<?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>0379-3982</journal-id>
<journal-title><![CDATA[Revista Tecnología en Marcha]]></journal-title>
<abbrev-journal-title><![CDATA[Tecnología en Marcha]]></abbrev-journal-title>
<issn>0379-3982</issn>
<publisher>
<publisher-name><![CDATA[Instituto Tecnológico de Costa Rica]]></publisher-name>
</publisher>
</journal-meta>
<article-meta>
<article-id>S0379-39822022000400084</article-id>
<article-id pub-id-type="doi">10.18845/tm.v35i4.5766</article-id>
<title-group>
<article-title xml:lang="en"><![CDATA[A machine learning proposal to predict poverty]]></article-title>
<article-title xml:lang="es"><![CDATA[Una propuesta de aprendizaje automático para predecir la pobreza]]></article-title>
</title-group>
<contrib-group>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Solís-Salazar]]></surname>
<given-names><![CDATA[Martín]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Madrigal-Sanabria]]></surname>
<given-names><![CDATA[Julio]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
</contrib-group>
<aff id="Af1">
<institution><![CDATA[,Instituto Tecnológico de Costa Rica  ]]></institution>
<addr-line><![CDATA[ ]]></addr-line>
<country>Costa Rica</country>
</aff>
<aff id="Af2">
<institution><![CDATA[,Universidad de Costa Rica  ]]></institution>
<addr-line><![CDATA[ ]]></addr-line>
<country>Costa Rica</country>
</aff>
<pub-date pub-type="pub">
<day>00</day>
<month>12</month>
<year>2022</year>
</pub-date>
<pub-date pub-type="epub">
<day>00</day>
<month>12</month>
<year>2022</year>
</pub-date>
<volume>35</volume>
<numero>4</numero>
<fpage>84</fpage>
<lpage>94</lpage>
<copyright-statement/>
<copyright-year/>
<self-uri xlink:href="http://www.scielo.sa.cr/scielo.php?script=sci_arttext&amp;pid=S0379-39822022000400084&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.sa.cr/scielo.php?script=sci_abstract&amp;pid=S0379-39822022000400084&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.sa.cr/scielo.php?script=sci_pdf&amp;pid=S0379-39822022000400084&amp;lng=en&amp;nrm=iso"></self-uri><abstract abstract-type="short" xml:lang="en"><p><![CDATA[Abstract Due to the high rate of inclusion and exclusion errors of traditional methods (Proxy Mean Test) used for the identification of households in poverty condition and selection of the social assistance programs beneficiaries, this research analyzed different perspectives to predict households in poverty condition, using a machine learning model based on XGBoost. The models proposed were compared with baseline methods. The data used were taken from the 2019 household survey of Costa Rica. The results showed that at least one of our approaches using XGBoost gave the best balance between inclusion and exclusion errors. The best model to predict poverty and extreme poverty was build using an XGBoost with a classification approach.]]></p></abstract>
<abstract abstract-type="short" xml:lang="es"><p><![CDATA[Resumen Debido a la alta tasa de errores de inclusión y exclusión de los métodos tradicionales (Proxy Mean Test) utilizados para la identificación de hogares en condición de pobreza y la selección de los beneficiarios de los programas de asistencia social, esta investigación analizó diferentes perspectivas para predecir hogares en condición de pobreza, utilizando un modelo de aprendizaje automático basado en XGBoost. Los modelos propuestos se compararon con métodos de referencia. Los datos utilizados fueron tomados de la encuesta de hogares del 2019 de Costa Rica. Los resultados mostraron que al menos uno de nuestros enfoques utilizando XGBoost dan el mejor balance entre el error de exclusión e inclusión. El mejor modelo se construyó utilizando XGBoost con un enfoque de clasificación.]]></p></abstract>
<kwd-group>
<kwd lng="es"><![CDATA[Aprendizaje automático]]></kwd>
<kwd lng="es"><![CDATA[predicción de la pobreza]]></kwd>
<kwd lng="es"><![CDATA[Proxy Mean Test]]></kwd>
<kwd lng="en"><![CDATA[Machine Learning]]></kwd>
<kwd lng="en"><![CDATA[poverty prediction]]></kwd>
<kwd lng="en"><![CDATA[Proxy Mean Test]]></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[Kidd]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Wylde, E]]></surname>
<given-names><![CDATA[E,]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Targeting the Poorest: An Assessment of the Proxy Means Test Methodology]]></article-title>
<source><![CDATA[Technical report, AusAID, Washington]]></source>
<year>2011</year>
</nlm-citation>
</ref>
<ref id="B2">
<label>(2)</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[McBride]]></surname>
<given-names><![CDATA[L]]></given-names>
</name>
<name>
<surname><![CDATA[Nichols]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Retooling poverty targeting using out-of-sample validation and machine learning]]></article-title>
<source><![CDATA[The World Bank Economic Review]]></source>
<year>2018</year>
<volume>32</volume>
<page-range>531-50</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[Budlender]]></surname>
