IDEAS home Printed from https://ideas.repec.org/a/imx/journl/v20y2025i2a7.html
   My bibliography  Save this article

Portfolio Optimization with Long-Short Term Memory Deep Learning (LSTM)

Author

Listed:
  • Angel Samaniego Alcántar

    (ITESO, México)

Abstract

El objetivo es una metodología para ponderar los activos financieros en una cartera de inversión. Se contrasta con los componentes del Dow Jones Industrial Average (DJIA). Para ello, se estudian carteras con horizontes de inversión entre 1 y 2 años utilizando la optimización Long-Short Term Memory (LSTM). La mejor cartera se obtuvo con un horizonte de inversión de 1.5 años. La red neuronal se entrena con 1 000 observaciones y se simulan más de 2 777 carteras. El modelo supera al DJIA entre un 73% y un 85%, con un diferencial de rentabilidad geométrica media anual entre 3.7% y 5%. Los componentes del DJIA en la historia se utilizan para asignar activos a las carteras entre 2008 a 2021. Se recomienda contrastar la metodología junto con otra metodología de selección de activos financieros. Las conclusiones se limitan a los activos que componen el DJIA. Mayoritariamente en la literatura se utilizan redes neuronales para el corto plazo; en este trabajo se contrasta el modelo para el largo plazo, buscando ponderar activos y no precios futuros de activos. Concluyendo que el modelo LSTM puede utilizarse para este fin, para horizontes de inversión de 1 a 2 años.

Suggested Citation

  • Angel Samaniego Alcántar, 2025. "Portfolio Optimization with Long-Short Term Memory Deep Learning (LSTM)," Remef - Revista Mexicana de Economía y Finanzas Nueva Época REMEF (The Mexican Journal of Economics and Finance), Instituto Mexicano de Ejecutivos de Finanzas, IMEF, vol. 20(2), pages 1-14, Abril - J.
  • Handle: RePEc:imx:journl:v:20:y:2025:i:2:a:7
    as

    Download full text from publisher

    File URL: https://www.remef.org.mx/index.php/remef/article/view/862
    Download Restriction: no
    ---><---

    More about this item

    Keywords

    Artificial neural network; portfolio diversification; deep learning; LSTM;
    All these keywords.

    JEL classification:

    • G11 - Financial Economics - - General Financial Markets - - - Portfolio Choice; Investment Decisions
    • G17 - Financial Economics - - General Financial Markets - - - Financial Forecasting and Simulation

    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:imx:journl:v:20:y:2025:i:2:a:7. 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: Ricardo Mendoza (email available below). General contact details of provider: https://www.remef.org.mx/index.php/remef/index .

    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.