<?xml version='1.0' encoding='utf-8'?>
<eprints xmlns='http://eprints.org/ep2/data/2.0'>
  <eprint id='https://pure.iiasa.ac.at/id/eprint/20573'>
    <eprintid>20573</eprintid>
    <rev_number>6</rev_number>
    <documents>
      <document id='https://pure.iiasa.ac.at/id/document/109735'>
        <docid>109735</docid>
        <rev_number>2</rev_number>
        <files>
          <file id='https://pure.iiasa.ac.at/id/file/332725'>
            <fileid>332725</fileid>
            <datasetid>document</datasetid>
            <objectid>109735</objectid>
            <filename>fdata-1-1542483.pdf</filename>
            <mime_type>application/pdf</mime_type>
            <hash>e80b0ef41a8935f9cb5b5881078f8fd9</hash>
            <hash_type>MD5</hash_type>
            <filesize>2377693</filesize>
            <mtime>2025-05-12 07:40:51</mtime>
            <url>https://pure.iiasa.ac.at/id/eprint/20573/1/fdata-1-1542483.pdf</url>
          </file>
        </files>
        <eprintid>20573</eprintid>
        <pos>1</pos>
        <placement>1</placement>
        <mime_type>application/pdf</mime_type>
        <format>text</format>
        <language>en</language>
        <security>public</security>
        <license>cc_by_4</license>
        <main>fdata-1-1542483.pdf</main>
        <content>published</content>
      </document>
      <document id='https://pure.iiasa.ac.at/id/document/109742'>
        <docid>109742</docid>
        <rev_number>2</rev_number>
        <files>
          <file id='https://pure.iiasa.ac.at/id/file/332740'>
            <fileid>332740</fileid>
            <datasetid>document</datasetid>
            <objectid>109742</objectid>
            <filename>lightbox.jpg</filename>
            <mime_type>image/png</mime_type>
            <hash>8805f42018ba8f653d652cc9f32a1a18</hash>
            <hash_type>MD5</hash_type>
            <filesize>41391</filesize>
            <mtime>2025-05-12 07:50:52</mtime>
            <url>https://pure.iiasa.ac.at/id/eprint/20573/2/lightbox.jpg</url>
          </file>
        </files>
        <eprintid>20573</eprintid>
        <pos>2</pos>
        <placement>2</placement>
        <mime_type>image/png</mime_type>
        <format>other</format>
        <formatdesc>Thumbnails conversion from text to thumbnail_lightbox</formatdesc>
        <language>en</language>
        <security>public</security>
        <main>lightbox.jpg</main>
        <relation>
          <item>
            <type>http://eprints.org/relation/isVersionOf</type>
            <uri>https://pure.iiasa.ac.at/id/document/109735</uri>
          </item>
          <item>
            <type>http://eprints.org/relation/isVolatileVersionOf</type>
            <uri>https://pure.iiasa.ac.at/id/document/109735</uri>
          </item>
          <item>
            <type>http://eprints.org/relation/islightboxThumbnailVersionOf</type>
            <uri>https://pure.iiasa.ac.at/id/document/109735</uri>
          </item>
        </relation>
      </document>
      <document id='https://pure.iiasa.ac.at/id/document/109743'>
        <docid>109743</docid>
        <rev_number>2</rev_number>
        <files>
          <file id='https://pure.iiasa.ac.at/id/file/332741'>
            <fileid>332741</fileid>
            <datasetid>document</datasetid>
            <objectid>109743</objectid>
            <filename>preview.jpg</filename>
            <mime_type>image/png</mime_type>
            <hash>00398f49b965c1cb9142d1e7dfab6183</hash>
            <hash_type>MD5</hash_type>
            <filesize>17749</filesize>
            <mtime>2025-05-12 07:50:52</mtime>
            <url>https://pure.iiasa.ac.at/id/eprint/20573/3/preview.jpg</url>
          </file>
        </files>
        <eprintid>20573</eprintid>
        <pos>3</pos>
        <placement>3</placement>
        <mime_type>image/png</mime_type>
        <format>other</format>
        <formatdesc>Thumbnails conversion from text to thumbnail_preview</formatdesc>
        <language>en</language>
