<?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>0123-3033</journal-id>
<journal-title><![CDATA[Ingeniería y competitividad]]></journal-title>
<abbrev-journal-title><![CDATA[Ing. compet.]]></abbrev-journal-title>
<issn>0123-3033</issn>
<publisher>
<publisher-name><![CDATA[Facultad de Ingeniería, Universidad del Valle]]></publisher-name>
</publisher>
</journal-meta>
<article-meta>
<article-id>S0123-30332023000300014</article-id>
<article-id pub-id-type="doi">10.25100/iyc.v25i3.12845</article-id>
<title-group>
<article-title xml:lang="es"><![CDATA[Comparación de algoritmos de Deep Learning para pronósticos en los precios de Criptomonedas]]></article-title>
<article-title xml:lang="en"><![CDATA[Comparison of Deep Learning algorithms for cryptocurrencies price forecasting]]></article-title>
</title-group>
<contrib-group>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Lambis-Alandete]]></surname>
<given-names><![CDATA[Erick]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Jiménez-Gómez]]></surname>
<given-names><![CDATA[Miguel]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Velásquez-Henao]]></surname>
<given-names><![CDATA[Juan D.]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
</contrib-group>
<aff id="Af1">
<institution><![CDATA[,Universidad Nacional de Colombia Facultad de Minas ]]></institution>
<addr-line><![CDATA[Medellín ]]></addr-line>
<country>Colombia</country>
</aff>
<pub-date pub-type="pub">
<day>00</day>
<month>12</month>
<year>2023</year>
</pub-date>
<pub-date pub-type="epub">
<day>00</day>
<month>12</month>
<year>2023</year>
</pub-date>
<volume>25</volume>
<numero>3</numero>
<copyright-statement/>
<copyright-year/>
<self-uri xlink:href="http://www.scielo.org.co/scielo.php?script=sci_arttext&amp;pid=S0123-30332023000300014&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.co/scielo.php?script=sci_abstract&amp;pid=S0123-30332023000300014&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.co/scielo.php?script=sci_pdf&amp;pid=S0123-30332023000300014&amp;lng=en&amp;nrm=iso"></self-uri><abstract abstract-type="short" xml:lang="es"><p><![CDATA[Resumen Debido al alto atractivo de las criptomonedas los inversionistas y los investigadores han prestado mayor atención en la previsión de sus precios. Con el desarrollo metodológico del Deep Learning, la previsión de las criptomonedas ha tenido mayor importancia en los últimos años. En este artículo, se evalúan cuatro modelos de Deep Learning: RNN, LSTM, GRU y CNN-LSTM con el objetivo de evaluar el desempeño en el pronóstico del precio de cierre diario de las dos criptomonedas más importantes: Bitcoin y Ethereum. Se utilizaron métricas de análisis de desempeño como MAE, RMSE, MSE y MAPE y como métrica de ajuste, el R2. Cada modelo de Deep Learning fue optimizado a partir de un conjunto de hiperparámetros y para diferentes ventanas de tiempo. Los resultados experimentales mostraron que el algoritmo RNN tuvo un rendimiento superior en la predicción del precio de Bitcoin y el algoritmo LSTM en el precio de Ethereum. Incluso, ambos métodos presentaron mejor desempeño con dos modelos de la literatura evaluados. Finalmente, la confiabilidad del pronóstico de cada modelo se evaluó analizando la autocorrelación de los errores y se encontró que los dos modelos más eficientes tienen alto poder de generalización.]]></p></abstract>
<abstract abstract-type="short" xml:lang="en"><p><![CDATA[Abstract Due to the growth and interest that cryptocurrencies have generated nowadays, investors and researchers have paid more attention to forecasting the prices of cryptocurrencies. With the methodological development of Deep Learning, forecasting cryptocurrencies has become more important in recent years. In this paper, four Deep Learning models RNN, LSTM, GRU and CNN-LSTM are evaluated with the aim of evaluating the performance in forecasting the daily closing price of the two most important cryptocurrencies: Bitcoin and Ethereum. Performance analysis metrics such as MAE, RMSE, MSE and MAPE were used and as a fitting metric, the R2. Each Deep Learning model was optimized from a set of hyperparameters and for different time windows. Experimental results showed that the RNN algorithm had superior performance in predicting the Bitcoin price and the LSTM algorithm in predicting the Ethereum price. Even, both methods presented better performance with two literature models evaluated. Finally, the forecast reliability of each model was evaluated by analyzing the autocorrelation of the errors and the two most efficient models were found to have high generalization power.]]></p></abstract>
<kwd-group>
<kwd lng="es"><![CDATA[Deep Learning]]></kwd>
<kwd lng="es"><![CDATA[Criptomonedas]]></kwd>
<kwd lng="es"><![CDATA[Series de Tiempo]]></kwd>
