<?xml version="1.0" encoding="ISO-8859-1"?><article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
<front>
<journal-meta>
<journal-id>1665-5346</journal-id>
<journal-title><![CDATA[Revista mexicana de economía y finanzas]]></journal-title>
<abbrev-journal-title><![CDATA[Rev. mex. econ. finanz]]></abbrev-journal-title>
<issn>1665-5346</issn>
<publisher>
<publisher-name><![CDATA[Instituto Mexicano de Ejecutivos de Finanzas A.C.]]></publisher-name>
</publisher>
</journal-meta>
<article-meta>
<article-id>S1665-53462025000200007</article-id>
<article-id pub-id-type="doi">10.21919/remef.v20i2.862</article-id>
<title-group>
<article-title xml:lang="en"><![CDATA[Portfolio Optimization with Long-Short Term Memory Deep Learning (LSTM)]]></article-title>
<article-title xml:lang="es"><![CDATA[Optimización de carteras con Aprendizaje Profundo de memoria a largo y corto plazo (LSTM)]]></article-title>
</title-group>
<contrib-group>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Samaniego Alcántar]]></surname>
<given-names><![CDATA[Ángel]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
</contrib-group>
<aff id="Af1">
<institution><![CDATA[,Instituto Tecnologico y de Estudios Superiores de Occidente  ]]></institution>
<addr-line><![CDATA[ ]]></addr-line>
<country>Mexico</country>
</aff>
<pub-date pub-type="pub">
<day>00</day>
<month>06</month>
<year>2025</year>
</pub-date>
<pub-date pub-type="epub">
<day>00</day>
<month>06</month>
<year>2025</year>
</pub-date>
<volume>20</volume>
<numero>2</numero>
<copyright-statement/>
<copyright-year/>
<self-uri xlink:href="http://www.scielo.org.mx/scielo.php?script=sci_arttext&amp;pid=S1665-53462025000200007&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.mx/scielo.php?script=sci_abstract&amp;pid=S1665-53462025000200007&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.mx/scielo.php?script=sci_pdf&amp;pid=S1665-53462025000200007&amp;lng=en&amp;nrm=iso"></self-uri><abstract abstract-type="short" xml:lang="en"><p><![CDATA[Abstract The objective is a methodology for weighting financial assets in an investment portfolio. It is contrasted by the components of the Dow Jones Industrial Average (DJIA). For this purpose, portfolios with investment horizons between 1 and 2 years are studied using Long-Short Term Memory (LSTM) optimization. The best portfolio was with an investment horizon of 1.5 years. The neural network is trained with 1,000 observations and more than 2,777 portfolios are simulated. The model outperforms the DJIA by 73% to 85%, with a geometric mean annual return differential between 3.7% and 5%. The components of the DJIA in history are used to allocate assets to portfolios between 2008 and 2021. It is recommended that the methodology be contrasted in conjunction with another methodology for selecting financial assets. The conclusions are limited to assets that make up the DJIA. Mostly in the literature, neural networks are used for the short term; this paper contrasts the model to the long term, seeking to weigh assets and not future asset prices. The conclusion is that the LSTM model can be used for this purpose, for investment horizons of 1 to 2 years.]]></p></abstract>
<abstract abstract-type="short" xml:lang="es"><p><![CDATA[Resumen 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.]]></p></abstract>
<kwd-group>
<kwd lng="en"><![CDATA[G11]]></kwd>
<kwd lng="en"><![CDATA[G17]]></kwd>
<kwd lng="en"><![CDATA[C61]]></kwd>
<kwd lng="en"><![CDATA[Artificial neural network]]></kwd>
<kwd lng="en"><![CDATA[portfolio diversification]]></kwd>
<kwd lng="en"><![CDATA[deep learning]]></kwd>
<kwd lng="en"><![CDATA[LSTM]]></kwd>
<kwd lng="es"><![CDATA[E12]]></kwd>
<kwd lng="es"><![CDATA[C50]]></kwd>
<kwd lng="es"><![CDATA[P10]]></kwd>
<kwd lng="es"><![CDATA[Red neuronal artificial]]></kwd>
<kwd lng="es"><![CDATA[diversificación de portafolios]]></kwd>
<kwd lng="es"><![CDATA[Aprendizaje profundo]]></kwd>
<kwd lng="es"><![CDATA[LSTM]]></kwd>
</kwd-group>
</article-meta>
</front><back>
<ref-list>
<ref id="B1">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Amenc]]></surname>
<given-names><![CDATA[N.]]></given-names>
</name>
<name>