<given-names><![CDATA[D]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Considerations in Using Proxy Means Tests In Eastern Caribbean States]]></article-title>
<source><![CDATA[St.Lucia]]></source>
<year>2016</year>
</nlm-citation>
</ref>
<ref id="B4">
<label>(4)</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Delgado-Jiménez]]></surname>
<given-names><![CDATA[F]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Efectividad en la selección de beneficiarios de los programas avancemos y bienestar familiar]]></article-title>
<source><![CDATA[Economía y Sociedad,]]></source>
<year>2017</year>
<volume>22</volume>
<page-range>1-24</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[Bah]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Finding the Best Indicators to Identify the Poor]]></article-title>
<source><![CDATA[Jakarta, Indonesia: National Team for the Acceleration of Poverty Reduction (TNP2K),]]></source>
<year>2013</year>
<page-range>01-2013</page-range></nlm-citation>
</ref>
<ref id="B6">
<label>(6)</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Brown]]></surname>
<given-names><![CDATA[C]]></given-names>
</name>
<name>
<surname><![CDATA[Ravallion]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
<name>
<surname><![CDATA[Van de Walle]]></surname>
<given-names><![CDATA[D,]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[A Poor Means Test? Econometric Targeting in Africa]]></article-title>
<source><![CDATA[Working Pape]]></source>
<year>2016</year>
<page-range>22919</page-range><publisher-loc><![CDATA[Massachusetts, EEUU: National Bureau of Economic Research ]]></publisher-loc>
</nlm-citation>
</ref>
<ref id="B7">
<label>(7)</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Kidd]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Gelders]]></surname>
<given-names><![CDATA[B]]></given-names>
</name>
<name>
<surname><![CDATA[Bailey-Athias]]></surname>
<given-names><![CDATA[D]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Exclusion by design: an assessment of the effectiveness of the proxy means test poverty targeting mechanism]]></article-title>
<source><![CDATA[Geneva: International Labour Office]]></source>
<year>2017</year>
<volume>56</volume>
</nlm-citation>
</ref>
<ref id="B8">
<label>(8)</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Ashwini]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[A Proxy Means Test for Sri Lanka]]></article-title>
<source><![CDATA[Working Paper]]></source>
<year>2018</year>
<page-range>8605</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[Mapa]]></surname>
<given-names><![CDATA[D. S]]></given-names>
</name>
<name>
<surname><![CDATA[M.L.F,]]></surname>
<given-names><![CDATA[Albis]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[New Proxy means test (PMT) models: improving targeting of the poor for social protection]]></article-title>
<source><![CDATA[In 12th National Convention on Statistics, Manila, Philippines]]></source>
<year>2013</year>
</nlm-citation>
</ref>
<ref id="B10">
<label>(10)</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Dewi]]></surname>
<given-names><![CDATA[R. K]]></given-names>
</name>
<name>
<surname><![CDATA[Suryahadi]]></surname>
<given-names><![CDATA[A]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[The implications of poverty dynamics for targeting the poor: simulations using Indonesian data]]></article-title>
<source><![CDATA[Working paper, SMERU Research Institute, Indonesia]]></source>
<year>2014</year>
</nlm-citation>
</ref>
<ref id="B11">
<label>(11)</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Hussein]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
<name>
<surname><![CDATA[Nazih]]></surname>
<given-names><![CDATA[O]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Poverty level characterization via feature selection and machine learning]]></article-title>
<source><![CDATA[In 27th Signal Processing and Communications Applications Conference (SIU), Siva, Turkey]]></source>
<year>2019</year>
</nlm-citation>
</ref>
<ref id="B12">
<label>(12)</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Pisacha]]></surname>
<given-names><![CDATA[M]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Better Model Selection for poverty targeting through Machine Learning: A case Study in Thailand]]></article-title>
<source><![CDATA[M.S. thesis]]></source>
<year>2017</year>
<publisher-loc><![CDATA[Thammasat University, Thailand ]]></publisher-loc>
</nlm-citation>
</ref>
<ref id="B13">
<label>(13)</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Pave]]></surname>
<given-names><![CDATA[T]]></given-names>
</name>
<name>
<surname><![CDATA[Stender]]></surname>
<given-names><![CDATA[N]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Is random forest a superior methodology for predicting poverty? an empirical assessment]]></article-title>
<source><![CDATA[Poverty &amp; Public Policy,]]></source>
<year>2017</year>
<volume>9</volume>
<page-range>118-33</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[Chen]]></surname>
