{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T15:57:31Z","timestamp":1787241451605,"version":"build-2736575974"},"reference-count":71,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2018,6,21]],"date-time":"2018-06-21T00:00:00Z","timestamp":1529539200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/100007567","name":"City University of Hong Kong","doi-asserted-by":"publisher","award":["7004683"],"award-info":[{"award-number":["7004683"]}],"id":[{"id":"10.13039\/100007567","id-type":"DOI","asserted-by":"publisher"}]},{"name":"JSPS KAKENHI","award":["17K00102"],"award-info":[{"award-number":["17K00102"]}]},{"name":"General Research Fund of the Research Grants Council of Hong Kong","award":["11208017"],"award-info":[{"award-number":["11208017"]}]},{"name":"City University of Hong Kong (HK)","award":["7004474"],"award-info":[{"award-number":["7004474"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Empir Software Eng"],"published-print":{"date-parts":[[2019,4]]},"DOI":"10.1007\/s10664-018-9633-6","type":"journal-article","created":{"date-parts":[[2018,6,20]],"date-time":"2018-06-20T23:59:35Z","timestamp":1529539175000},"page":"602-636","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":83,"title":["On the relative value of data resampling approaches for software defect prediction"],"prefix":"10.1007","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9140-9271","authenticated-orcid":false,"given":"Kwabena Ebo","family":"Bennin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jacky W.","family":"Keung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akito","family":"Monden","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,6,21]]},"reference":[{"key":"9633_CR1","unstructured":"Agrawal A, Menzies T (2017) Better data is better than better data miners (benefits of tuning smote for defect prediction). arXiv:\n                    1705.03697"},{"issue":"1","key":"9633_CR2","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1016\/j.jss.2009.06.055","volume":"83","author":"E Arisholm","year":"2010","unstructured":"Arisholm E, Briand LC, Johannessen EB (2010) A systematic and comprehensive investigation of methods to build and evaluate fault prediction models. J Syst Softw 83 (1):2\u201317","journal-title":"J Syst Softw"},{"issue":"2","key":"9633_CR3","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1109\/TKDE.2012.232","volume":"26","author":"S Barua","year":"2014","unstructured":"Barua S, Md MI, Yao Xi, Murase K (2014) Mwmote\u2013majority weighted minority oversampling technique for imbalanced data set learning. IEEE Trans Knowl Data Eng 26(2):405\u2013425","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"9633_CR4","doi-asserted-by":"crossref","unstructured":"Bennin K, Keung J, Monden A, Phannachitta P, Mensah S (2017) The significant effects of data sampling approaches on software defect prioritization and classification. In: 11th international symposium on empirical software engineering and measurement, ESEM 2017","DOI":"10.1109\/ESEM.2017.50"},{"key":"9633_CR5","doi-asserted-by":"crossref","unstructured":"Bennin KE, Keung J, Monden A, Kamei Y, Ubayashi N (2016) Investigating the effects of balanced training and testing datasets on effort-aware fault prediction models. In: 2016 IEEE 40th annual Computer software and applications conference (COMPSAC), vol 1. IEEE, pp 154\u2013163","DOI":"10.1109\/COMPSAC.2016.144"},{"key":"9633_CR6","doi-asserted-by":"crossref","unstructured":"Bennin KE, Toda K, Kamei Y, Keung J, Monden A, Ubayashi N (2016) Empirical evaluation of cross-release effort-aware defect prediction models. In: S2016 IEEE international conference on oftware quality, reliability and security (QRS). IEEE, pp 214\u2013221","DOI":"10.1109\/QRS.2016.33"},{"key":"9633_CR7","doi-asserted-by":"crossref","unstructured":"Bennin KE, Keung J, Phannachitta P, Monden A, Mensah S (2017) Mahakil: diversity based oversampling approach to alleviate the class imbalance issue in software defect prediction. IEEE Trans Softw