<?xml version="1.0" encoding="utf-8"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:hal="http://hal.archives-ouvertes.fr/" xmlns:gml="http://www.opengis.net/gml/3.3/" xmlns:gmlce="http://www.opengis.net/gml/3.3/ce" version="1.1" xsi:schemaLocation="http://www.tei-c.org/ns/1.0 http://api.archives-ouvertes.fr/documents/aofr-sword.xsd">
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>HAL TEI export of hal-04015711</title>
      </titleStmt>
      <publicationStmt>
        <distributor>CCSD</distributor>
        <availability status="restricted">
          <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal</licence>
        </availability>
        <date when="2026-05-26T12:46:43+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">When stakes are high: balancing accuracy and transparency with Model-Agnostic Interpretable Data-driven suRRogates</title>
            <author role="aut">
              <persName>
                <forename type="first">Roel</forename>
                <surname>Henckaerts</surname>
              </persName>
              <email type="md5">163200da0c5fe4be136bc3acdd1f66ad</email>
              <email type="domain">kuleuven.be</email>
              <idno type="idhal" notation="numeric">1234135</idno>
              <idno type="halauthorid" notation="string">2747068-1234135</idno>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Katrien</forename>
                <surname>Antonio</surname>
              </persName>
              <idno type="halauthorid">2747046-0</idno>
              <affiliation ref="#struct-300656"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Marie-Pier</forename>
                <surname>Côté</surname>
              </persName>
              <idno type="halauthorid">2747069-0</idno>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Katrien</forename>
                <surname>Antonio</surname>
              </persName>
              <email type="md5">fe520a7c45e8e75f1e6bc3783f6e8576</email>
              <email type="domain">gmail.com</email>
            </editor>
            <funder>DIALOG</funder>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2023-03-06 10:04:34</date>
              <date type="whenModified">2026-05-12 10:18:05</date>
              <date type="whenReleased">2023-03-29 09:53:45</date>
              <date type="whenProduced">2020-12-10</date>
              <date type="whenEndEmbargoed">2023-03-06</date>
              <ref type="file" target="https://hal.science/hal-04015711v1/document">
                <date notBefore="2023-03-06"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-04015711v1/file/2007.06894.pdf" id="file-4015711-3497654">
                <date notBefore="2023-03-06"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="1392902">
                <persName>
                  <forename>Katrien</forename>
                  <surname>Antonio</surname>
                </persName>
                <email type="md5">fe520a7c45e8e75f1e6bc3783f6e8576</email>
                <email type="domain">gmail.com</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04015711</idno>
            <idno type="halUri">https://hal.science/hal-04015711</idno>
            <idno type="halBibtex">henckaerts:hal-04015711</idno>
            <idno type="halRefHtml">&lt;i&gt;Expert Systems with Applications&lt;/i&gt;, 2020, &lt;a target="_blank" href="https://dx.doi.org/10.48550/arXiv.2007.06894"&gt;&amp;#x27E8;10.48550/arXiv.2007.06894&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Expert Systems with Applications, 2020, &amp;#x27E8;10.48550/arXiv.2007.06894&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-4015711-3497654"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CHAIRE-DIALOG">Chaire Dialog</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">When stakes are high: balancing accuracy and transparency with Model-Agnostic Interpretable Data-driven suRRogates</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Roel</forename>
                    <surname>Henckaerts</surname>
                  </persName>
                  <email type="md5">163200da0c5fe4be136bc3acdd1f66ad</email>
                  <email type="domain">kuleuven.be</email>
                  <idno type="idhal" notation="numeric">1234135</idno>
                  <idno type="halauthorid" notation="string">2747068-1234135</idno>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Katrien</forename>
                    <surname>Antonio</surname>
                  </persName>
                  <idno type="halauthorid">2747046-0</idno>
                  <affiliation ref="#struct-300656"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Marie-Pier</forename>
                    <surname>Côté</surname>
                  </persName>
                  <idno type="halauthorid">2747069-0</idno>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">13229</idno>
                <idno type="issn">0957-4174</idno>
                <idno type="eissn">1873-6793</idno>
                <title level="j">Expert Systems with Applications</title>
                <imprint>
                  <publisher>Elsevier</publisher>
                  <date type="datePub">2020-12-10</date>
                </imprint>
              </monogr>
              <idno type="doi">10.48550/arXiv.2007.06894</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Feature selection</term>
                <term xml:lang="en">GLM</term>
                <term xml:lang="en">Insurance</term>
                <term xml:lang="en">Segmentation</term>
                <term xml:lang="en">XAI</term>
                <term xml:lang="en">Compliance</term>
                <term xml:lang="en">Compliance Feature selection GLM Insurance Segmentation XAI</term>
              </keywords>
              <classCode scheme="halDomain" n="stat.ml">Statistics [stat]/Machine Learning [stat.ML]</classCode>
              <classCode scheme="halTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halOldTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halTreeTypology" n="ART">Journal articles</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Highly regulated industries, like banking and insurance, ask for transparent decision-making algorithms. At the same time, competitive markets are pushing for the use of complex black box models. We therefore present a procedure to develop a Model-Agnostic Interpretable Data-driven suRRogate (maidrr) suited for structured tabular data. Knowledge is extracted from a black box via partial dependence effects. These are used to perform smart feature engineering by grouping variable values. This results in a segmentation of the feature space with automatic variable selection. A transparent generalized linear model (GLM) is fit to the features in categorical format and their relevant interactions. We demonstrate our R package maidrr with a case study on general insurance claim frequency modeling for six publicly available datasets. Our maidrr GLM closely approximates a gradient boosting machine (GBM) black box and outperforms both a linear and tree surrogate as benchmarks.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-300656" status="VALID">
          <idno type="IdRef">026458632</idno>
          <idno type="ROR">https://ror.org/05f950310</idno>
          <orgName>Catholic University of Leuven = Katholieke Universiteit Leuven</orgName>
          <orgName type="acronym">KU Leuven</orgName>
          <desc>
            <address>
              <addrLine>Oude Markt 13 - bus 5005, 3000 Leuven</addrLine>
              <country key="BE"/>
            </address>
            <ref type="url">http://www.kuleuven.be/english/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>