From point to probabilistic gradient boosting for claim frequency and severity prediction

<?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">MAP20260003023</controlfield>
    <controlfield tag="003">MAP</controlfield>
    <controlfield tag="005">20260211184311.0</controlfield>
    <controlfield tag="008">260206e20250811che|||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=" " ind2=" ">
      <subfield code="0">MAPA20260002408</subfield>
      <subfield code="a">Chevalier, Dominik</subfield>
    </datafield>
    <datafield tag="245" ind1="1" ind2="0">
      <subfield code="a">From point to probabilistic gradient boosting for claim frequency and severity prediction</subfield>
      <subfield code="c">Dominik Chevalier and Marie-Pier Côté</subfield>
    </datafield>
    <datafield tag="520" ind1=" " ind2=" ">
      <subfield code="a">This survey paper provides a comprehensive review of point and probabilistic gradient boosting algorithms applied to insurance claim frequency and severity modelling. The authors compare leading boosting methodssuch as GBM, XGBoost, LightGBM, CatBoost, EGBM, XGBoostLSS, cyc-GBM and NGBoostusing public insurance datasets of varying size and complexity. The study evaluates computational efficiency, predictive performance, model adequacy, and calibration. Results show that LightGBM and XGBoostLSS are the most computationally efficient, CatBoost performs well with high-cardinality categorical variables, and probabilistic boosting methods can improve model adequacy without sacrificing accuracy. The paper highlights that no single method is universally superior, and offers actuarial guidance for choosing boosting algorithms for pricing and risk modelling</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="4">
      <subfield code="0">MAPA20080592011</subfield>
      <subfield code="a">Modelos actuariales</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="4">
      <subfield code="0">MAPA20230006092</subfield>
      <subfield code="a">Frecuencia siniestral</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">MAPA20080611613</subfield>
      <subfield code="a">Modelos probabílisticos</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="4">
      <subfield code="0">MAPA20080564322</subfield>
      <subfield code="a">Tarificación</subfield>
    </datafield>
    <datafield tag="650" ind1=" " ind2="4">
      <subfield code="0">MAPA20080592059</subfield>
      <subfield code="a">Modelos predictivos</subfield>
    </datafield>
    <datafield tag="700" ind1="1" ind2=" ">
      <subfield code="0">MAPA20260002415</subfield>
      <subfield code="a">Côté, Marie-Pier</subfield>
    </datafield>
    <datafield tag="710" ind1="2" ind2=" ">
      <subfield code="0">MAPA20180008764</subfield>
      <subfield code="a">Springer</subfield>
    </datafield>
    <datafield tag="773" ind1="0" ind2=" ">
      <subfield code="w">MAP20220007085</subfield>
      <subfield code="g">11/08/2025 Volume 15 - Number 2 - August  2025 </subfield>
      <subfield code="t">European Actuarial Journal</subfield>
      <subfield code="d">Cham, Switzerland  : Springer Nature Switzerland AG,  2021-2022</subfield>
    </datafield>
  </record>
</collection>