Evaluating Google Trends data to the task of predicting stock returns
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Institucional do FGV (FGV Repositório Digital) |
Texto Completo: | https://hdl.handle.net/10438/31061 |
Resumo: | The problem of predicting financial assets returns is one of the main problems of the empirical finance literature. In particular one of it’s main challenges is to evaluate the usefulness of the so called alternative data to this task. One of the most common alternative datasets is Google Trends data which have gained popularity in recent years. In this work we want to evaluate the usefulness of this data to the task of predicting U.S. stock indices returns. To achieve this goal we break up the problem in two steps: first we employ feature selection methods, and second we employ forecasting models. We use 15 feature selection methods and 10 forecasting models to achieve this goal. In contrast to what the literature have found, we do not found evidence that the Google Trends data contributes to predict the returns of the stock indices in question. The conclusions seems to be robust across feature selection methods, forecasting models, accuracy and risk and return metrics. |
id |
FGV_271e6ce2507193f43652afc9f7444a01 |
---|---|
oai_identifier_str |
oai:repositorio.fgv.br:10438/31061 |
network_acronym_str |
FGV |
network_name_str |
Repositório Institucional do FGV (FGV Repositório Digital) |
repository_id_str |
3974 |
spelling |
Oliveira, Daniel CunhaEscolas::EESPMendonça, Diogo de PrincePereira, Pedro L. VallsFujita, Andre2021-09-09T20:08:46Z2021-09-09T20:08:46Z2021-08-06https://hdl.handle.net/10438/31061The problem of predicting financial assets returns is one of the main problems of the empirical finance literature. In particular one of it’s main challenges is to evaluate the usefulness of the so called alternative data to this task. One of the most common alternative datasets is Google Trends data which have gained popularity in recent years. In this work we want to evaluate the usefulness of this data to the task of predicting U.S. stock indices returns. To achieve this goal we break up the problem in two steps: first we employ feature selection methods, and second we employ forecasting models. We use 15 feature selection methods and 10 forecasting models to achieve this goal. In contrast to what the literature have found, we do not found evidence that the Google Trends data contributes to predict the returns of the stock indices in question. The conclusions seems to be robust across feature selection methods, forecasting models, accuracy and risk and return metrics.A previsão dos retornos de ativos financeiros é um dos principais problemas da literatura de finanças empíricas. Em particular, um dos desafios atuais da literatura é avaliar a utilidade dos chamados dados alternativos para esta tarefa. Um dos dados mais comuns caracterizados como tal são os dados do Google Trends, e este tem alcançado popularidade elevada na literatura. Neste trabalho pretendemos avaliar a utilidade dos dados do Google Trends para a tarefa de previsão de índices de ações americanos. Para atingir este objetivo, separaremos o problema de previsão em duas etapas: primeiro a etapa de seleção de covariaveis, e segundo a etapa de previsão. Utilizamos 15 métodos de seleção de features e 10 métodos de previsão. Ao contrário do que a literatura anterior relatou, nós não encontramos evidencia de que os dados do Google Trends contribui para prever os retornos dos índices de ações estudados. As conclusões parecem ser consistentes entre modelos de seleção de covariaveis, modelos de previsão, e em relação a medidas de acurácia e de risco e retorno.engGoogle TrendsPrecificação de ativosPrevisãoAprendizado de máquinaSéries temporaisEconomiaAções (Finanças) - Preços - PrevisãoAnálise de séries temporaisAprendizado do computadorEvaluating Google Trends data to the task of predicting stock returnsinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisinfo:eu-repo/semantics/openAccessreponame:Repositório Institucional do FGV (FGV Repositório Digital)instname:Fundação Getulio Vargas (FGV)instacron:FGVORIGINALFGV___Master_thesis___Daniel_Oliveira(1).pdfFGV___Master_thesis___Daniel_Oliveira(1).pdfPDFapplication/pdf3183072https://repositorio.fgv.br/bitstreams/d23ebac7-2779-4207-bb47-fc2557ada61b/download93f7ef7fcf5419ff4d1476e88ea70e4bMD55LICENSElicense.txtlicense.txttext/plain; charset=utf-84707https://repositorio.fgv.br/bitstreams/8ae8b6b4-f561-41ff-9bed-aeab112091b8/downloaddfb340242cced38a6cca06c627998fa1MD56TEXTFGV___Master_thesis___Daniel_Oliveira(1).pdf.txtFGV___Master_thesis___Daniel_Oliveira(1).pdf.txtExtracted