Health policyholder clustering using medical consumption

<?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">MAP20220013406</controlfield>
    <controlfield tag="003">MAP</controlfield>
    <controlfield tag="005">20220504130529.0</controlfield>
    <controlfield tag="008">220504e20201207esp|||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">344.1</subfield>
    </datafield>
    <datafield tag="100" ind1="1" ind2=" ">
      <subfield code="0">MAPA20220004602</subfield>
      <subfield code="a">Gauchon, Romain</subfield>
    </datafield>
    <datafield tag="245" ind1="1" ind2="0">
      <subfield code="a">Health policyholder clustering using medical consumption</subfield>
      <subfield code="c">Romain Gauchon, Stéphane Loisel, Jean-Louis Rullière </subfield>
    </datafield>
    <datafield tag="520" ind1=" " ind2=" ">
      <subfield code="a">On paper, prevention appears to be a good complement to health insurance. However, its implementation is often costly. To maximize the impact and efficiency of prevention plans, plans should target particular groups of policyholders. In this article, we propose a way of clustering policyholders that could be a starting point for the targeting of prevention plans. This two-step method considers mainly policyholder health consumption for classification. The dimension is first reduced using a nonnegative matrix factorization algorithm, producing intermediate health product clusters. Policyholders are then clustered using Kohonen's map algorithm. This leads to a natural visualization of the results, allowing the simple comparison of results from different databases. The method is applied to two real French health insurer datasets. The method is shown to be easily understandable and able to cluster most policyholders efficiently.

</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="4">
      <subfield code="0">MAPA20080573867</subfield>
      <subfield code="a">Seguro de salud</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="4">
      <subfield code="0">MAPA20210014192</subfield>
      <subfield code="a">Prevención</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="4">
      <subfield code="0">MAPA20080579258</subfield>
      <subfield code="a">Cálculo actuarial</subfield>
    </datafield>
    <datafield tag="700" ind1="1" ind2=" ">
      <subfield code="0">MAPA20100059609</subfield>
      <subfield code="a">Loisel, Stéphane</subfield>
    </datafield>
    <datafield tag="700" ind1="1" ind2=" ">
      <subfield code="0">MAPA20220004619</subfield>
      <subfield code="a">Rullière, Jean-Louis</subfield>
    </datafield>
    <datafield tag="773" ind1="0" ind2=" ">
      <subfield code="w">MAP20220007085</subfield>
      <subfield code="g">07/12/2020 Número 2 - diciembre 2020 , p. 599-626</subfield>
      <subfield code="t">European Actuarial Journal</subfield>
      <subfield code="d">Cham, Switzerland  : Springer Nature Switzerland AG,  2021-2022</subfield>
    </datafield>
  </record>
</collection>