{"id":"https://openalex.org/W6893630458","doi":"https://doi.org/10.5281/zenodo.3855094","title":"On the Performance of Oversampling Techniques for Class Imbalance Problems","display_name":"On the Performance of Oversampling Techniques for Class Imbalance Problems","publication_year":2020,"publication_date":"2020-05-06","ids":{"openalex":"https://openalex.org/W6893630458","doi":"https://doi.org/10.5281/zenodo.3855094"},"language":"en","primary_location":{"id":"pmh:oai:zenodo.org:3855094","is_oa":true,"landing_page_url":"https://zenodo.org/record/3855094","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/other"},"type":"other","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/3855094","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jiawen Kong","orcid":null},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Jiawen Kong","raw_affiliation_strings":["University of Leiden"],"affiliations":[{"raw_affiliation_string":"University of Leiden","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Thiago Rios","orcid":null},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Thiago Rios","raw_affiliation_strings":["Honda Research Institute Europe GmBH"],"affiliations":[{"raw_affiliation_string":"Honda Research Institute Europe GmBH","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kowalczyk, Wojtek","orcid":"https://orcid.org/0000-0002-6973-1341"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Kowalczyk, Wojtek","raw_affiliation_strings":["University of Leiden"],"affiliations":[{"raw_affiliation_string":"University of Leiden","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Menzel, Stefan","orcid":null},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Menzel, Stefan","raw_affiliation_strings":["Honda Research Institute Europe GmBH"],"affiliations":[{"raw_affiliation_string":"Honda Research Institute Europe GmBH","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"last","author":{"id":null,"display_name":"B\u00e4ck, Thomas","orcid":"https://orcid.org/0000-0001-6768-1478"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"B\u00e4ck, Thomas","raw_affiliation_strings":["University of Leiden"],"affiliations":[{"raw_affiliation_string":"University of Leiden","institution_ids":["https://openalex.org/I121797337"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I121797337"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.9822999835014343},{"id":"https://openalex.org/keywords/resampling","display_name":"Resampling","score":0.8133999705314636},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.70169997215271},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6036999821662903},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.48980000615119934},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4587000012397766},{"id":"https://openalex.org/keywords/bootstrapping","display_name":"Bootstrapping (finance)","score":0.3977000117301941},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.3856000006198883}],"concepts":[{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.9822999835014343},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.8133999705314636},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.70169997215271},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6337000131607056},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6036999821662903},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5273000001907349},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.48980000615119934},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48100000619888306},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4587000012397766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4472000002861023},{"id":"https://openalex.org/C207609745","wikidata":"https://www.wikidata.org/wiki/Q4944086","display_name":"Bootstrapping (finance)","level":2,"score":0.3977000117301941},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3856000006198883},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3781999945640564},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3652999997138977},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29120001196861267},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:zenodo.org:3855094","is_oa":true,"landing_page_url":"https://zenodo.org/record/3855094","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/other"},{"id":"doi:10.5281/zenodo.3855094","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.3855094","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:3855094","is_oa":true,"landing_page_url":"https://zenodo.org/record/3855094","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/other"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"file":[1],"is":[2],"the":[3,8,23,33,58,64,74,92,114,128,132,155,169,174,181,204,216],"source":[4],"code":[5],"used":[6],"in":[7,32,57,122,193],"paper":[9],"below:":[10],"Jiawen":[11],"Kong,":[12],"Thiago":[13],"Rios,":[14],"Wojtek":[15],"Kowalczyk,":[16],"Stefan":[17],"Menzel":[18],"and":[19,40,67,102,125,147,180],"Thomas":[20],"B\u00e4ck,":[21],"\u201cOn":[22],"Performance":[24],"of":[25,63,94,172,183],"Oversampling":[26],"Techniques":[27],"for":[28,168,202],"Class":[29],"Imbalance":[30],"Problems\u201d":[31],"24th":[34],"Pacific-Asia":[35],"Conference":[36],"on":[37,73,83,141],"Knowledge":[38],"Discovery":[39],"Data":[41],"Mining,":[42],"Singapore,":[43],"11-14":[44],"May":[45],"2020,":[46],"doi:":[47],"10.1007/978-3-030-47436-2_7":[48],"Although":[49,186],"over":[50],"90":[51],"oversampling":[52,97,110,151],"approaches":[53],"have":[54],"been":[55],"developed":[56],"imbalance":[59],"learning":[60],"domain,":[61],"most":[62,123,207],"empirical":[65],"study":[66,91],"application":[68],"work":[69],"are":[70,87,166],"still":[71],"based":[72],"\u201cclassical\u201d":[75,101],"resampling":[76,184],"techniques.":[77,185],"In":[78,160],"this":[79],"paper,":[80],"several":[81],"experiments":[82],"19":[84],"benchmark":[85],"datasets":[86,146],"set":[88],"up":[89],"to":[90,106],"efficiency":[93],"six":[95,133],"powerful":[96],"approaches,":[98],"including":[99],"both":[100],"new":[103],"ones.":[104],"According":[105],"our":[107,139,142,194],"experimental":[108],"results,":[109],"techniques":[111,152],"that":[112],"consider":[113],"minority":[115],"class":[116],"distribution":[117],"(new":[118],"ones)":[119],"perform":[120],"better":[121],"cases":[124],"RACOG":[126],"gives":[127],"best":[129],"performance":[130,156],"among":[131],"reviewed":[134],"approaches.":[135],"We":[136],"further":[137],"validate":[138],"conclusion":[140],"real-world":[143],"inspired":[144],"vehicle":[145],"also":[148],"find":[149,197],"applying":[150],"can":[153,190],"improve":[154],"by":[157],"around":[158],"10%.":[159],"addition,":[161],"seven":[162],"data":[163,177],"complexity":[164,178],"measures":[165,179],"considered":[167],"initial":[170],"purpose":[171],"investigating":[173],"relationship":[175,189],"between":[176],"choice":[182],"no":[187],"obvious":[188],"be":[191],"abstracted":[192],"experiments,":[195],"we":[196],"F1v":[198],"value,":[199],"a":[200,211],"measure":[201],"evaluating":[203],"overlap":[205],"which":[206],"researchers":[208],"ignore,":[209],"has":[210],"strong":[212],"negative":[213],"correlation":[214],"with":[215],"potential":[217],"AUC":[218],"value":[219],"(after":[220],"resampling).":[221]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}