A Model stacking approach for forecasting

<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.loc.gov/MARC21/slim http://www.loc.gov/standards/marcxml/schema/MARC21slim.xsd">
  <record>
    <leader>00000cab a2200000   4500</leader>
    <controlfield tag="001">MAP20230021996</controlfield>
    <controlfield tag="003">MAP</controlfield>
    <controlfield tag="005">20231214124046.0</controlfield>
    <controlfield tag="008">231027e20230906usa|||p      |0|||b|eng d</controlfield>
    <datafield tag="040" ind1=" " ind2=" ">
      <subfield code="a">MAP</subfield>
      <subfield code="b">spa</subfield>
      <subfield code="d">MAP</subfield>
    </datafield>
    <datafield tag="084" ind1=" " ind2=" ">
      <subfield code="a">6</subfield>
    </datafield>
    <datafield tag="100" ind1="1" ind2=" ">
      <subfield code="0">MAPA20120024595</subfield>
      <subfield code="a">Li, Jackie</subfield>
    </datafield>
    <datafield tag="245" ind1="1" ind2="2">
      <subfield code="a">A Model stacking approach for forecasting</subfield>
      <subfield code="c">Jackie Li</subfield>
    </datafield>
    <datafield tag="520" ind1=" " ind2=" ">
      <subfield code="a">This article adopts a machine learning method called stacked generalization for forecasting mortality. The main idea is to combine the forecasts from different projection models or algorithms in a certain way in order to increase the prediction accuracy. In particular, the article considers not just the traditionally used mortality projection models, such as the LeeCarter and CBD models and their extensions, but also some learning algorithms called feedforward and recurrent neural networks that are starting to gain attention in the actuarial literature. For blending the different forecasts, the article examines a number of choices, including simple averaging, weighted averaging, linear regression, and neural network. Using U.S. mortality data, it is found that the proposed stacking approach often outperforms the cases where a projection model or algorithm is applied individually, and that neural networks tend to generate better results than many of the traditional models. </subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="4">
      <subfield code="0">MAPA20170005476</subfield>
      <subfield code="a">Machine learning</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="4">
      <subfield code="0">MAPA20120011137</subfield>
      <subfield code="a">Predicciones estadísticas</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="4">
      <subfield code="0">MAPA20080555306</subfield>
      <subfield code="a">Mortalidad</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="4">
      <subfield code="0">MAPA20080597665</subfield>
      <subfield code="a">Métodos estadísticos</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="4">
      <subfield code="0">MAPA20080624842</subfield>
      <subfield code="a">Redes neuronales artificiales</subfield>
    </datafield>
    <datafield tag="773" ind1="0" ind2=" ">
      <subfield code="w">MAP20077000239</subfield>
      <subfield code="g">06/09/2023 Tomo 27 Número 3 - 2023 , 17 p.</subfield>
      <subfield code="x">1092-0277</subfield>
      <subfield code="t">North American actuarial journal</subfield>
      <subfield code="d">Schaumburg : Society of Actuaries, 1997-</subfield>
    </datafield>
    <datafield tag="856" ind1="0" ind2="0">
      <subfield code="y">MÁS INFORMACIÓN</subfield>
      <subfield code="u">
mailto:centrodocumentacion@fundacionmapfre.org?subject=Consulta%20de%20una%20publicaci%C3%B3n%20&body=Necesito%20m%C3%A1s%20informaci%C3%B3n%20sobre%20este%20documento%3A%20%0A%0A%5Banote%20aqu%C3%AD%20el%20titulo%20completo%20del%20documento%20del%20que%20desea%20informaci%C3%B3n%20y%20nos%20pondremos%20en%20contacto%20con%20usted%5D%20%0A%0AGracias%20%0A
</subfield>
    </datafield>
  </record>
</collection>