Eng","DOI":"10.1145\/3180155.3182520"},{"issue":"7","key":"9633_CR8","doi-asserted-by":"publisher","first-page":"1145","DOI":"10.1016\/S0031-3203(96)00142-2","volume":"30","author":"AP Bradley","year":"1997","unstructured":"Bradley AP (1997) The use of the area under the roc curve in the evaluation of machine learning algorithms. Pattern Recogn 30(7):1145\u20131159","journal-title":"Pattern Recogn"},{"issue":"1","key":"9633_CR9","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/S0378-3758(02)00269-0","volume":"108","author":"E Brunner","year":"2002","unstructured":"Brunner E, Munzel U, Puri ML (2002) The multivariate nonparametric behrens\u2013fisher problem. J Stat Plan Inference 108(1):37\u201353","journal-title":"J Stat Plan Inference"},{"key":"9633_CR10","doi-asserted-by":"crossref","unstructured":"Bunkhumpornpat C, Sinapiromsaran K, Lursinsap C (2009) Safe-level-smote: Safe-level-synthetic minority over-sampling technique for handling the class imbalanced problem. In: Pacific-asia conference on knowledge discovery and data mining. Springer, pp 475\u2013482","DOI":"10.1007\/978-3-642-01307-2_43"},{"key":"9633_CR11","unstructured":"Chawla NV (2010) Data mining for imbalanced datasets: an overview. In: Data mining and knowledge discovery handbook. Springer, pp 875\u2013886"},{"key":"9633_CR12","doi-asserted-by":"crossref","unstructured":"Chawla NV, Bowyer KW, Hall LO., Kegelmeyer WP (2002) Smote: synthetic minority over-sampling technique. J Artif Intell Res:321\u2013357","DOI":"10.1613\/jair.953"},{"key":"9633_CR13","doi-asserted-by":"crossref","unstructured":"D\u2019Ambros M, Lanza M, Robbes R (2010) An extensive comparison of bug prediction approaches. In: Proceedings of 2010 7th IEEE Working Conference on Mining Software Repositories (MSR). IEEE, pp 31\u201341","DOI":"10.1109\/MSR.2010.5463279"},{"issue":"4-5","key":"9633_CR14","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1007\/s10664-011-9173-9","volume":"17","author":"M D\u2019Ambros","year":"2012","unstructured":"D\u2019Ambros M, Lanza M, Robbes R (2012) Evaluating defect prediction approaches: a benchmark and an extensive comparison. Empir Softw Eng 17(4-5):531\u2013577","journal-title":"Empir Softw Eng"},{"key":"9633_CR15","doi-asserted-by":"crossref","unstructured":"Domingos P (1999) Metacost: a general method for making classifiers cost-sensitive. In: Proceedings of the fifth ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, pp 155\u2013164","DOI":"10.1145\/312129.312220"},{"issue":"5","key":"9633_CR16","doi-asserted-by":"publisher","first-page":"1097","DOI":"10.1109\/TSMCA.2009.2020804","volume":"39","author":"DJ Drown","year":"2009","unstructured":"Drown DJ, Khoshgoftaar TM, Seliya N (2009) Evolutionary sampling and software quality modeling of high-assurance systems. IEEE Trans Syst, Man, Cybern-Part A: Syst Humans 39(5):1097\u2013 1107","journal-title":"IEEE Trans Syst, Man, Cybern-Part A: Syst Humans"},{"issue":"1","key":"9633_CR17","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1111\/j.0824-7935.2004.t01-1-00228.x","volume":"20","author":"A Estabrooks","year":"2004","unstructured":"Estabrooks A, Jo T, Japkowicz N (2004) A multiple resampling method for learning from imbalanced data sets. Comput Intell 20(1):18\u201336","journal-title":"Comput Intell"},{"issue":"1","key":"9633_CR18","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1016\/j.knosys.2011.06.013","volume":"25","author":"V Garc\u00eda","year":"2012","unstructured":"Garc\u00eda V, S\u00e1nchez JS, Mollineda RA (2012) On the effectiveness of preprocessing methods when dealing with different levels of class imbalance. Knowl-Based Syst 25(1):13\u201321","journal-title":"Knowl-Based Syst"},{"key":"9633_CR19","doi-asserted-by":"crossref","unstructured":"Gray D, Bowes D, Davey N, Yi S, Christianson B (2011) The misuse of the nasa metrics data program data sets for automated software defect prediction. In: Proceedings of 15th Annual Conference on Evaluation & Assessment in Software Engineering (EASE 2011). IET, pp 96\u2013103","DOI":"10.1049\/ic.2011.0012"},{"issue":"6","key":"9633_CR20","doi-asserted-by":"publisher","first-page":"1276","DOI":"10.1109\/TSE.2011.103","volume":"38","author":"T