{"id":"https://openalex.org/W2963548617","doi":"https://doi.org/10.1109/tse.2018.2876537","title":"The Impact of Class Rebalancing Techniques on the Performance and Interpretation of Defect Prediction Models","display_name":"The Impact of Class Rebalancing Techniques on the Performance and Interpretation of Defect Prediction Models","publication_year":2018,"publication_date":"2018-10-17","ids":{"openalex":"https://openalex.org/W2963548617","doi":"https://doi.org/10.1109/tse.2018.2876537","mag":"2963548617"},"language":"en","primary_location":{"id":"doi:10.1109/tse.2018.2876537","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2018.2876537","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081449581","display_name":"Chakkrit Tantithamthavorn","orcid":"https://orcid.org/0000-0002-5516-9984"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Chakkrit Tantithamthavorn","raw_affiliation_strings":["Faculty of Information Technology, Monash University, Clayton, VIC, Australia"],"raw_orcid":"https://orcid.org/0000-0002-5516-9984","affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Monash University, Clayton, VIC, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091586373","display_name":"Ahmed E. Hassan","orcid":"https://orcid.org/0000-0001-7749-5513"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ahmed E. Hassan","raw_affiliation_strings":["School of Computing, Queen's University, Kingston, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing, Queen's University, Kingston, ON, Canada","institution_ids":["https://openalex.org/I204722609"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011588138","display_name":"Kenichi Matsumoto","orcid":"https://orcid.org/0000-0002-7418-9323"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kenichi Matsumoto","raw_affiliation_strings":["Graduate School of Information Science, Nara Institute of Science and Technology, Ikoma, Japan"],"raw_orcid":"https://orcid.org/0000-0002-7418-9323","affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, Nara Institute of Science and Technology, Ikoma, Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":44.6976,"has_fulltext":false,"cited_by_count":316,"citation_normalized_percentile":{"value":0.99778637,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"46","issue":"11","first_page":"1200","last_page":"1219"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12423","display_name":"Software Reliability and Analysis Research","score":0.9866999983787537,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8405883312225342},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6606180667877197},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6361232995986938},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6245733499526978},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.5384827256202698},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5084239840507507},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.495218425989151},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.43722596764564514},{"id":"https://openalex.org/keywords/predictive-modelling","display_name":"Predictive modelling","score":0.4329685568809509}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8405883312225342},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6606180667877197},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6361232995986938},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6245733499526978},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.5384827256202698},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5084239840507507},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.495218425989151},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.43722596764564514},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.4329685568809509},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tse.2018.2876537","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2018.2876537","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-article"},{"id":"pmh:oai:digital.library.adelaide.edu.au:2440/133849","is_oa":false,"landing_page_url":"https://hdl.handle.net/2440/133849","pdf_url":null,"source":{"id":"https://openalex.org/S4306401835","display_name":"Adelaide Research & Scholarship (AR&S) (University of Adelaide)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I5681781","host_organization_name":"The University of Adelaide","host_organization_lineage":["https://openalex.org/I5681781"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dx.doi.org/10.1109/tse.2018.2876537","raw_type":"Journal article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4000000059604645}],"awards":[{"id":"https://openalex.org/G4416570303","display_name":"Practical and Explainable Analytics to Prevent Future Software Defects","funder_award_id":"DE200100941","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":120,"referenced_works":["https://openalex.org/W25935857","https://openalex.org/W66570796","https://openalex.org/W168970045","https://openalex.org/W1920585257","https://openalex.org/W1964544799","https://openalex.org/W1971654961","https://openalex.org/W1991181258","https://openalex.org/W1993555269","https://openalex.org/W1994493193","https://openalex.org/W1995945562","https://openalex.org/W2005504865","https://openalex.org/W2007705030","https://openalex.org/W2020458104","https://openalex.org/W2022406334","https://openalex.org/W2024623357","https://openalex.org/W2033418259","https://openalex.org/W2034158106","https://openalex.org/W2037557484","https://openalex.org/W2038464048","https://openalex.org/W2038917214","https://openalex.org/W2040615655","https://openalex.org/W2041496338","https://openalex.org/W2046830558","https://openalex.org/W2051978688","https://openalex.org/W2060374620","https://openalex.org/W2067490448","https://openalex.org/W2068430427","https://openalex.org/W2073241381","https://openalex.org/W2074218040","https://