<surname><![CDATA[Le Sourd]]></surname>
<given-names><![CDATA[V.]]></given-names>
</name>
</person-group>
<source><![CDATA[Portfolio theory and performance analysis]]></source>
<year>2003</year>
<publisher-loc><![CDATA[Great Britain ]]></publisher-loc>
<publisher-name><![CDATA[Wiley]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B2">
<nlm-citation citation-type="book">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Andersson]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Mirkhani]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
</person-group>
<source><![CDATA[Portfolio Performance Optimization Using Multivariate Time Series Volatilities Processed With Deep Layering LSTM Neurons and Markowitz]]></source>
<year>2020</year>
<publisher-name><![CDATA[KTH Royal Institute of Technology School of Engineering Sciences]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B3">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Borovkova]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Tsiamas]]></surname>
<given-names><![CDATA[I.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[An Ensemble of LSTM Neural Networks for High-Frequency Stock Market Classification]]></article-title>
<source><![CDATA[SSRN Electronic Journal]]></source>
<year>2018</year>
</nlm-citation>
</ref>
<ref id="B4">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Bukhari]]></surname>
<given-names><![CDATA[A. H.]]></given-names>
</name>
<name>
<surname><![CDATA[Raja]]></surname>
<given-names><![CDATA[M. A. Z.]]></given-names>
</name>
<name>
<surname><![CDATA[Sulaiman]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Islam]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Shoaib]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
<name>
<surname><![CDATA[Kumam]]></surname>
<given-names><![CDATA[P.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Fractional neuro-sequential ARFIMA-LSTM for financial market forecasting]]></article-title>
<source><![CDATA[IEEE Access]]></source>
<year>2020</year>
<volume>8</volume>
<page-range>71326-38</page-range></nlm-citation>
</ref>
<ref id="B5">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Chen]]></surname>
<given-names><![CDATA[K.]]></given-names>
</name>
<name>
<surname><![CDATA[Zhou]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
<name>
<surname><![CDATA[Dai]]></surname>
<given-names><![CDATA[F.]]></given-names>
</name>
</person-group>
<source><![CDATA[A LSTM-based method for stock returns prediction: a case study of China stock market]]></source>
<year>2015</year>
<conf-name><![CDATA[ IEEE International Conference on Big Data]]></conf-name>
<conf-date>2015</conf-date>
<conf-loc> </conf-loc>
<page-range>2823-4</page-range></nlm-citation>
</ref>
<ref id="B6">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Choi]]></surname>
<given-names><![CDATA[H. K.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Stock price correlation coefficient prediction with ARIMA-LSTM hybrid model]]></article-title>
<source><![CDATA[arXiv]]></source>
<year>2018</year>
<page-range>1-22</page-range></nlm-citation>
</ref>
<ref id="B7">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Chong]]></surname>
<given-names><![CDATA[E.]]></given-names>
</name>
<name>
<surname><![CDATA[Han]]></surname>
<given-names><![CDATA[C.]]></given-names>
</name>
<name>
<surname><![CDATA[Park]]></surname>
<given-names><![CDATA[F.C.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Deep learning networks for stock market analysis and prediction: Methodology. data representations, and case studies]]></article-title>
<source><![CDATA[Experts Systems with Applications]]></source>
<year>2017</year>
<volume>83</volume>
<page-range>187-205</page-range></nlm-citation>
</ref>
<ref id="B8">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Ding]]></surname>
<given-names><![CDATA[G.]]></given-names>
</name>
<name>
<surname><![CDATA[Qin]]></surname>
<given-names><![CDATA[L.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Study on the prediction of stock price based on the associated network model of LSTM]]></article-title>
<source><![CDATA[Int. J. Mach. Learn. &amp; Cyber]]></source>
<year>2020</year>
