A representation-learning approach for insurance pricing with images

<?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">MAP20240013561</controlfield>
    <controlfield tag="003">MAP</controlfield>
    <controlfield tag="005">20240830125047.0</controlfield>
    <controlfield tag="008">240830e20240515bel|||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">219</subfield>
    </datafield>
    <datafield tag="100" ind1="1" ind2=" ">
      <subfield code="0">MAPA20240021078</subfield>
      <subfield code="a">Blier-Wong, Christopher </subfield>
    </datafield>
    <datafield tag="245" ind1="1" ind2="0">
      <subfield code="a">A representation-learning approach for insurance pricing with images</subfield>
      <subfield code="c">Christopher Blier-Wong, Luc Lamontagne and Etienne Marceau</subfield>
    </datafield>
    <datafield tag="520" ind1=" " ind2=" ">
      <subfield code="a">Unstructured data are a promising new source of information that insurance companies may use to understand their risk portfolio better and improve the customer experience. However, these novel data sources are difficult to incorporate into existing ratemaking frameworks due to the size and format of the unstructured data. This paper proposes a framework to use street view imagery within a generalized linear model. To do so, we use representation learning to extract an embedding vector containing useful information from the image. This embedding is dense and low dimensional, making it appropriate to use within existing ratemaking models. We find that there is useful information included in street view imagery to predict the frequency of claims for certain types of perils. This model can be used as in a ratemaking framework but also opens the door to future empirical research on attempting to extract which characteristics within the image leads to increased or decreased predicted claim frequencies. Throughout, we discuss the practical difficulties (technical and social) of using this type of data for insurance pricing</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="4">
      <subfield code="0">MAPA20080586294</subfield>
      <subfield code="a">Mercado de seguros</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="4">
      <subfield code="0">MAPA20080545062</subfield>
      <subfield code="a">Precios</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="4">
      <subfield code="0">MAPA20080545338</subfield>
      <subfield code="a">Seguros</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="4">
      <subfield code="0">MAPA20150006509</subfield>
      <subfield code="a">Experiencia del cliente</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="4">
      <subfield code="0">MAPA20210011108</subfield>
      <subfield code="a">Riesgo</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="4">
      <subfield code="0">MAPA20080627904</subfield>
      <subfield code="a">Ciencias Actuariales y Financieras</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="4">
      <subfield code="0">MAPA20080541408</subfield>
      <subfield code="a">Imagen</subfield>
    </datafield>
    <datafield tag="700" ind1="1" ind2=" ">
      <subfield code="0">MAPA20240021085</subfield>
      <subfield code="a">Lamontagne, Luc  </subfield>
    </datafield>
    <datafield tag="700" ind1="1" ind2=" ">
      <subfield code="0">MAPA20110002756</subfield>
      <subfield code="a">Marceau, É.</subfield>
    </datafield>
    <datafield tag="773" ind1="0" ind2=" ">
      <subfield code="w">MAP20077000420</subfield>
      <subfield code="g">15/05/2024 Volumen 54 Número 2 - mayo 2024 , p.280-309</subfield>
      <subfield code="x">0515-0361</subfield>
      <subfield code="t">Astin bulletin</subfield>
      <subfield code="d">Belgium : ASTIN and AFIR Sections of the International Actuarial Association</subfield>
    </datafield>
    <datafield tag="856" ind1=" " ind2=" ">
      <subfield code="u">https://www.cambridge.org/core/journals/astin-bulletin-journal-of-the-iaa/article/representationlearning-approach-for-insurance-pricing-with-images/E442676A2F597A9DBBDFC9FB986C3070</subfield>
    </datafield>
  </record>
</collection>