openalex.org/W2093125667","https://openalex.org/W2094947835","https://openalex.org/W2096451472","https://openalex.org/W2096945460","https://openalex.org/W2097360283","https://openalex.org/W2097883090","https://openalex.org/W2098673848","https://openalex.org/W2103715428","https://openalex.org/W2105672266","https://openalex.org/W2105776892","https://openalex.org/W2107031757","https://openalex.org/W2107498895","https://openalex.org/W2107692981","https://openalex.org/W2108191500","https://openalex.org/W2108769867","https://openalex.org/W2109325327","https://openalex.org/W2109826612","https://openalex.org/W2110498832","https://openalex.org/W2110915013","https://openalex.org/W2114124859","https://openalex.org/W2115709314","https://openalex.org/W2117190680","https://openalex.org/W2118978333","https://openalex.org/W2119910794","https://openalex.org/W2120457925","https://openalex.org/W2122702470","https://openalex.org/W2125999269","https://openalex.org/W2129925362","https://openalex.org/W2130898128","https://openalex.org/W2132887549","https://openalex.org/W2134488238","https://openalex.org/W2142481192","https://openalex.org/W2146338950","https://openalex.org/W2147386665","https://openalex.org/W2148143831","https://openalex.org/W2148371346","https://openalex.org/W2151553346","https://openalex.org/W2151666086","https://openalex.org/W2158744032","https://openalex.org/W2163732854","https://openalex.org/W2163837601","https://openalex.org/W2164403426","https://openalex.org/W2171824022","https://openalex.org/W2172232422","https://openalex.org/W2218021565","https://openalex.org/W2297716127","https://openalex.org/W2367798545","https://openalex.org/W2374812233","https://openalex.org/W2408574027","https://openalex.org/W2474835145","https://openalex.org/W2516843914","https://openalex.org/W2562348157","https://openalex.org/W2568720339","https://openalex.org/W2570487166","https://openalex.org/W2589382121","https://openalex.org/W2589805776","https://openalex.org/W2737319015","https://openalex.org/W2786678788","https://openalex.org/W2795013017","https://openalex.org/W2808113972","https://openalex.org/W2808896747","https://openalex.org/W2963097549","https://openalex.org/W2963520355","https://openalex.org/W2987883775","https://openalex.org/W3106889297","https://openalex.org/W4206600618","https://openalex.org/W4232424506","https://openalex.org/W4236586490","https://openalex.org/W4240402692","https://openalex.org/W4243379839","https://openalex.org/W4243562335","https://openalex.org/W4245807786","https://openalex.org/W4250023757","https://openalex.org/W4285719527","https://openalex.org/W4294541781","https://openalex.org/W4295192648","https://openalex.org/W4399549220","https://openalex.org/W4399577370","https://openalex.org/W4399582985","https://openalex.org/W4399585247","https://openalex.org/W4399637125","https://openalex.org/W6602729356","https://openalex.org/W6667573648","https://openalex.org/W6676396137","https://openalex.org/W6734155205","https://openalex.org/W6747996232","https://openalex.org/W6748471295","https://openalex.org/W6752881601","https://openalex.org/W6769764061","https://openalex.org/W6869234452","https://openalex.org/W6869665370"],"related_works":["https://openalex.org/W4313320911","https://openalex.org/W4327743144","https://openalex.org/W4245077728","https://openalex.org/W2607424049","https://openalex.org/W4390922876","https://openalex.org/W3183204001","https://openalex.org/W4318612353","https://openalex.org/W4389829534","https://openalex.org/W4400065455","https://openalex.org/W4390939596"],"abstract_inverted_index":{"Defect":[0],"models":[1,43,152],"that":[2,130,139,166],"are":[3,21,118,175],"trained":[4],"on":[5,38,98,146,154],"class":[6,35,75,95,115,143],"imbalanced":[7],"datasets":[8,129],"(i.e.,":[9],"the":[10,32,39,51,82,92,99,110,140,147,155,160,167,172],"proportion":[11],"of":[12,34,41,53,56,84,94,104,127,142,149],"defective":[13],"and":[14,60,102,134,159,171,185,196],"clean":[15],"modules":[16],"is":[17],"not":[18],"equally":[19],"represented)":[20],"highly":[22],"susceptible":[23],"to":[24,50,69,182],"produce":[25],"inaccurate":[26],"prediction":[27,151],"models.":[28,86,106,122,200],"Prior":[29],"research":[30],"compares":[31],"impact":[33,93,141],"rebalancing":[36,76,96,116,144],"techniques":[37,77,97,117,145],"performance":[40,61,100,148,157],"defect":[42,85,105,121,150,199],"but":[44,188],"arrives":[45],"at":[46],"contradictory":[47,64],"conclusions":[48,65],"due":[49],"use":[52],"different":[54],"choice":[55],"datasets,":[57],"classification":[58,162],"techniques,":[59],"measures.":[62],"Such":[63],"make":[66],"it":[67],"hard":[68],"derive":[70],"practical":[71],"guidelines":[72],"for":[73,120],"whether":[74],"should":[78,190],"be":[79,191],"applied":[80],"in":[81,113],"context":[83],"In":[87],"this":[88],"paper,":[89],"we":[90,137],"investigate":[91,109],"measures":[101],"interpretation":[103],"We":[107,164],"also":[108],"experimental":[111],"settings":[112],"which":[114],"beneficial":[119,176],"Through":[123],"a":[124],"case":[125],"study":[126],"101":[128],"span":[131],"across":[132],"proprietary":[133],"open-source":[135],"systems,":[136],"conclude":[138],"depends":[153],"used":[156,161],"measure":[158],"techniques.":[163],"observe":[165],"optimized":[168],"SMOTE":[169],"technique":[170,174],"under-sampling":[173],"when":[177,193],"quality":[178],"assurance":[179],"teams":[180],"wish":[181],"increase":[183],"AUC":[184],"Recall,":[186],"respectively,":[187],"they":[189],"avoided":[192],"deriving":[194],"knowledge":[195],"understandings":[197],"from":[198]},"counts_by_year":[{"year":2026,"cited_by_count":19},{"year":2025,"cited_by_count":35},{"year":2024,"cited_by_count":51},{"year":2023,"cited_by_count":47},{"year":2022,"cited_by_count":53},{"year":2021,"cited_by_count":42},{"year":2020,"cited_by_count":37},{"year":2019,"cited_by_count":22},{"year":2018,"cited_by_count":10}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}