<kwd lng="es"><![CDATA[inversionista]]></kwd>
<kwd lng="en"><![CDATA[deep Learning]]></kwd>
<kwd lng="en"><![CDATA[Cryptocurrencies]]></kwd>
<kwd lng="en"><![CDATA[Time Series]]></kwd>
<kwd lng="en"><![CDATA[investor]]></kwd>
</kwd-group>
</article-meta>
</front><back>
<ref-list>
<ref id="B1">
<label>1</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Kang]]></surname>
<given-names><![CDATA[CY]]></given-names>
</name>
<name>
<surname><![CDATA[Lee]]></surname>
<given-names><![CDATA[CP]]></given-names>
</name>
<name>
<surname><![CDATA[Lim]]></surname>
<given-names><![CDATA[KM]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Cryptocurrency Price Prediction with Convolutional Neural Network and Stacked Gated Recurrent Unit]]></article-title>
<source><![CDATA[Data]]></source>
<year>2022</year>
<volume>7</volume>
<numero>11</numero>
<issue>11</issue>
<page-range>149</page-range></nlm-citation>
</ref>
<ref id="B2">
<label>2</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Fleischer]]></surname>
<given-names><![CDATA[JP]]></given-names>
</name>
<name>
<surname><![CDATA[von Laszewski]]></surname>
<given-names><![CDATA[G]]></given-names>
</name>
<name>
<surname><![CDATA[Theran]]></surname>
<given-names><![CDATA[C]]></given-names>
</name>
<name>
<surname><![CDATA[Bautista]]></surname>
<given-names><![CDATA[YJP]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Time Series Analysis of Cryptocurrency Prices Using Long Short-Term Memory]]></article-title>
<source><![CDATA[Algorithms]]></source>
<year>2022</year>
<volume>15</volume>
<numero>7</numero>
<issue>7</issue>
<page-range>230</page-range></nlm-citation>
</ref>
<ref id="B3">
<label>3</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Ammer]]></surname>
<given-names><![CDATA[MA]]></given-names>
</name>
<name>
<surname><![CDATA[Aldhyani]]></surname>
<given-names><![CDATA[THH]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Deep Learning Algorithm to Predict Cryptocurrency Fluctuation Prices Increasing Investment Awareness]]></article-title>
<source><![CDATA[Electron]]></source>
<year>2022</year>
<volume>11</volume>
<numero>15</numero>
<issue>15</issue>
<page-range>2349</page-range></nlm-citation>
</ref>
<ref id="B4">
<label>4</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Patel]]></surname>
<given-names><![CDATA[MM]]></given-names>
</name>
<name>
<surname><![CDATA[Tanwar]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Gupta]]></surname>
<given-names><![CDATA[R]]></given-names>
</name>
<name>
<surname><![CDATA[Kumar]]></surname>
<given-names><![CDATA[N]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[A Deep Learning-based Cryptocurrency Price Prediction Scheme for Financial Institutions]]></article-title>
<source><![CDATA[J Inf Secur Appl]]></source>
<year>2020</year>
<volume>55</volume>
<page-range>102583</page-range></nlm-citation>
</ref>
<ref id="B5">
<label>5</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Lahmiri]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Bekiros]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Cryptocurrency forecasting with deep learning chaotic neural networks]]></article-title>
<source><![CDATA[Chaos, Solitons and Fractals]]></source>
<year>2019</year>
<volume>118</volume>
<page-range>35-40</page-range></nlm-citation>
</ref>
<ref id="B6">
<label>6</label><nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Wu]]></surname>
<given-names><![CDATA[C-H]]></given-names>
</name>
<name>
<surname><![CDATA[Lu]]></surname>
<given-names><![CDATA[C-C]]></given-names>
</name>
<name>
<surname><![CDATA[Ma]]></surname>
<given-names><![CDATA[Y-F]]></given-names>
</name>
<name>
<surname><![CDATA[Lu]]></surname>
<given-names><![CDATA[R-S]]></given-names>
</name>
</person-group>
<source><![CDATA[A new forecasting framework for bitcoin price with LSTM]]></source>
<year>2019</year>
<conf-name><![CDATA[ IEEE International Conference on Data Mining Workshops, ICDMW]]></conf-name>
<conf-date>2019</conf-date>
<conf-loc> </conf-loc>
<page-range>168-75</page-range></nlm-citation>
</ref>
<ref id="B7">
<label>7</label><nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Pintelas]]></surname>
<given-names><![CDATA[E]]></given-names>
</name>
<name>
<surname><![CDATA[Livieris]]></surname>
<given-names><![CDATA[IE]]></given-names>
</name>
<name>
<surname><![CDATA[Stavroyiannis]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Kotsilieris]]></surname>
<given-names><![CDATA[T]]></given-names>
</name>
<name>
<surname><![CDATA[Pintelas]]></surname>
<given-names><![CDATA[P]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Investigating the Problem of Cryptocurrency Price Prediction: A Deep Learning Approach]]></article-title>