<given-names><![CDATA[T]]></given-names>
</name>
<name>
<surname><![CDATA[Guestrin]]></surname>
<given-names><![CDATA[C]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Xgboost: A scalable tree boosting system]]></article-title>
<source><![CDATA[In Proceedings of the 22nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining,]]></source>
<year>2016</year>
<publisher-loc><![CDATA[EEUU, San Francisco, CA, USA ]]></publisher-loc>
</nlm-citation>
</ref>
<ref id="B15">
<label>(15)</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Guyon]]></surname>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Gene selection for cancer classification using support vector machines]]></article-title>
<source><![CDATA[Machine learning]]></source>
<year>2002</year>
<volume>46</volume>
<page-range>389</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[Peng]]></surname>
<given-names><![CDATA[H]]></given-names>
</name>
<name>
<surname><![CDATA[Long]]></surname>
<given-names><![CDATA[F]]></given-names>
</name>
<name>
<surname><![CDATA[Ding]]></surname>
<given-names><![CDATA[C]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Feature selection based on mutual information: cri- teria of max-dependency, max-relevance, and min-redundancy]]></article-title>
<source><![CDATA[IEEE Trans. Pattern Anal. Mach. Intell.]]></source>
<year>2005</year>
<volume>27</volume>
<page-range>1226-38</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[García]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Luengo]]></surname>
<given-names><![CDATA[J]]></given-names>
</name>
<name>
<surname><![CDATA[Herrera]]></surname>
<given-names><![CDATA[F]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Tutorial on practical tips of the most influential data preprocessing algorithms in data mining]]></article-title>
<source><![CDATA[Knowledge-Based Systems,]]></source>
<year>2016</year>
<volume>98</volume>
<page-range>1-29</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[Poursaeed]]></surname>
<given-names><![CDATA[O]]></given-names>
</name>
<name>
<surname><![CDATA[Matera]]></surname>
<given-names><![CDATA[T]]></given-names>
</name>
<name>
<surname><![CDATA[Belongie]]></surname>
<given-names><![CDATA[T. S,]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Vision-based real estate price estimation]]></article-title>
<source><![CDATA[Machine Vision and Applications]]></source>
<year>2018</year>
<volume>29</volume>
<page-range>667-76</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[Yoshimura]]></surname>
<given-names><![CDATA[Y]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Deep learning architect: classification for architectural design through the eye of artificial intelligence]]></article-title>
<source><![CDATA[In International Conference on Computers in Urban Planning and Urban Management]]></source>
<year>2019</year>
<page-range>249-65</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[Ngestrini]]></surname>
<given-names><![CDATA[R]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Predicting Poverty of a Region from Satellite Imagery using CNNs]]></article-title>
<source><![CDATA[M.S. thesis, Utrecht University, Utrecht]]></source>
<year>2019</year>
</nlm-citation>
</ref>
<ref id="B21">
<label>(21)</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Pandey]]></surname>
<given-names><![CDATA[S.M,]]></given-names>
</name>
<name>
<surname><![CDATA[Agarwal]]></surname>
<given-names><![CDATA[T]]></given-names>
</name>
<name>
<surname><![CDATA[Krishnan]]></surname>
<given-names><![CDATA[N.C,]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Multi-task deep learning for predicting poverty from satellite images]]></article-title>
<source><![CDATA[In Thirty-Second AAAI Conference on Artificial Intelligence]]></source>
<year>2018</year>
<publisher-loc><![CDATA[New Orleans, USA ]]></publisher-loc>
</nlm-citation>
</ref>
<ref id="B22">
<label>(22)</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Jean]]></surname>
<given-names><![CDATA[N]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Combining satellite imagery and machine learning to predict poverty]]></article-title>
<source><![CDATA[Science,]]></source>
<year>2016</year>
<volume>353</volume>
<page-range>790-4</page-range></nlm-citation>
</ref>
<ref id="B23">
<label>(23)</label><nlm-citation citation-type="journal">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Maluleke]]></surname>
<given-names><![CDATA[V.H,]]></given-names>
</name>
<name>
<surname><![CDATA[Er]]></surname>
<given-names><![CDATA[S]]></given-names>
</name>
<name>
<surname><![CDATA[Williams]]></surname>
<given-names><![CDATA[Q. R]]></given-names>
</name>
</person-group>
<article-title xml:lang=""><![CDATA[Estimating poverty using aerial images: South African application]]></article-title>
<source><![CDATA[Data Science and Applications]]></source>
<year>2018</year>
<volume>1,</volume>
<page-range>29-36</page-range></nlm-citation>
</ref>
</ref-list>
</back>
</article>