        <security>public</security>
        <main>preview.jpg</main>
        <relation>
          <item>
            <type>http://eprints.org/relation/isVersionOf</type>
            <uri>https://pure.iiasa.ac.at/id/document/109735</uri>
          </item>
          <item>
            <type>http://eprints.org/relation/isVolatileVersionOf</type>
            <uri>https://pure.iiasa.ac.at/id/document/109735</uri>
          </item>
          <item>
            <type>http://eprints.org/relation/ispreviewThumbnailVersionOf</type>
            <uri>https://pure.iiasa.ac.at/id/document/109735</uri>
          </item>
        </relation>
      </document>
      <document id='https://pure.iiasa.ac.at/id/document/109744'>
        <docid>109744</docid>
        <rev_number>2</rev_number>
        <files>
          <file id='https://pure.iiasa.ac.at/id/file/332742'>
            <fileid>332742</fileid>
            <datasetid>document</datasetid>
            <objectid>109744</objectid>
            <filename>medium.jpg</filename>
            <mime_type>image/png</mime_type>
            <hash>0b1185787967f8bd0f4736ffd7bbc124</hash>
            <hash_type>MD5</hash_type>
            <filesize>6129</filesize>
            <mtime>2025-05-12 07:50:53</mtime>
            <url>https://pure.iiasa.ac.at/id/eprint/20573/4/medium.jpg</url>
          </file>
        </files>
        <eprintid>20573</eprintid>
        <pos>4</pos>
        <placement>4</placement>
        <mime_type>image/png</mime_type>
        <format>other</format>
        <formatdesc>Thumbnails conversion from text to thumbnail_medium</formatdesc>
        <language>en</language>
        <security>public</security>
        <main>medium.jpg</main>
        <relation>
          <item>
            <type>http://eprints.org/relation/isVersionOf</type>
            <uri>https://pure.iiasa.ac.at/id/document/109735</uri>
          </item>
          <item>
            <type>http://eprints.org/relation/isVolatileVersionOf</type>
            <uri>https://pure.iiasa.ac.at/id/document/109735</uri>
          </item>
          <item>
            <type>http://eprints.org/relation/ismediumThumbnailVersionOf</type>
            <uri>https://pure.iiasa.ac.at/id/document/109735</uri>
          </item>
        </relation>
      </document>
      <document id='https://pure.iiasa.ac.at/id/document/109745'>
        <docid>109745</docid>
        <rev_number>2</rev_number>
        <files>
          <file id='https://pure.iiasa.ac.at/id/file/332743'>
            <fileid>332743</fileid>
            <datasetid>document</datasetid>
            <objectid>109745</objectid>
            <filename>small.jpg</filename>
            <mime_type>image/png</mime_type>
            <hash>5d24e59f7d38a91330741f06f1026cf3</hash>
            <hash_type>MD5</hash_type>
            <filesize>1870</filesize>
            <mtime>2025-05-12 07:50:53</mtime>
            <url>https://pure.iiasa.ac.at/id/eprint/20573/5/small.jpg</url>
          </file>
        </files>
        <eprintid>20573</eprintid>
        <pos>5</pos>
        <placement>5</placement>
        <mime_type>image/png</mime_type>
        <format>other</format>
        <formatdesc>Thumbnails conversion from text to thumbnail_small</formatdesc>
        <language>en</language>
        <security>public</security>
        <main>small.jpg</main>
        <relation>
          <item>
            <type>http://eprints.org/relation/isVersionOf</type>
            <uri>https://pure.iiasa.ac.at/id/document/109735</uri>
          </item>
          <item>
            <type>http://eprints.org/relation/isVolatileVersionOf</type>
            <uri>https://pure.iiasa.ac.at/id/document/109735</uri>
          </item>
          <item>
            <type>http://eprints.org/relation/issmallThumbnailVersionOf</type>
            <uri>https://pure.iiasa.ac.at/id/document/109735</uri>
          </item>
        </relation>
      </document>
      <document id='https://pure.iiasa.ac.at/id/document/109746'>
