Advanced Search
MyIDEAS: Login to save this paper or follow this series

Aplicacao das Redes Neuronais Artificiais a Deteccao dos Mercados Euronext Mais Rentaveis

Contents:

Author Info

  • Paulo Horta

    ()
    (CMVM)

  • Carlos Mendes

    ()
    (Universidade Nova de Lisboa, Faculdade de Ciencias e Tecnologia)

Registered author(s):

    Abstract

    Com este estudo investigasse a possibilidade de utilizacao de uma rede neuronial artificial na deteccao dos mercados de accoes da Euronext que proporcionam a melhor rendibilidade diaria. A rede, treinada com o algoritmo de Levenberg-Marquardt, recomenda a um investidor hipotetico a escolha do Indice de precos representativo do mercado que se preve que maior rendibilidade oferece no dia de negociacao seguinte. Verifica-se que as recomendacoes da rede superam as rendibilidades dos benchmarks nos primeiros meses de 2007. O teste de Pesaran-Timmermann permite concluir que os resultados obtidos na previsao da direccao dos movimentos dos mercados Euronext (subida ou descida) nao sao devidos ao acaso. De igual modo, a matriz das classificacoes permite concluir que o desempenho do modelo na classificacao diaria de cada mercado em "1º melhor", "2º melhor", "3º melhor" ou "4º melhor", tambem nao e fruto do "acaso maximo" ou do "acaso proporcional". Finalmente, como se utilizou, por um lado, uma rede do tipo feedforward com quatro neuronios na camada de output e, por outro lado, como se efectuou uma experiencia de bootstrap que mostra que as elasticidades dos mercados sao, em geral, estatisticamente significativas, conclui-se que os mercados Euronext estao significativamente relacionados entre si, deixando assim em aberto a possibilidade dos agentes do mercado (v.g. gestores de carteiras) potenciarem a rentabilizacao dos seus investimentos recorrendo a este tipo de modelos neuronais.

    Download Info

    If you experience problems downloading a file, check if you have the proper application to view it first. In case of further problems read the IDEAS help page. Note that these files are not on the IDEAS site. Please be patient as the files may be large.
    File URL: http://www.cefage.uevora.pt/en/content/download/943/12200/version/1/file/2007_05.pdf
    Download Restriction: no

    Bibliographic Info

    Paper provided by University of Evora, CEFAGE-UE (Portugal) in its series CEFAGE-UE Working Papers with number 2007_05.

    as in new window
    Length: 32 pages
    Date of creation: 2007
    Date of revision:
    Handle: RePEc:cfe:wpcefa:2007_05

    Contact details of provider:
    Postal: Colégio Espírito SANTO
    Phone: (351) 266 740 869
    Email:
    Web page: http://www.cefage.uevora.pt
    More information through EDIRC

    Related research

    Keywords: Redes neuronais; feedforward; classificacao; mercados Euronext; bootstrap; avaliacao de performance; estrategias de investimento;

    Find related papers by JEL classification:

    This paper has been announced in the following NEP Reports:

    References

    No references listed on IDEAS
    You can help add them by filling out this form.

    Citations

    Lists

    This item is not listed on Wikipedia, on a reading list or among the top items on IDEAS.

    Statistics

    Access and download statistics

    Corrections

    When requesting a correction, please mention this item's handle: RePEc:cfe:wpcefa:2007_05. See general information about how to correct material in RePEc.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Angela Pacheco).

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If references are entirely missing, you can add them using this form.

    If the full references list an item that is present in RePEc, but the system did not link to it, you can help with this form.

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your profile, as there may be some citations waiting for confirmation.

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.