<volume>11</volume>
<page-range>1307-17</page-range></nlm-citation>
</ref>
<ref id="B9">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Fisher]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
<name>
<surname><![CDATA[Krauss]]></surname>
<given-names><![CDATA[C]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Deep learning with long short-term memory networks for financial market predictions]]></article-title>
<source><![CDATA[European Journal of Operational Research]]></source>
<year>2018</year>
<volume>270</volume>
<page-range>654-69</page-range></nlm-citation>
</ref>
<ref id="B10">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Gülmez]]></surname>
<given-names><![CDATA[B.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Stock price prediction with optimized deep LSTM network with artificial rabbits optimization algorithm]]></article-title>
<source><![CDATA[Expert Systems with Applications]]></source>
<year>2023</year>
<volume>227</volume>
</nlm-citation>
</ref>
<ref id="B11">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Hochreiter]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Schmidhuber]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Long short-term memory]]></article-title>
<source><![CDATA[Neural computation]]></source>
<year>1997</year>
<volume>9</volume>
<numero>8</numero>
<issue>8</issue>
<page-range>1735-80</page-range></nlm-citation>
</ref>
<ref id="B12">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Istiake Sunny]]></surname>
<given-names><![CDATA[M. A.]]></given-names>
</name>
<name>
<surname><![CDATA[Maswood]]></surname>
<given-names><![CDATA[M. M. S.]]></given-names>
</name>
<name>
<surname><![CDATA[Alharbi]]></surname>
<given-names><![CDATA[A. G.]]></given-names>
</name>
</person-group>
<source><![CDATA[Deep Learning-Based Stock Price Prediction Using LSTM and Bi-Directional LSTM Model]]></source>
<year>2020</year>
<conf-name><![CDATA[ 2ndNovel Intelligent and Leading Emerging Sciences Conference]]></conf-name>
<conf-date>2020</conf-date>
<conf-loc> </conf-loc>
</nlm-citation>
</ref>
<ref id="B13">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Markowitz]]></surname>
<given-names><![CDATA[H.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Portfolio Selection]]></article-title>
<source><![CDATA[The Journal of Finance]]></source>
<year>1952</year>
<volume>7</volume>
<page-range>77-91</page-range></nlm-citation>
</ref>
<ref id="B14">
<nlm-citation citation-type="">
<collab>Mathworks</collab>
<source><![CDATA[Long Short-Term Memory Networks]]></source>
<year>2022</year>
</nlm-citation>
</ref>
<ref id="B15">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Nelson]]></surname>
<given-names><![CDATA[D.M.Q.]]></given-names>
</name>
<name>
<surname><![CDATA[Pereira]]></surname>
<given-names><![CDATA[A.C.M.]]></given-names>
</name>
<name>
<surname><![CDATA[de Oliveria]]></surname>
<given-names><![CDATA[R.A.]]></given-names>
</name>
</person-group>
<source><![CDATA[Stock market&#8217;s price movement prediction with LSTM neural networks]]></source>
<year>2017</year>
<conf-name><![CDATA[ International Join Conference on Neural Networks]]></conf-name>
<conf-date>2017</conf-date>
<conf-loc> </conf-loc>
</nlm-citation>
</ref>
<ref id="B16">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Rácz]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Fogarasi]]></surname>
<given-names><![CDATA[N.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Trading sparse, mean reverting portfolios using VAR(1) and LSTM prediction]]></article-title>
<source><![CDATA[Acta Universitatis Sapientiae Informatica]]></source>
<year>2021</year>
<volume>13</volume>
<numero>2</numero>
<issue>2</issue>
<page-range>288-302</page-range></nlm-citation>
</ref>
<ref id="B17">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Sen]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Dutta]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Mehtab]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
</person-group>
<source><![CDATA[Stock Portfolio Optimization Using a Deep Learning LSTM Model]]></source>
<year>2021</year>
