<?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-05318949</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="2026-05-03T11:04:07+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Categorical Data Encoding:  from H.O. Hirschfeld to Machine Learning</title>
            <author role="aut">
              <persName>
                <forename type="first">Gilbert</forename>
                <surname>Saporta</surname>
              </persName>
              <email type="md5">6298c57098dc5d21247fd35757d2103d</email>
              <email type="domain">cnam.fr</email>
              <idno type="idhal" notation="string">gilbert-saporta</idno>
              <idno type="idhal" notation="numeric">180161</idno>
              <idno type="halauthorid" notation="string">4563-180161</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-3406-5887</idno>
              <idno type="IDREF">https://www.idref.fr/027122565</idno>
              <idno type="ARXIV">https://arxiv.org/a/saporta_g_1</idno>
              <affiliation ref="#struct-390785"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Gilbert</forename>
                <surname>Saporta</surname>
              </persName>
              <email type="md5">6298c57098dc5d21247fd35757d2103d</email>
              <email type="domain">cnam.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2025-10-17 09:08:03</date>
              <date type="whenModified">2025-10-19 03:13:54</date>
              <date type="whenReleased">2025-10-17 09:08:03</date>
              <date type="whenProduced">2025-10-05</date>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="167713">
                <persName>
                  <forename>Gilbert</forename>
                  <surname>Saporta</surname>
                </persName>
                <email type="md5">6298c57098dc5d21247fd35757d2103d</email>
                <email type="domain">cnam.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-05318949</idno>
            <idno type="halUri">https://cnam.hal.science/hal-05318949</idno>
            <idno type="halBibtex">saporta:hal-05318949</idno>
            <idno type="halRefHtml">&lt;i&gt;65th ISI World Statistics Congress&lt;/i&gt;, International Statistical Institute, Oct 2025, La Haye, Netherlands</idno>
            <idno type="halRef">65th ISI World Statistics Congress, International Statistical Institute, Oct 2025, La Haye, Netherlands</idno>
            <availability status="restricted"/>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNAM">Conservatoire National des Arts et Métiers</idno>
            <idno type="stamp" n="CEDRIC-CNAM" corresp="CNAM">Centre d'études et de recherche en informatique et communications </idno>
            <idno type="stamp" n="HESAM-CNAM" corresp="HESAM">Conservatoire National des Arts et Métiers - Hesam</idno>
            <idno type="stamp" n="HESAM">Hesam</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="invited" n="0">No</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
            <note type="proceedings" n="0">No</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Categorical Data Encoding:  from H.O. Hirschfeld to Machine Learning</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Gilbert</forename>
                    <surname>Saporta</surname>
                  </persName>
                  <email type="md5">6298c57098dc5d21247fd35757d2103d</email>
                  <email type="domain">cnam.fr</email>
                  <idno type="idhal" notation="string">gilbert-saporta</idno>
                  <idno type="idhal" notation="numeric">180161</idno>
                  <idno type="halauthorid" notation="string">4563-180161</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-3406-5887</idno>
                  <idno type="IDREF">https://www.idref.fr/027122565</idno>
                  <idno type="ARXIV">https://arxiv.org/a/saporta_g_1</idno>
                  <affiliation ref="#struct-390785"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>65th ISI World Statistics Congress</title>
                  <date type="start">2025-10-05</date>
                  <date type="end">2025-10-09</date>
                  <settlement>La Haye</settlement>
                  <country key="NL">Netherlands</country>
                </meeting>
                <respStmt>
                  <resp>conferenceOrganizer</resp>
                  <name>International Statistical Institute</name>
                </respStmt>
                <imprint/>
              </monogr>
              <ref type="publisher">https://www.isi-next.org/conferences/isi-wsc2025/</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">optimal scaling, categorical data, encoding</term>
              </keywords>
              <classCode scheme="halDomain" n="stat">Statistics [stat]</classCode>
              <classCode scheme="halDomain" n="stat.ml">Statistics [stat]/Machine Learning [stat.ML]</classCode>
              <classCode scheme="halTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halOldTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halTreeTypology" n="COMM">Conference papers</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>The need for Machine Learning algorithms to convert qualitative data into numerical data has led to many (and sometimes incongruous) proposals or to the rediscovery of work by statisticians dating back almost a century. The optimal coding methods developed by Hirschfeld (aka H.O. Hartley), R.A.Fisher, L.Guttmann, C.Hayashi and many others are at the origin of correspondence analysis. The links with the search for transformations to normal distributions were established by H.O.Lancaster, M.Kendall and A. Stuart. This paper starting with pioneering work in the 1930s, will provide an overview of the various approaches up to the current revival inspired by the need to process high-dimensional categorical data.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-390785" status="VALID">
          <orgName>CEDRIC. Méthodes statistiques de data-mining et apprentissage</orgName>
          <orgName type="acronym">CEDRIC - MSDMA</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-16574" type="direct"/>
            <relation name="EA4629" active="#struct-179741" type="indirect"/>
            <relation name="EA4629" active="#struct-300351" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-16574" status="VALID">
          <idno type="IdRef">155463381</idno>
          <idno type="RNSR">201119480F</idno>
          <idno type="ROR">https://ror.org/044j5mm75</idno>
          <orgName>Centre d'études et de recherche en informatique et communications</orgName>
          <orgName type="acronym">CEDRIC</orgName>
          <desc>
            <address>
              <addrLine>292 rue Saint-Martin 75141 PARIS Cedex 03Case courrier 2D4P30</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://cedric.cnam.fr/</ref>
          </desc>
          <listRelation>
            <relation name="EA4629" active="#struct-179741" type="direct"/>
            <relation name="EA4629" active="#struct-300351" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-179741" status="VALID">
          <orgName>Ecole Nationale Supérieure d'Informatique pour l'Industrie et l'Entreprise</orgName>
          <orgName type="acronym">ENSIIE</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ensiie.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-300351" status="VALID">
          <idno type="IdRef">027404978</idno>
          <idno type="ISNI">0000000121690459</idno>
          <idno type="ROR">https://ror.org/0175hh227</idno>
          <orgName>Conservatoire National des Arts et Métiers [Cnam]</orgName>
          <orgName type="acronym">Cnam</orgName>
          <desc>
            <address>
              <addrLine>292 Rue Saint-Martin, 75003 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.cnam.fr/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>