Ensaios sobre o uso de redes neurais na previsão de taxa de câmbio

Página do item simplificado
dc.contributor.advisorBasso, Leonardo Fernando Cruz
dc.contributor.advisor1Latteshttp://lattes.cnpq.br/1866154361601651por
dc.contributor.authorCosta, Marisa Gomes da
dc.creator.Latteshttp://lattes.cnpq.br/1739721239636939por
dc.date.accessioned2020-07-28T19:30:30Z
dc.date.accessioned2020-12-07T15:05:31Z
dc.date.available2020-12-07T15:05:31Z
dc.date.issued2020-04-24
dc.description.abstractThis study aims to compare and evaluate the predictive power of artificial neural network models on exchange rates. Initially, a bibliometric study and literature review is carried out in order to identify the current research status in the area. Then, an empirical study is propesed to forecast various Exchange rates using data of opening, closing,high and low in daily frequency. The data sample includes exchange rates (BRL / USD, EUR / USD and GBP / USD) from January 2014 to December 2019. Forecasts are made for a period ahead. Different architectures of the LSTM recurrent neural network model were tested. To rank the models in terms of predictive power, the results of the predictions are compared to the prediction of the random walk model, using it as a benchmark, as well as ARIMA. The selection of models is made by the model confidence set (MCS). Lunde and Nason. The results indicated that the LSTM model is superior to the random walk and ARIMA for all analyzed currencies.eng
dc.description.sponsorshipCoordenação de Aperfeiçoamento de Pessoal de Nível Superiorpor
dc.formatapplication/pdf*
dc.identifier.citationCOSTA, Marisa Gomes da. Ensaios sobre o uso de redes neurais na previsão de taxa de câmbio. 2020. 92 f. Tese (Doutorado em Administração de Empresas) - Universidade Presbiteriana Mackenzie, São Paulo, 2020.por
dc.identifier.urihttp://dspace.mackenzie.br/handle/10899/26467
dc.keywordsconfidence set modeleng
dc.keywordsmachine learningeng
dc.keywordsLSTMeng
dc.keywordsneural networkseng
dc.keywordshot topicseng
dc.languageporpor
dc.publisherUniversidade Presbiteriana Mackenziepor
dc.rightsAcesso Abertopor
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectconfidence set modelpor
dc.subjectaprendizagem de máquinapor
dc.subjectLSTMpor
dc.subjectredes neurais recorrentespor
dc.subjecttemas emergentespor
dc.subject.cnpqCNPQ::CIENCIAS SOCIAIS APLICADAS::ADMINISTRACAO::ADMINISTRACAO DE EMPRESASpor
dc.titleEnsaios sobre o uso de redes neurais na previsão de taxa de câmbiopor
dc.typeTesepor
local.contributor.board1Hadad Junior, Eli
local.contributor.board1Latteshttp://lattes.cnpq.br/2030318390506756por
local.contributor.board2Mendonça, Diogo de Prince
local.contributor.board2Latteshttp://lattes.cnpq.br/3160691112817642por
local.contributor.board3Jucá, Michele Nascimento
local.contributor.board3Latteshttp://lattes.cnpq.br/6770985264140454por
local.contributor.board4Kimura, Herbert
local.contributor.board4Latteshttp://lattes.cnpq.br/2048706172366367por
local.publisher.countryBrasilpor
local.publisher.departmentCentro de Ciências Sociais e Aplicadas (CCSA)por
local.publisher.initialsUPMpor
local.publisher.programAdministração de Empresaspor
Arquivos
Pacote Original
Agora exibindo 1 - 1 de 1
Imagem de Miniatura
Nome:
MARISA GOMES DA COSTA.pdf
Tamanho:
2.3 MB
Formato:
Adobe Portable Document Format
Descrição:
Baixar
Coleções
Administração de Empresas - Teses - CCSA Higienópolis