<source><![CDATA[Vol. 584 IFIP, IFIP Advances in Information and Communication Technology]]></source>
<year>2020</year>
<page-range>99-110</page-range></nlm-citation>
</ref>
<ref id="B8">
<label>8</label><nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Awoke]]></surname>
<given-names><![CDATA[T]]></given-names>
</name>
<name>
<surname><![CDATA[Rout]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
<name>
<surname><![CDATA[Mohanty]]></surname>
<given-names><![CDATA[L]]></given-names>
</name>
<name>
<surname><![CDATA[Satapathy]]></surname>
<given-names><![CDATA[SC]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Bitcoin Price Prediction and Analysis Using Deep Learning Models]]></article-title>
<source><![CDATA[Vol. 134, Lecture Notes in Networks and Systems]]></source>
<year>2021</year>
<page-range>631-40</page-range></nlm-citation>
</ref>
<ref id="B9">
<label>9</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Oyedele]]></surname>
<given-names><![CDATA[AA]]></given-names>
</name>
<name>
<surname><![CDATA[Ajayi]]></surname>
<given-names><![CDATA[AO]]></given-names>
</name>
<name>
<surname><![CDATA[Oyedele]]></surname>
<given-names><![CDATA[LO]]></given-names>
</name>
<name>
<surname><![CDATA[Bello]]></surname>
<given-names><![CDATA[SA]]></given-names>
</name>
<name>
<surname><![CDATA[Jimoh]]></surname>
<given-names><![CDATA[KO]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Performance evaluation of deep learning and boosted trees for cryptocurrency closing price prediction]]></article-title>
<source><![CDATA[Expert Syst Appl]]></source>
<year>2023</year>
<volume>213</volume>
<page-range>119233</page-range></nlm-citation>
</ref>
<ref id="B10">
<label>10</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Ferdiansyah]]></surname>
<given-names><![CDATA[F]]></given-names>
</name>
<name>
<surname><![CDATA[Othman]]></surname>
<given-names><![CDATA[SH]]></given-names>
</name>
<name>
<surname><![CDATA[Radzi]]></surname>
<given-names><![CDATA[RZM]]></given-names>
</name>
<name>
<surname><![CDATA[Stiawan]]></surname>
<given-names><![CDATA[D]]></given-names>
</name>
<name>
<surname><![CDATA[Sutikno]]></surname>
<given-names><![CDATA[T]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Hybrid gated recurrent unit bidirectional-long short-term memory model to improve cryptocurrency prediction accuracy]]></article-title>
<source><![CDATA[IAES Int J Artif Intell]]></source>
<year>2023</year>
<volume>12</volume>
<numero>1</numero>
<issue>1</issue>
<page-range>251-61</page-range></nlm-citation>
</ref>
<ref id="B11">
<label>11</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Nasirtafreshi]]></surname>
<given-names><![CDATA[I]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Forecasting cryptocurrency prices using Recurrent Neural Network and Long Short-term Memory]]></article-title>
<source><![CDATA[Data Knowl Eng]]></source>
<year>2022</year>
<volume>139</volume>
<page-range>102009</page-range></nlm-citation>
</ref>
<ref id="B12">
<label>12</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Bao]]></surname>
<given-names><![CDATA[W]]></given-names>
</name>
<name>
<surname><![CDATA[Yue]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
<name>
<surname><![CDATA[Rao]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[A deep learning framework for financial time series using stacked autoencoders and longshort term memory]]></article-title>
<source><![CDATA[PLoS One]]></source>
<year>2017</year>
<volume>12</volume>
<numero>7</numero>
<issue>7</issue>
<page-range>1-24</page-range></nlm-citation>
</ref>
<ref id="B13">
<label>13</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Kim]]></surname>
<given-names><![CDATA[HY]]></given-names>
</name>
<name>
<surname><![CDATA[Won]]></surname>
<given-names><![CDATA[CH]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Forecasting the volatility of stock price index A hybrid model integrating LSTM with multiple GARCH-type models]]></article-title>
<source><![CDATA[Expert Syst Appl]]></source>
<year>2018</year>
<volume>103</volume>
<page-range>25-37</page-range></nlm-citation>
</ref>
<ref id="B14">
<label>14</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Zha]]></surname>
<given-names><![CDATA[W]]></given-names>
</name>
<name>
<surname><![CDATA[Liu]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
<name>
<surname><![CDATA[Wan]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
<name>
<surname><![CDATA[Luo]]></surname>
<given-names><![CDATA[R]]></given-names>
</name>
<name>
<surname><![CDATA[Li]]></surname>
<given-names><![CDATA[D]]></given-names>
</name>
<name>
<surname><![CDATA[Yang]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Forecasting monthly gas field production based on the CNN-LSTM model]]></article-title>