<conf-name><![CDATA[ IEEE Mysore Sub Section International Conference]]></conf-name>
<conf-date>2021</conf-date>
<conf-loc> </conf-loc>
</nlm-citation>
</ref>
<ref id="B18">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Sen]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Mehtab]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Dutta]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Stock Price Prediction Using Machine Learning and LSTM-Based Deep Learning Models]]></article-title>
<source><![CDATA[TechRxiv]]></source>
<year>2021</year>
</nlm-citation>
</ref>
<ref id="B19">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Shah]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Vaidya]]></surname>
<given-names><![CDATA[D.]]></given-names>
</name>
<name>
<surname><![CDATA[Shah]]></surname>
<given-names><![CDATA[M.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[A comprehensive review on multiple hybrid deep learning approaches for stock prediction]]></article-title>
<source><![CDATA[Intelligent Systems with Applications]]></source>
<year>2022</year>
<volume>16</volume>
</nlm-citation>
</ref>
<ref id="B20">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Song]]></surname>
<given-names><![CDATA[H.]]></given-names>
</name>
<name>
<surname><![CDATA[Choi]]></surname>
<given-names><![CDATA[H.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Forecasting Stock Market Indices Using the Recurrent Neural Network Based Hybrid Models: CNN-LSTM, GRU-CNN, and Ensemble Models]]></article-title>
<source><![CDATA[Applied Sciences]]></source>
<year>2023</year>
<volume>13</volume>
<numero>7</numero>
<issue>7</issue>
</nlm-citation>
</ref>
<ref id="B21">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Wang]]></surname>
<given-names><![CDATA[R.]]></given-names>
</name>
<name>
<surname><![CDATA[Zuo]]></surname>
<given-names><![CDATA[Z.]]></given-names>
</name>
</person-group>
<source><![CDATA[Stock Price Prediction with Long-short Term Memory Model]]></source>
<year>2021</year>
<conf-name><![CDATA[ 3rdInternational Conference on Machine Learning, Big Data and Business Intelligence]]></conf-name>
<conf-date>2021</conf-date>
<conf-loc> </conf-loc>
</nlm-citation>
</ref>
<ref id="B22">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Yao]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
<name>
<surname><![CDATA[Luo]]></surname>
<given-names><![CDATA[L.]]></given-names>
</name>
<name>
<surname><![CDATA[Peng]]></surname>
<given-names><![CDATA[H.]]></given-names>
</name>
</person-group>
<source><![CDATA[High-Frequency Stock Trend Forecast Using LSTM Model]]></source>
<year>2018</year>
<conf-name><![CDATA[ 13thInternational Conference on Computer Science &amp; Education (ICCSE)]]></conf-name>
<conf-date>2018</conf-date>
<conf-loc> </conf-loc>
<page-range>1-4</page-range></nlm-citation>
</ref>
<ref id="B23">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Yue]]></surname>
<given-names><![CDATA[H.]]></given-names>
</name>
<name>
<surname><![CDATA[Liu]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Tian]]></surname>
<given-names><![CDATA[D.]]></given-names>
</name>
<name>
<surname><![CDATA[Zhang]]></surname>
<given-names><![CDATA[Q.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[A Novel Anti-Risk Method for Portfolio Trading Using Deep Reinforcement Learning]]></article-title>
<source><![CDATA[Electronics]]></source>
<year>2022</year>
<volume>11</volume>
<numero>9</numero>
<issue>9</issue>
</nlm-citation>
</ref>
<ref id="B24">
<nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Zhang]]></surname>
<given-names><![CDATA[R.]]></given-names>
</name>
<name>
<surname><![CDATA[Huang]]></surname>
<given-names><![CDATA[C.]]></given-names>
</name>
<name>
<surname><![CDATA[Zhang]]></surname>
<given-names><![CDATA[W.]]></given-names>
</name>
<name>
<surname><![CDATA[Chen]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Multi-factor stock selection model based on LSTM]]></article-title>
<source><![CDATA[International Journal of Economics and Finance]]></source>
<year>2018</year>
<volume>10</volume>
<numero>8</numero>
<issue>8</issue>
<page-range>1-36</page-range></nlm-citation>
</ref>
</ref-list>
</back>
</article>
