{"id":"https://openalex.org/W4245807786","doi":"https://doi.org/10.1109/tse.2017.2731766","title":"MAHAKIL: Diversity Based Oversampling Approach to Alleviate the Class Imbalance Issue in Software Defect Prediction","display_name":"MAHAKIL: Diversity Based Oversampling Approach to Alleviate the Class Imbalance Issue in Software Defect Prediction","publication_year":2017,"publication_date":"2017-07-25","ids":{"openalex":"https://openalex.org/W4245807786","doi":"https://doi.org/10.1109/tse.2017.2731766"},"language":"en","primary_location":{"id":"doi:10.1109/tse.2017.2731766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2017.2731766","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,"listed_in":["cwts-core","jufo-3","norway-2"],"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/A5012394915","display_name":"Kwabena Ebo Bennin","orcid":"https://orcid.org/0000-0001-9140-9271","observed_orcids":["https://orcid.org/0000-0001-9140-9271"]},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kwabena Ebo Bennin","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-9140-9271","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051403641","display_name":"Jacky Keung","orcid":"https://orcid.org/0000-0002-3803-9600","observed_orcids":["https://orcid.org/0000-0002-3803-9600"]},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jacky Keung","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022069660","display_name":"Passakorn Phannachitta","orcid":"https://orcid.org/0000-0003-3931-9097","observed_orcids":["https://orcid.org/0000-0003-3931-9097"]},"institutions":[{"id":"https://openalex.org/I48076826","display_name":"Chiang Mai University","ror":"https://ror.org/05m2fqn25","country_code":"TH","type":"education","lineage":["https://openalex.org/I48076826"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Passakorn Phannachitta","raw_affiliation_strings":["College of Arts, Media and Technology, Chiang Mai University, Chiang Mai, Thailand"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Arts, Media and Technology, Chiang Mai University, Chiang Mai, Thailand","institution_ids":["https://openalex.org/I48076826"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078686662","display_name":"Akito Monden","orcid":"https://orcid.org/0000-0003-4295-207X","observed_orcids":["https://orcid.org/0000-0003-4295-207X"]},"institutions":[{"id":"https://openalex.org/I163770644","display_name":"Okayama University","ror":"https://ror.org/02pc6pc55","country_code":"JP","type":"education","lineage":["https://openalex.org/I163770644"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akito Monden","raw_affiliation_strings":["Graduate School of Natural Science and Technology, Okayama University, Okayama, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Natural Science and Technology, Okayama University, Okayama, Japan","institution_ids":["https://openalex.org/I163770644"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020836505","display_name":"Solomon Mensah","orcid":"https://orcid.org/0000-0001-5629-2661","observed_orcids":["https://orcid.org/0000-0001-5629-2661"]},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Solomon Mensah","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-5629-2661","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Kowloon Tong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":58.6272,"has_fulltext":false,"cited_by_count":297,"citation_normalized_percentile":{"value":0.99863459,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"44","issue":"6","first_page":"534","last_page":"550"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9894000291824341,"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":0.9884999990463257,"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/oversampling","display_name":"Oversampling","score":0.9741464853286743},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7906148433685303},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6518341898918152},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6223573684692383},{"id":"https://openalex.org/keywords/software-bug","display_name":"Software bug","score":0.6017430424690247},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.545463502407074},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5345444083213806},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5325160622596741},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.523598313331604},{"id":"https://openalex.org/keywords/inheritance","display_name":"Inheritance (genetic algorithm)","score":0.4153589606285095},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09957057237625122},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09338206052780151}],"concepts":[{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.9741464853286743},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7906148433685303},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6518341898918152},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6223573684692383},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.6017430424690247},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.545463502407074},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5345444083213806},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5325160622596741},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.523598313331604},{"id":"https://openalex.org/C2780902518","wikidata":"https://www.wikidata.org/wiki/Q6033780","display_name":"Inheritance (genetic algorithm)","level":3,"score":0.4153589606285095},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09957057237625122},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09338206052780151},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tse.2017.2731766","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2017.2731766","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,"listed_in":["cwts-core","jufo-3","norway-2"],"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"}],"best_oa_location":null,"sustainable_development_goals":[],"x_sdgs":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1530292997","display_name":null,"funder_award_id":"7004474","funder_id":"https://openalex.org/F4320309893","funder_display_name":"City University of Hong Kong"},{"id":"https://openalex.org/G4574520152","display_name":null,"funder_award_id":"7004683","funder_id":"https://openalex.org/F4320309893","funder_display_name":"City University of Hong Kong"}],"funders":[{"id":"https://openalex.org/F4320309893","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":90,"referenced_works":["https://openalex.org/W85350352","https://openalex.org/W87312633","https://openalex.org/W203932818","https://openalex.org/W273955616","https://openalex.org/W1533970595","https://openalex.org/W1540596182","https://openalex.org/W1563938718","https://openalex.org/W1574715085","https://openalex.org/W1595468493","https://openalex.org/W1916142487","https://openalex.org/W1941659294","https://openalex.org/W1975040830","https://openalex.org/W1981554658","https://openalex.org/W1984026144","https://openalex.org/W1989141971","https://openalex.org/W1992331847","https://openalex.org/W2003638356","https://openalex.org/W2004902747","https://openalex.org/W2006658471","https://openalex.org/W2008596407","https://openalex.org/W2012591582","https://openalex.org/W2014455254","https://openalex.org/W2025700486","https://openalex.org/W2026742411","https://openalex.org/W2039081830","https://openalex.org/W2048456683","https://openalex.org/W2056601071","https://openalex.org/W2058732827","https://openalex.org/W2059171296","https://openalex.org/W2062020999","https://openalex.org/W2072043274","https://openalex.org/W2087240369","https://openalex.org/W2090135786","https://openalex.org/W2090954654","https://openalex.org/W2101227285","https://openalex.org/W2103614420","https://openalex.org/W2103715428","https://openalex.org/W2104933073","https://openalex.org/W2105776892","https://openalex.org/W2110656807","https://openalex.org/W2113224932","https://openalex.org/W2118978333","https://openalex.org/W2119157339","https://openalex.org/W2120457925","https://openalex.org/W2120474334","https://openalex.org/W2120484483","https://openalex.org/W2121866145","https://openalex.org/W2122111042","https://openalex.org/W2123127356","https://openalex.org/W2125055259","https://openalex.org/W2125999269","https://openalex.org/W2126326838","https://openalex.org/W2126626812","https://openalex.org/W2132791018","https://openalex.org/W2133711389","https://openalex.org/W2133869716","https://openalex.org/W2136706100","https://openalex.org/W2137235241","https://openalex.org/W2139164805","https://openalex.org/W2141051748","https://openalex