<source><![CDATA[Energy]]></source>
<year>2022</year>
<volume>260</volume>
<page-range>124889</page-range></nlm-citation>
</ref>
<ref id="B15">
<label>15</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Luo]]></surname>
<given-names><![CDATA[H]]></given-names>
</name>
<name>
<surname><![CDATA[Wang]]></surname>
<given-names><![CDATA[D]]></given-names>
</name>
<name>
<surname><![CDATA[Cheng]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
<name>
<surname><![CDATA[Wu]]></surname>
<given-names><![CDATA[Q]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Multi-step-ahead copper price forecasting using a two-phase architecture based on an improved LSTM with novel input strategy and error correction]]></article-title>
<source><![CDATA[Resour Policy]]></source>
<year>2022</year>
<volume>79</volume>
<page-range>102962</page-range></nlm-citation>
</ref>
<ref id="B16">
<label>16</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Lawi]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
<name>
<surname><![CDATA[Mesra]]></surname>
<given-names><![CDATA[H]]></given-names>
</name>
<name>
<surname><![CDATA[Amir]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Implementation of Long Short-Term Memory and Gated Recurrent Units on grouped time-series data to predict stock prices accurately]]></article-title>
<source><![CDATA[J Big Data]]></source>
<year>2022</year>
<volume>9</volume>
<numero>1</numero>
<issue>1</issue>
<page-range>89</page-range></nlm-citation>
</ref>
<ref id="B17">
<label>17</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Tang]]></surname>
<given-names><![CDATA[H]]></given-names>
</name>
<name>
<surname><![CDATA[Ling]]></surname>
<given-names><![CDATA[X]]></given-names>
</name>
<name>
<surname><![CDATA[Li]]></surname>
<given-names><![CDATA[L]]></given-names>
</name>
<name>
<surname><![CDATA[Xiong]]></surname>
<given-names><![CDATA[L]]></given-names>
</name>
<name>
<surname><![CDATA[Yao]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
<name>
<surname><![CDATA[Huang]]></surname>
<given-names><![CDATA[X]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[One-shot pruning of gated recurrent unit neural network by sensitivity for time-series prediction]]></article-title>
<source><![CDATA[Neurocomputing]]></source>
<year>2022</year>
<volume>512</volume>
<page-range>15-24</page-range></nlm-citation>
</ref>
<ref id="B18">
<label>18</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Gu]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
<name>
<surname><![CDATA[Wang]]></surname>
<given-names><![CDATA[Z]]></given-names>
</name>
<name>
<surname><![CDATA[Kuen]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
<name>
<surname><![CDATA[Ma]]></surname>
<given-names><![CDATA[L]]></given-names>
</name>
<name>
<surname><![CDATA[Shahroudy]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
<name>
<surname><![CDATA[Shuai]]></surname>
<given-names><![CDATA[B]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Recent advances in convolutional neural networks]]></article-title>
<source><![CDATA[Pattern Recognit]]></source>
<year>2018</year>
<volume>77</volume>
<page-range>354-77</page-range></nlm-citation>
</ref>
<ref id="B19">
<label>19</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Ghimire]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Deo]]></surname>
<given-names><![CDATA[RC]]></given-names>
</name>
<name>
<surname><![CDATA[Casillas-Pérez]]></surname>
<given-names><![CDATA[D]]></given-names>
</name>
<name>
<surname><![CDATA[Salcedo-Sanz]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Sharma]]></surname>
<given-names><![CDATA[E]]></given-names>
</name>
<name>
<surname><![CDATA[Ali]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Deep learning CNN-LSTM-MLP hybrid fusion model for feature optimizations and daily solar radiation prediction]]></article-title>
<source><![CDATA[Meas J Int Meas Confed]]></source>
<year>2022</year>
<volume>202</volume>
<page-range>111759</page-range></nlm-citation>
</ref>
<ref id="B20">
<label>20</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Livieris]]></surname>
<given-names><![CDATA[IE]]></given-names>
</name>
<name>
<surname><![CDATA[Stavroyiannis]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Pintelas]]></surname>
<given-names><![CDATA[E]]></given-names>
</name>
<name>
<surname><![CDATA[Pintelas]]></surname>
<given-names><![CDATA[P]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[A novel validation framework to enhance deep learning models in time-series forecasting]]></article-title>
<source><![CDATA[Neural Comput Appl]]></source>
<year>2020</year>
<volume>32</volume>
<numero>23</numero>
<issue>23</issue>
<page-range>17149-67</page-range></nlm-citation>
</ref>
</ref-list>
</back>
</article>
