<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet type="text/xsl" href="static/style.xsl"?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-11-22T17:09:54Z</responseDate><request verb="GetRecord" identifier="oai:vdu.lt:20.500.12259/110816" metadataPrefix="oai_dc">https://portalcris.vdu.lt/server/oai/request</request><GetRecord><record><header><identifier>oai:vdu.lt:20.500.12259/110816</identifier><datestamp>2026-06-04T11:29:02Z</datestamp><setSpec>com_20.500.12259_1176</setSpec><setSpec>com_20.500.12259_36909</setSpec><setSpec>com_20.500.12259_156110</setSpec><setSpec>col_20.500.12259_30708</setSpec><setSpec>col_20.500.12259_36910</setSpec></header><metadata><oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:doc="http://www.lyncode.com/xoai" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
   <dc:title>Fraud detection in health insurance using ensemble learning methods</dc:title>
   <dc:creator>Kunickaitė, Rimantė</dc:creator>
   <dc:creator>Zdanavičiūtė, Monika</dc:creator>
   <dc:creator>Krilavičius, Tomas</dc:creator>
   <dc:subject>Insurance</dc:subject>
   <dc:subject>Fraud</dc:subject>
   <dc:subject>Ensemble learning</dc:subject>
   <dc:subject>Machine learning</dc:subject>
   <dc:subject>Straipsnis konferencijos medžiagoje Scopus duomenų bazėje / Article in conference proceedings in Scopus database (P1a2)</dc:subject>
   <dc:subject>Informatika  / Informatics (N009)</dc:subject>
   <dc:description>Insurance fraud is one of the most expensive economic financial crimes. Most risk management solutions use rules to detect potential abuse, but as the patterns of abuse change, those solutions become ineffective. In this paper we apply machine learning (Decision Trees, Bagging, Random Forests and Boosting) for fraud detection in health insurance. Performance of the model is evaluated using accuracy, error rate, sensitivity and specificity. The best results were achieved using Bagging technique. In further research it would be useful to analyze applicability of deep learning models and anomaly detection methods.</dc:description>
   <dc:description>Matematikos ir statistikos katedra / Department of Mathematics and Statistics</dc:description>
   <dc:description>Taikomosios informatikos katedra / Department of Applied Informatics</dc:description>
   <dc:description>Informatikos fakultetas / Faculty of Informatics</dc:description>
   <dc:description>Vytauto Didžiojo universitetas / Vytautas Magnus University</dc:description>
   <dc:date>2020-10-27T19:02:21Z</dc:date>
   <dc:date>2020-10-27T19:02:21Z</dc:date>
   <dc:date>2020</dc:date>
   <dc:date>2020-10-30T10:10Z</dc:date>
   <dc:type>type::text::journal::journal article::research article</dc:type>
   <dc:identifier>VDU02-000064545</dc:identifier>
   <dc:identifier>https://www.vdu.lt/cris/bitstream/20.500.12259/110816/2/ISSN1613-0073_2020_V_2698.PG_70-77.pdf</dc:identifier>
   <dc:identifier>https://hdl.handle.net/20.500.12259/110816</dc:identifier>
   <dc:language>en</dc:language>
   <dc:relation>CEUR Workshop proceedings [electronic resource]: IVUS 2020, Information society and university studies, Kaunas, Lithuania, 23 April, 2020: proceedings. Aachen : CEUR-WS, 2020, Vol. 2698</dc:relation>
   <dc:relation>Scopus</dc:relation>
   <dc:relation>1613-0073</dc:relation>
   <dc:rights>open access</dc:rights>
   <dc:format>p. 70-77</dc:format>
   <dc:format>application/pdf</dc:format>
   <dc:format>application/pdf</dc:format>
   <dc:coverage>DE</dc:coverage>
   <dc:publisher>Aachen : CEUR-WS</dc:publisher>
</oai_dc:dc>
</metadata></record></GetRecord></OAI-PMH>