IDEAS home Printed from https://ideas.repec.org/a/elt/journl/v70y2003i280p721-744.html
   My bibliography  Save this article

Modelos predictivos de redes neuronales en índices bursátiles

Author

Listed:
  • Parisi F, Antonino

    (Departamento de Administración, Universidad de Chile)

  • Parisi F, Franco

    (Management Departament, Jesse Jones Graduate School of Management, Rice University)

  • Guerrero C., José Luis

    (MacDonough School of Business, Georgetown University)

Abstract

This study analices the neuronal networks models’ capacity to predict the sign of the weekly variations of CAC40, Hang Seng, KLSE, MMX, STI, Dow Jones Industry, S&p500, GDAX, Bovespa, Nikkei225 and FTSE100.The relative performance of the models was measured by the number of correct predictions of the index’s variation sign, on the base of 51 joint out-samples, each one made up of 50 weekly observations. The results proved that the predictive capacity of the models change thought the time, then it is necessary to reestimate the weight of the equation and reconstruct the model period after period. This suggest that an exclusive and unique explanatory model of the stock-exchange indice’s evolution does not exist.// Este estudio analiza la capacidad de los modelos de redes neuronales para predecir el signo de las variaciones semanales de los índices bursátiles CAC40, Hang Seng, KLSE, MMX, STI, Dow Jones Industry, S&P500, GDAX, Bovespa, Nikkei225 y FTSE 100, entendiendo que la predicción de la dirección del movimiento del índice accionario es pertinente para desarrollar estrategias de transacción efectivas (Leung, Daouk y Chen, 2000). Se usaron modelos de redes neuronales de algoritmo de aprendizaje supervisado de programación hacia atrás: el perceptrón multicapa, la red recurrente Jordan- Elman y la red Ward. Por otra parte, el proceso de evaluación se hizo sobre la base de 51 conjuntos extramuestrales, cada uno compuesto por 50 observaciones semanales. En esta etapa, el desempeño relativo de los modelos fue medido por el número de predicciones correctas (hits) del signo de la variación del índice, aplicando para ello la prueba de acierto direccional de Pesaran y Timmermann (1992). Los resultados muestran que la capacidad predictiva de los modelos varía a lo largo del tiempo, por lo que es necesario no sólo recalcular los coeficientes de la ecuación periodo a periodo sino también reelaborar el modelo en sí, por lo que no existiría un único modelo explicativo de la evolución de los índices bursátiles. Finalmente, al comparar los resultados de la red Ward y del modelo ARIMA con los de una estrategia buy and hold se observó que, independientemente de la significancia estadística de la capacidad predictiva, ambas técnicas permitieron aumentar la rentabilidad o reducir las pérdidas.

Suggested Citation

  • Parisi F, Antonino & Parisi F, Franco & Guerrero C., José Luis, 2003. "Modelos predictivos de redes neuronales en índices bursátiles," El Trimestre Económico, Fondo de Cultura Económica, vol. 0(280), pages 721-744, octubre-d.
  • Handle: RePEc:elt:journl:v:70:y:2003:i:280:p:721-744
    as

    Download full text from publisher

    To our knowledge, this item is not available for download. To find whether it is available, there are three options:
    1. Check below whether another version of this item is available online.
    2. Check on the provider's web page whether it is in fact available.
    3. Perform a search for a similarly titled item that would be available.

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Parisi, Antonino & Parisi, Franco & Díaz, David, 2008. "Forecasting gold price changes: Rolling and recursive neural network models," Journal of Multinational Financial Management, Elsevier, vol. 18(5), pages 477-487, December.
    2. Miguel Prado Román & Raúl Gómez Martínez & Miguel Angel Sánchez de Lara, 2018. "La Capacidad de Inversión en el Mercado Alternativo Internacional: ¿Existen Inversiones Seguras?," Revista de Investigación en Ciencias Contables y Administrativas, Universidad Michoacana de San Nicolás de Hidalgo, Facultad de Contaduría y Ciencias Administrativas, vol. 3(2), pages 3-24, August.

    More about this item

    Keywords

    redes neuronales; red Ward; test directional accuracy; capacidad predictiva;
    All these keywords.

    JEL classification:

    • G10 - Financial Economics - - General Financial Markets - - - General (includes Measurement and Data)
    • G14 - Financial Economics - - General Financial Markets - - - Information and Market Efficiency; Event Studies; Insider Trading
    • G15 - Financial Economics - - General Financial Markets - - - International Financial Markets

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:elt:journl:v:70:y:2003:i:280:p:721-744. See general information about how to correct material in RePEc.

    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.

    We have no bibliographic references for this item. You can help adding them by using 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 RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Nuria Pliego Vinageras (email available below). General contact details of provider: http://www.fondodeculturaeconomica.com/ .

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

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.