Predictive modeling in insurance: Key issues to consider throughout the lifecycle of a model

<?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>00000cam a22000004b 4500</leader>
    <controlfield tag="001">MAP20120038622</controlfield>
    <controlfield tag="003">MAP</controlfield>
    <controlfield tag="005">20220911204631.0</controlfield>
    <controlfield tag="008">120905s2012    che||||       ||| ||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">20</subfield>
    </datafield>
    <datafield tag="100" ind1="1" ind2=" ">
      <subfield code="0">MAPA20120021778</subfield>
      <subfield code="a">Homewwod, Chris</subfield>
    </datafield>
    <datafield tag="245" ind1="0" ind2="0">
      <subfield code="a">Predictive modeling in insurance: Key issues to consider throughout the lifecycle of a model</subfield>
      <subfield code="c">Chris Homewwod</subfield>
    </datafield>
    <datafield tag="260" ind1=" " ind2=" ">
      <subfield code="a">Zurich</subfield>
      <subfield code="b">Swiss Re Ltd.</subfield>
      <subfield code="c">cop. 2012</subfield>
    </datafield>
    <datafield tag="520" ind1=" " ind2=" ">
      <subfield code="a">Most personal lines and a number of larger commercial lines insurers have incorporated a predictive analytics capability into their organization. For those carriers evaluating if and how they should approach implementing such capabilities, there is much to consider, as doing so will involve a significant investment balanced against the risks associated with failing to invest in such capabilities. In order to effectively navigate the best path to building this capability, it is important to form an understanding of how predictive analytics are used in the insurance industry, what a predictive model is, and to think through the key considerations during the typical lifecycle of predictive models. Written with chief underwriting officers and product line heads  in mind, the information below will serve as a guide to how these decision makers might critically think about, identify, and plan around these issues as they relate to predictive models used to optimize relative pricing</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="1">
      <subfield code="0">MAPA20080590567</subfield>
      <subfield code="a">Empresas de seguros</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="1">
      <subfield code="0">MAPA20080592059</subfield>
      <subfield code="a">Modelos predictivos</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="1">
      <subfield code="0">MAPA20080614720</subfield>
      <subfield code="a">Modelos de planificación</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="1">
      <subfield code="0">MAPA20080598358</subfield>
      <subfield code="a">Productos de seguros</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="1">
      <subfield code="0">MAPA20100002773</subfield>
      <subfield code="a">Ciclos de vida</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="1">
      <subfield code="0">MAPA20080599096</subfield>
      <subfield code="a">Selección de riesgos</subfield>
    </datafield>
    <datafield tag="710" ind1="2" ind2=" ">
      <subfield code="0">MAPA20080442071</subfield>
      <subfield code="a">Swiss Reinsurance</subfield>
    </datafield>
  </record>
</collection>