Transfer learning in the actuarial domain : foundations and applications

<?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">MAP20260012308</controlfield>
    <controlfield tag="003">MAP</controlfield>
    <controlfield tag="005">20260422174136.0</controlfield>
    <controlfield tag="008">260421e20260316esp|||p      |0|||b|spa 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=" " ind2=" ">
      <subfield code="0">MAPA20260007359</subfield>
      <subfield code="a">Kim, Youngsun </subfield>
    </datafield>
    <datafield tag="245" ind1="1" ind2="0">
      <subfield code="a">Transfer learning in the actuarial domain</subfield>
      <subfield code="b">: foundations and applications</subfield>
      <subfield code="c">Youngsun Kim and Daniel Bauer</subfield>
    </datafield>
    <datafield tag="520" ind1=" " ind2=" ">
      <subfield code="a">The article systematically analyzes the use of transfer learning in the actuarial field, particularly in the prediction of claim frequency when labeled data are scarce. It presents formal definitions, typologies, and methodological approaches, linking them to classical concepts such as credibility theory. Through empirical applications in automobile insurance, instance-based, feature-based, and parameter-based methods are evaluated. The results show improvements in accuracy and stability compared to traditional models. The study positions transfer learning as a relevant tool for modern actuarial analysis</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="4">
      <subfield code="0">MAPA20080579258</subfield>
      <subfield code="a">Cálculo actuarial</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">MAPA20080592059</subfield>
      <subfield code="a">Modelos predictivos</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="4">
      <subfield code="0">MAPA20080603779</subfield>
      <subfield code="a">Seguro de automóviles</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="4">
      <subfield code="0">MAPA20080611200</subfield>
      <subfield code="a">Inteligencia artificial</subfield>
    </datafield>
    <datafield tag="700" ind1="1" ind2=" ">
      <subfield code="0">MAPA20080650254</subfield>
      <subfield code="a">Bauer, Daniel</subfield>
    </datafield>
    <datafield tag="773" ind1="0" ind2=" ">
      <subfield code="w">MAP20077000239</subfield>
      <subfield code="g">16/03/2026 Tomo 30 Número 1 - 2026 , 23 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>
  </record>
</collection>