        <docid>109746</docid>
        <rev_number>1</rev_number>
        <files>
          <file id='https://pure.iiasa.ac.at/id/file/332744'>
            <fileid>332744</fileid>
            <datasetid>document</datasetid>
            <objectid>109746</objectid>
            <filename>indexcodes.txt</filename>
            <mime_type>text/plain</mime_type>
            <hash>d3fe6b897b928db7ae2d255635ced951</hash>
            <hash_type>MD5</hash_type>
            <filesize>11320</filesize>
            <mtime>2025-05-12 07:50:54</mtime>
            <url>https://pure.iiasa.ac.at/id/eprint/20573/6/indexcodes.txt</url>
          </file>
        </files>
        <eprintid>20573</eprintid>
        <pos>6</pos>
        <placement>6</placement>
        <mime_type>text/plain</mime_type>
        <format>other</format>
        <formatdesc>Generate index codes conversion from text to indexcodes</formatdesc>
        <language>en</language>
        <security>public</security>
        <main>indexcodes.txt</main>
        <relation>
          <item>
            <type>http://eprints.org/relation/isVersionOf</type>
            <uri>https://pure.iiasa.ac.at/id/document/109735</uri>
          </item>
          <item>
            <type>http://eprints.org/relation/isVolatileVersionOf</type>
            <uri>https://pure.iiasa.ac.at/id/document/109735</uri>
          </item>
          <item>
            <type>http://eprints.org/relation/isIndexCodesVersionOf</type>
            <uri>https://pure.iiasa.ac.at/id/document/109735</uri>
          </item>
        </relation>
      </document>
    </documents>
    <eprint_status>archive</eprint_status>
    <userid>353</userid>
    <dir>disk0/00/02/05/73</dir>
    <datestamp>2025-05-12 07:41:48</datestamp>
    <lastmod>2025-05-12 07:41:48</lastmod>
    <status_changed>2025-05-12 07:41:48</status_changed>
    <type>article</type>
    <metadata_visibility>show</metadata_visibility>
    <creators>
      <item>
        <name>
          <family>Hassani</family>
          <given>H.</given>
        </name>
        <id>9469</id>
      </item>
      <item>
        <name>
          <family>Entezarian</family>
          <given>M.R.</given>
        </name>
      </item>
      <item>
        <name>
          <family>Zaeimzadeh</family>
          <given>S.</given>
        </name>
      </item>
      <item>
        <name>
          <family>Marvian</family>
          <given>L.</given>
        </name>
      </item>
      <item>
        <name>
          <family>Komendantova</family>
          <given>N.</given>
        </name>
        <id>1880</id>
        <orcid>0000-0003-2568-6179</orcid>
      </item>
    </creators>
    <title>An oversampling-undersampling strategy for large-scale data linkage</title>
    <ispublished>pub</ispublished>
    <divisions>
      <item>ASA</item>
      <item>CAT</item>
    </divisions>
    <abstract>Effective record linkage in big data, particularly in imbalanced datasets, is a critical yet highly challenging task due to the inherent complexity involved. This article utilizes an oversampling-undersampling strategy to address linkage imbalances, enabling more accurate and efficient record linkage within large-scale datasets. It tries to increase the instances of the minority class and decrease the dominance of the majority classes to try to reach a more balanced dataset that can be used for training and testing. Sensitivity testing was carried out by varying the training-test ratio and degree of imbalance.</abstract>
    <date>2025-04-23</date>
    <date_type>published</date_type>
    <id_number>doi:10.3389/fdata.2025.1542483</id_number>
    <creators_browse_id>
      <item>3410</item>
      <item>161</item>
    </creators_browse_id>
    <full_text_status>public</full_text_status>
    <publication>Frontiers in Big Data</publication>
    <volume>8</volume>
    <refereed>TRUE</refereed>
    <issn>2624-909X</issn>
    <fp7_type>info:eu-repo/semantics/article</fp7_type>
  </eprint>
</eprints>