texttext/plain101351https://repositorio.fgv.br/bitstreams/c4a97ea8-8297-4afe-bf46-c48b675a8fdb/download0b80c5c3ea49029c7dfa5ba861546358MD59THUMBNAILFGV___Master_thesis___Daniel_Oliveira(1).pdf.jpgFGV___Master_thesis___Daniel_Oliveira(1).pdf.jpgGenerated Thumbnailimage/jpeg2348https://repositorio.fgv.br/bitstreams/034f60d6-8656-4ed0-8e39-ef5e2a4c7401/download5e6050582aa20f2c1cafbfe8624764d1MD51010438/310612023-11-25 23:13:43.96restrictedoai:repositorio.fgv.br:10438/31061https://repositorio.fgv.brRepositório InstitucionalPRIhttp://bibliotecadigital.fgv.br/dspace-oai/requestopendoar:39742023-11-25T23:13:43Repositório Institucional do FGV (FGV Repositório Digital) - Fundação Getulio Vargas (FGV)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 |
dc.title.eng.fl_str_mv |
Evaluating Google Trends data to the task of predicting stock returns |
title |
Evaluating Google Trends data to the task of predicting stock returns |
spellingShingle |
Evaluating Google Trends data to the task of predicting stock returns Oliveira, Daniel Cunha Google Trends Precificação de ativos Previsão Aprendizado de máquina Séries temporais Economia Ações (Finanças) - Preços - Previsão Análise de séries temporais Aprendizado do computador |
title_short |
Evaluating Google Trends data to the task of predicting stock returns |
title_full |
Evaluating Google Trends data to the task of predicting stock returns |
title_fullStr |
Evaluating Google Trends data to the task of predicting stock returns |
title_full_unstemmed |
Evaluating Google Trends data to the task of predicting stock returns |
title_sort |
Evaluating Google Trends data to the task of predicting stock returns |
author |
Oliveira, Daniel Cunha |
author_facet |
Oliveira, Daniel Cunha |
author_role |
author |
dc.contributor.unidadefgv.por.fl_str_mv |
Escolas::EESP |
dc.contributor.member.none.fl_str_mv |
Mendonça, Diogo de Prince |
dc.contributor.author.fl_str_mv |
Oliveira, Daniel Cunha |
dc.contributor.advisor1.fl_str_mv |
Pereira, Pedro L. Valls Fujita, Andre |
contributor_str_mv |
Pereira, Pedro L. Valls Fujita, Andre |
dc.subject.eng.fl_str_mv |
Google Trends |
topic |
Google Trends Precificação de ativos Previsão Aprendizado de máquina Séries temporais Economia Ações (Finanças) - Preços - Previsão Análise de séries temporais Aprendizado do computador |
dc.subject.por.fl_str_mv |
Precificação de ativos Previsão Aprendizado de máquina Séries temporais |
dc.subject.area.por.fl_str_mv |
Economia |
dc.subject.bibliodata.por.fl_str_mv |
Ações (Finanças) - Preços - Previsão Análise de séries temporais Aprendizado do computador |
description |
The problem of predicting financial assets returns is one of the main problems of the empirical finance literature. In particular one of it’s main challenges is to evaluate the usefulness of the so called alternative data to this task. One of the most common alternative datasets is Google Trends data which have gained popularity in recent years. In this work we want to evaluate the usefulness of this data to the task of predicting U.S. stock indices returns. To achieve this goal we break up the problem in two steps: first we employ feature selection methods, and second we employ forecasting models. We use 15 feature selection methods and 10 forecasting models to achieve this goal. In contrast to what the literature have found, we do not found evidence that the Google Trends data contributes to predict the returns of the stock indices in question. The conclusions seems to be robust across feature selection methods, forecasting models, accuracy and risk and return metrics. |
publishDate |
2021 |
dc.date.accessioned.fl_str_mv |
2021-09-09T20:08:46Z |
dc.date.available.fl_str_mv |
2021-09-09T20:08:46Z |
dc.date.issued.fl_str_mv |
2021-08-06 |
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/10438/31061 |
url |
https://hdl.handle.net/10438/31061 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
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/d23ebac7-2779-4207-bb47-fc2557ada61b/download https://repositorio.fgv.br/bitstreams/8ae8b6b4-f561-41ff-9bed-aeab112091b8/download https://repositorio.fgv.br/bitstreams/c4a97ea8-8297-4afe-bf46-c48b675a8fdb/download https://repositorio.fgv.br/bitstreams/034f60d6-8656-4ed0-8e39-ef5e2a4c7401/download |
bitstream.checksum.fl_str_mv |
93f7ef7fcf5419ff4d1476e88ea70e4b dfb340242cced38a6cca06c627998fa1 0b80c5c3ea49029c7dfa5ba861546358 5e6050582aa20f2c1cafbfe8624764d1 |
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_ |
1810023704220925952 |