.org/W2141081944","https://openalex.org/W2143637886","https://openalex.org/W2148143831","https://openalex.org/W2151666086","https://openalex.org/W2163590173","https://openalex.org/W2168453597","https://openalex.org/W2172232422","https://openalex.org/W2424693453","https://openalex.org/W2493218965","https://openalex.org/W2510312579","https://openalex.org/W2528160956","https://openalex.org/W2582743722","https://openalex.org/W2775159301","https://openalex.org/W2911964244","https://openalex.org/W3141989311","https://openalex.org/W4239863959","https://openalex.org/W4252441533","https://openalex.org/W4291213652","https://openalex.org/W6603460400","https://openalex.org/W6603553207","https://openalex.org/W6610017368","https://openalex.org/W6631885290","https://openalex.org/W6632267817","https://openalex.org/W6633571703","https://openalex.org/W6634333142","https://openalex.org/W6675634716","https://openalex.org/W6679745481","https://openalex.org/W6680366005","https://openalex.org/W6717489403","https://openalex.org/W6723357538"],"related_works":["https://openalex.org/W2766503024","https://openalex.org/W2781247653","https://openalex.org/W4206637278","https://openalex.org/W4386005305","https://openalex.org/W4386214543","https://openalex.org/W3082051559","https://openalex.org/W1969988626","https://openalex.org/W1682621979","https://openalex.org/W2300921526","https://openalex.org/W2949064622"],"abstract_inverted_index":{"Highly":[0],"imbalanced":[1,206],"data":[2,63,123],"typically":[3],"make":[4],"accurate":[5],"predictions":[6],"difficult.":[7],"Unfortunately,":[8],"software":[9,82],"defect":[10,83,144,200],"datasets":[11,84,145],"tend":[12],"to":[13,33,118],"have":[14],"fewer":[15],"defective":[16,31],"modules":[17,32],"than":[18,175],"non-defective":[19],"modules.":[20],"Synthetic":[21],"oversampling":[22,79,178],"approaches":[23],"address":[24],"this":[25,69,95],"concern":[26],"by":[27,47],"creating":[28],"new":[29,107],"minority":[30],"balance":[34],"the":[35,44,89,119,122,136,147,160,165,176],"class":[36],"distribution":[37],"before":[38],"a":[39,74,106],"model":[40],"is":[41,86,192],"trained.":[42],"Notwithstanding":[43],"successes":[45],"achieved":[46],"these":[48],"approaches,":[49,179],"they":[50],"mostly":[51],"result":[52],"in":[53],"over-generalization":[54],"(high":[55],"rates":[56],"of":[57,92,143],"false":[58],"alarms)":[59],"and":[60,76,104,116,135,150,167,170,186],"generate":[61],"near-duplicated":[62],"instances":[64],"(less":[65],"diverse":[66],"data).":[67],"In":[68],"study,":[70],"we":[71],"introduce":[72],"MAHAKIL,":[73],"novel":[75],"efficient":[77,197],"synthetic":[78],"approach":[80,139],"for":[81,163,199],"that":[85,109,157],"based":[87,180],"on":[88,181,204],"chromosomal":[90],"theory":[91],"inheritance.":[93],"Exploiting":[94],"theory,":[96],"MAHAKIL":[97,128,158,191],"interprets":[98],"two":[99],"distinct":[100],"sub-classes":[101],"as":[102,195],"parents":[103],"generates":[105],"instance":[108],"inherits":[110],"different":[111],"traits":[112],"from":[113,146],"each":[114],"parent":[115],"contributes":[117],"diversity":[120],"within":[121],"distribution.":[124],"We":[125],"extensively":[126],"compare":[127],"with":[129],"SMOTE,":[130],"Borderline-SMOTE,":[131],"ADASYN,":[132],"Random":[133],"Oversampling":[134],"No":[137],"sampling":[138],"using":[140],"20":[141],"releases":[142],"PROMISE":[148],"repository":[149],"five":[151],"prediction":[152,161,201],"models.":[153],"Our":[154],"experiments":[155],"indicate":[156],"improves":[159],"performance":[162],"all":[164],"models":[166,202],"achieves":[168],"better":[169],"more":[171],"significant":[172],"pf":[173],"values":[174],"other":[177],"Brunner's":[182],"statistical":[183],"significance":[184],"test":[185],"Cliff's":[187],"effect":[188],"sizes.":[189],"Therefore,":[190],"strongly":[193],"recommended":[194],"an":[196],"alternative":[198],"built":[203],"highly":[205],"datasets.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":15},{"year":2025,"cited_by_count":26},{"year":2024,"cited_by_count":33},{"year":2023,"cited_by_count":40},{"year":2022,"cited_by_count":47},{"year":2021,"cited_by_count":45},{"year":2020,"cited_by_count":34},{"year":2019,"cited_by_count":34},{"year":2018,"cited_by_count":19},{"year":2017,"cited_by_count":4}],"updated_date":"2026-09-22T17:25:34.749102","created_date":"2025-10-10T00:00:00"}