{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T04:14:02Z","timestamp":1783397642387,"version":"3.54.6"},"reference-count":99,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2020,11,1]],"date-time":"2020-11-01T00:00:00Z","timestamp":1604188800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,11,1]],"date-time":"2020-11-01T00:00:00Z","timestamp":1604188800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,11,1]],"date-time":"2020-11-01T00:00:00Z","timestamp":1604188800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Grant-in-Aid for JSPS Fellows","award":["16J03360"],"award-info":[{"award-number":["16J03360"]}]},{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DE200100941"],"award-info":[{"award-number":["DE200100941"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IIEEE Trans. Software Eng."],"published-print":{"date-parts":[[2020,11,1]]},"DOI":"10.1109\/tse.2018.2876537","type":"journal-article","created":{"date-parts":[[2018,10,17]],"date-time":"2018-10-17T21:49:01Z","timestamp":1539812941000},"page":"1200-1219","source":"Crossref","is-referenced-by-count":248,"title":["The Impact of Class Rebalancing Techniques on the Performance and Interpretation of Defect Prediction Models"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5516-9984","authenticated-orcid":false,"given":"Chakkrit","family":"Tantithamthavorn","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmed E.","family":"Hassan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7418-9323","authenticated-orcid":false,"given":"Kenichi","family":"Matsumoto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-017-1713-3"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI.2010.27"},{"key":"ref33","article-title":"An exploration of challenges limiting pragmatic software defect prediction","author":"shihab","year":"2012"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2011.103"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2008.239"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-011-9173-9"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2010.12.016"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/NAFIPS.2007.383813"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"ref34","article-title":"Survey on software defect prediction","author":"nam","year":"2014"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1985793.1985859"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2013.11"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2025113.2025120"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TR.2013.2259203"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2009.2027131"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2015.139"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-016-9488-7"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2601248.2601294"},{"key":"ref26","article-title":"The promise repository of empirical software engineering data","author":"menzies","year":"2015"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1007\/s10664-011-9182-8","article-title":"On the dataset shift problem in software engineering prediction models","volume":"17","author":"turhan","year":"2011","journal-title":"Empirical Softw Eng"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-012-9205-0"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/2884781.2884852"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2015.91"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2008.35"},{"key":"ref57","article-title":"DMwR: Functions and data for &#x201D;Data Mining with R","author":"torgo","year":"2013"},{"key":"ref56","article-title":"Caret: Classification and regression training","author":"kuhn","year":"2015"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.2307\/2288636"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1038\/ng.295"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/MSR.2010.5463348"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2016.2553030"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/COMPSAC.2016.67"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1368088.1368114"},{"key":"ref3","first-page":"489","article-title":"Predicting faults from cached history","author":"kim","year":"2007","journal-title":"Proc Int Conf Softw Eng"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MSR.2010.5463279"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2009.5070510"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2025113.2025157"},{"key":"ref49","first-page":"1","article-title":"On the relative value of data resampling approaches for software defect prediction","author":"bennin","year":"2018","journal-title":"Empirical Softw Eng"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ISSRE.2010.25"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1002\/bltj.2229"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-4541-9"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.32614\/RJ-2014-008"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3180155.3180197"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2810146.2810150"},{"key":"ref42","first-page":"812","article-title":"The impact of mislabelling on the performance and interpretation of defect prediction models","author":"tantithamthavorn","year":"2015","journal-title":"Proceedings of the International Conference on Software Engineering ICSE'94"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.infsof.2014.12.006"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-012-0295-5"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2016.2584050"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-0258(20000430)19:8<1059::AID-SIM412>3.0.CO;2-0"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-0258(19960229)15:4<361::AID-SIM168>3.0.CO;2-4"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1002\/sim.4780100805"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2009.11.009"},{"key":"ref76","author":"harrell","year":"2002","journal-title":"Regression