8d4fc958501894faMD5810438/26622023-11-08 11:08:15.989open.accessoai:repositorio.fgv.br:10438/2662https://repositorio.fgv.brRepositório InstitucionalPRIhttp://bibliotecadigital.fgv.br/dspace-oai/requestopendoar:39742023-11-08T11:08:15Repositório Institucional do FGV (FGV Repositório Digital) - Fundação Getulio Vargas (FGV)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 |
dc.title.por.fl_str_mv |
Previsão de retornos intradiários através de regressões usando funções-núcleo |
title |
Previsão de retornos intradiários através de regressões usando funções-núcleo |
spellingShingle |
Previsão de retornos intradiários através de regressões usando funções-núcleo Pereira, Pedro L. Valls Intraday returns Kernel regression Nearest neighbors Technical indicators Modelos econométricos Economia Economia |
title_short |
Previsão de retornos intradiários através de regressões usando funções-núcleo |
title_full |
Previsão de retornos intradiários através de regressões usando funções-núcleo |
title_fullStr |
Previsão de retornos intradiários através de regressões usando funções-núcleo |
title_full_unstemmed |
Previsão de retornos intradiários através de regressões usando funções-núcleo |
title_sort |
Previsão de retornos intradiários através de regressões usando funções-núcleo |
author |
Pereira, Pedro L. Valls |
author_facet |
Pereira, Pedro L. Valls |
author_role |
author |
dc.contributor.unidadefgv.por.fl_str_mv |
Escolas::EESP |
dc.contributor.author.fl_str_mv |
Pereira, Pedro L. Valls |
dc.subject.eng.fl_str_mv |
Intraday returns Kernel regression Nearest neighbors Technical indicators |
topic |
Intraday returns Kernel regression Nearest neighbors Technical indicators Modelos econométricos Economia Economia |
dc.subject.por.fl_str_mv |
Modelos econométricos |
dc.subject.area.por.fl_str_mv |
Economia |
dc.subject.bibliodata.por.fl_str_mv |
Economia |
description |
The contributions of this paper are twofold. First we discuss and apply a method for the evaluation of non linear regressions in forecasting intraday returns of Brazilian stocks, in order to maximize the return of a simulated trading portfolio. Second, Kernel regressions associated with Nearest Neighbors sample partitioning are carried out. Some independent variables are technical indicators, which parameters are optimized in-the-sample. The results are positive as a trading strategy and outperformed by a small difference the linear autoregression benchmark model in a quartile per quartile analysis |
publishDate |
2009 |
dc.date.accessioned.fl_str_mv |
2009-06-10T14:21:11Z |
dc.date.available.fl_str_mv |
2009-06-10T14:21:11Z |
dc.date.issued.fl_str_mv |
2009-06-10 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10438/2662 |
url |
http://hdl.handle.net/10438/2662 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.ispartofseries.por.fl_str_mv |
Textos para discussão ; 178 |
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/46c0242d-e55b-4515-ba99-9684d736a0db/download https://repositorio.fgv.br/bitstreams/33b8a35f-9219-41e9-a943-353ec8bbeac3/download https://repositorio.fgv.br/bitstreams/0b9a05dc-bd37-4a12-bef6-f0bb37f8ff1b/download https://repositorio.fgv.br/bitstreams/cdbcfa55-179b-4e56-9671-4c51c8b8175f/download |
bitstream.checksum.fl_str_mv |
ce4bab97bef53b76c4bb1c9c85728ac0 42edde7bb90bf0beec39df2db7fd37f4 92311783686aee55a39e9d27c43fc1e8 d3078c4c650f59bf8d4fc958501894fa |
bitstream.checksumAlgorithm.fl_str_mv |
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_ |
1810023695836512256 |