On the classification of financial data with domain agnostic features

Detalhes bibliográficos
Autor(a) principal: Bastos, João A.
Data de Publicação: 2021
Outros Autores: Caiado, Jorge
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10400.5/21676
Resumo: We compare a data-driven domain agnostic set of canonical features with a smaller collection of features that capture well-known stylized facts about financial asset returns. We show that these facts discriminate better different asset types than general-purpose features. Therefore, financial time series analysis is a domain where well-informed expert knowledge may not be disregarded in favor of agnostic representations of the data.
id RCAP_effddb9911ec8b2c641e8529ce247f95
oai_identifier_str oai:www.repository.utl.pt:10400.5/21676
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling On the classification of financial data with domain agnostic featuresFinancial economicsTime seriesClusteringClassificationMachine learningWe compare a data-driven domain agnostic set of canonical features with a smaller collection of features that capture well-known stylized facts about financial asset returns. We show that these facts discriminate better different asset types than general-purpose features. Therefore, financial time series analysis is a domain where well-informed expert knowledge may not be disregarded in favor of agnostic representations of the data.ISEG - REM - Research in Economics and MathematicsRepositório da Universidade de LisboaBastos, João A.Caiado, Jorge2021-07-27T14:29:54Z2021-072021-07-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://hdl.handle.net/10400.5/21676engBastos, João A. e Jorge Caiado (2021). "On the classification of financial data with domain agnostic features". Instituto Superior de Economia e Gestão – REM Working paper nº 0185 – 20212184-108Xinfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-03-06T14:51:13Zoai:www.repository.utl.pt:10400.5/21676Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T17:06:13.278386Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv On the classification of financial data with domain agnostic features
title On the classification of financial data with domain agnostic features
spellingShingle On the classification of financial data with domain agnostic features
Bastos, João A.
Financial economics
Time series
Clustering
Classification
Machine learning
title_short On the classification of financial data with domain agnostic features
title_full On the classification of financial data with domain agnostic features
title_fullStr On the classification of financial data with domain agnostic features
title_full_unstemmed On the classification of financial data with domain agnostic features
title_sort On the classification of financial data with domain agnostic features
author Bastos, João A.
author_facet Bastos, João A.
Caiado, Jorge
author_role author
author2 Caiado, Jorge
author2_role author
dc.contributor.none.fl_str_mv Repositório da Universidade de Lisboa
dc.contributor.author.fl_str_mv Bastos, João A.
Caiado, Jorge
dc.subject.por.fl_str_mv Financial economics
Time series
Clustering
Classification
Machine learning
topic Financial economics
Time series
Clustering
Classification
Machine learning
description We compare a data-driven domain agnostic set of canonical features with a smaller collection of features that capture well-known stylized facts about financial asset returns. We show that these facts discriminate better different asset types than general-purpose features. Therefore, financial time series analysis is a domain where well-informed expert knowledge may not be disregarded in favor of agnostic representations of the data.
publishDate 2021
dc.date.none.fl_str_mv 2021-07-27T14:29:54Z
2021-07
2021-07-01T00:00:00Z
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/10400.5/21676
url http://hdl.handle.net/10400.5/21676
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv Bastos, João A. e Jorge Caiado (2021). "On the classification of financial data with domain agnostic features". Instituto Superior de Economia e Gestão – REM Working paper nº 0185 – 2021
2184-108X
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv ISEG - REM - Research in Economics and Mathematics
publisher.none.fl_str_mv ISEG - REM - Research in Economics and Mathematics
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799131155050528768

Registros relacionados