Modeling Strategies"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/45.3-4.562"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1186\/cc3765"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1097\/EDE.0b013e3181c30fb2"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2005.50"},{"key":"ref79","author":"steyerberg","year":"2008","journal-title":"Clinical Prediction Models A Practical Approach to Development Validation and Updating"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/2884781.2884857"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ISSREW.2016.30"},{"key":"ref61","article-title":"The impact of automated parameter optimization on defect prediction models","author":"tantithamthavorn","year":"2018","journal-title":"IEEE Trans Softw Eng"},{"key":"ref63","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1145\/3183519.3183547","article-title":"An experience report on defect modelling in practice: Pitfalls and challenges","author":"tantithamthavorn","year":"2018","journal-title":"Proc Int Conf Softw Eng Softw Eng Practice Track"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME.2018.00018"},{"key":"ref65","article-title":"The impact of correlated metrics on defect models","author":"jiarpakdee","year":"2018","journal-title":"Under review at IEEE Trans Softw Eng"},{"key":"ref66","article-title":"The varclus procedure","author":"sarle","year":"1990","journal-title":"SAS Institute Inc User s Guide"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1037\/0022-006X.67.3.332"},{"key":"ref68","article-title":"rms: Regression modeling strategies","author":"harrell","year":"2015"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/PROMISE.2007.10"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1175\/1520-0493(1950)078<0001:VOFEIT>2.0.CO;2"},{"key":"ref1","first-page":"353","article-title":"An example of software system debugging","author":"akiyama","year":"1971","journal-title":"Proc Int Fed Inf Process Societies Congress"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2013.6606589"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICSM.2010.5609530"},{"key":"ref93","first-page":"61:1","article-title":"Recalling the &#x201C;Imprecision","author":"rahman","year":"2012","journal-title":"Proc Int'l Symp the Foundations of Software Eng"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1145\/2491411.2491418"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/2786805.2786814"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2012.70"},{"key":"ref98","article-title":"glmnet: Lasso and elastic-net regularized generalized linear models","author":"hastie","year":"2017"},{"key":"ref99","article-title":"randomforest: Breiman and cutler's random forests for classification and regression","author":"liaw","year":"2015"},{"key":"ref96","article-title":"Class prediction for high-dimensional class-imbalanced data","volume":"11","author":"lusa","year":"2010","journal-title":"BMC Bioinf"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v033.i01"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/1852786.1852792"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2025113.2025155"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1145\/2597073.2597076","article-title":"The impact of code review coverage and code review participation on software quality","author":"mcintosh","year":"2014","journal-title":"Proc 8th Working Conf Mining Softw Repositories"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2009.42"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1882291.1882311"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2008.239"},{"key":"ref16","article-title":"C4.5 and imbalanced data sets: Investigating the effect of sampling method, probabilistic estimate, and decision tree structure","author":"chawla","year":"2003","journal-title":"Proc ICML03 Workshop Class Imbalances"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.112.1.155"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2009.2029559"},{"key":"ref81","author":"cohen","year":"1988","journal-title":"Statistical Power Analysis for the Behavioral Sciences"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ESEM.2007.28"},{"key":"ref84","article-title":"Distribution-free multiple comparisons","author":"nemenyi","year":"1963"},{"key":"ref19","first-page":"67","article-title":"Finding defective modules from highly unbalanced datasets","volume":"2","author":"riquelme","year":"2008","journal-title":"Actas de los Talleres de las Jornadas de Ingenier&#x00ED;a del Software y Bases de Datos"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2012.45"},{"key":"ref80","article-title":"ScottKnottESD: The Scott-Knott Effect Size Difference (ESD) Test","author":"tantithamthavorn","year":"2017"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/1595696.1595713"},{"key":"ref85","article-title":"C50: C5.0 decision trees and rule-based models","author":"kuhn","year":"2015"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-14-106"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2017.2731766"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/2889160.2889256"}],"container-title":["IEEE Transactions on Software Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/32\/9257116\/08494821.pdf?arnumber=8494821","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,4]],"date-time":"2022-09-04T05:11:44Z","timestamp":1662268304000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8494821\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,1]]},"references-count":99,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tse.2018.2876537","relation":{},"ISSN":["0098-5589","1939-3520","2326-3881"],"issn-type":[{"value":"0098-5589","type":"print"},{"value":"1939-3520","type":"electronic"},{"value":"2326-3881","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,11,1]]}}}