Hall","year":"2012","unstructured":"Hall T, Beecham S, Bowes D, Gray D, Counsell S (2012) A systematic literature review on fault prediction performance in software engineering. IEEE Trans Softw Eng 38(6):1276\u20131304","journal-title":"IEEE Trans Softw Eng"},{"key":"9633_CR21","doi-asserted-by":"crossref","unstructured":"Han H, Wang W-Y, Mao B-H (2005) Borderline-smote: a new over-sampling method in imbalanced data sets learning. In: Advances in intelligent computing. Springer, pp 878\u2013887","DOI":"10.1007\/11538059_91"},{"key":"9633_CR22","doi-asserted-by":"crossref","unstructured":"Hata H, Mizuno O, Kikuno T (2012) Bug prediction based on fine-grained module histories. In: Proceedings of the 34th International Conference on Software Engineering. IEEE Press, pp 200\u2013210","DOI":"10.1109\/ICSE.2012.6227193"},{"issue":"9","key":"9633_CR23","doi-asserted-by":"publisher","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","volume":"21","author":"H He","year":"2009","unstructured":"He H, Garcia EA (2009) Learning from imbalanced data. IEEE Trans knowl data Eng 21(9):1263\u20131284","journal-title":"IEEE Trans knowl data Eng"},{"key":"9633_CR24","unstructured":"He H, Bai Y, Garcia E, Shutao L et al (2008) Adasyn: adaptive synthetic sampling approach for imbalanced learning. In: IEEE international joint conference on Neural networks, 2008. IJCNN 2008. (IEEE world congress on computational intelligence). IEEE, pp 1322\u20131328"},{"issue":"2","key":"9633_CR25","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1007\/s10515-011-0090-3","volume":"19","author":"Z He","year":"2012","unstructured":"He Z, Shu F, Ye Y, Li M, Wang Q (2012) An investigation on the feasibility of cross-project defect prediction. Autom Softw Eng 19(2):167\u2013199","journal-title":"Autom Softw Eng"},{"issue":"5","key":"9633_CR26","doi-asserted-by":"publisher","first-page":"429","DOI":"10.3233\/IDA-2002-6504","volume":"6","author":"N Japkowicz","year":"2002","unstructured":"Japkowicz N, Stephen S (2002) The class imbalance problem: a systematic study. Intell Data Anal 6(5):429\u2013449","journal-title":"Intell Data Anal"},{"issue":"5","key":"9633_CR27","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1007\/s10664-008-9079-3","volume":"13","author":"Y Jiang","year":"2008","unstructured":"Jiang Y, Cukic B, Ma Y (2008) Techniques for evaluating fault prediction models. Empir Softw Eng 13(5):561\u2013595","journal-title":"Empir Softw Eng"},{"key":"9633_CR28","doi-asserted-by":"crossref","unstructured":"Joshi MV, Kumar V, Agarwal RC (2001) Evaluating boosting algorithms to classify rare classes: comparison and improvements. In: Proceedings IEEE International Conference on Data Mining, 2001. ICDM 2001. IEEE, pp 257\u2013264","DOI":"10.1109\/ICDM.2001.989527"},{"key":"9633_CR29","doi-asserted-by":"crossref","unstructured":"Jureczko M, Madeyski L (2010) Towards identifying software project clusters with regard to defect prediction. In: Proceedings of the 6th International Conference on Predictive Models in Software Engineering. ACM, p 9","DOI":"10.1145\/1868328.1868342"},{"key":"9633_CR30","unstructured":"Jureczko M, Spinellis D (2010) Using object-oriented design metrics to predict software defects: models and methods of system dependability. Oficyna Wydawnicza Politechniki Wroclawskiej:69\u201381"},{"key":"9633_CR31","doi-asserted-by":"crossref","unstructured":"Kamei Y, Monden A, Matsumoto S, Kakimoto T, Matsumoto Kx-I (2007) The effects of over and under sampling on fault-prone module detection. In: First international symposium on empirical software engineering and measurement, 2007. ESEM 2007. IEEE, pp 196\u2013204","DOI":"10.1109\/ESEM.2007.28"},{"key":"9633_CR32","doi-asserted-by":"crossref","unstructured":"Kamei Y, Matsumoto S, Monden A, Matsumoto K-I, Adams B, Hassan AE (2010) Revisiting common bug prediction findings using effort-aware models. In: Proceedings of 2010 IEEE International Conference onSoftware Maintenance (ICSM). IEEE, pp 1\u201310","DOI":"10.1109\/ICSM.2010.5609530"},{"key":"9633_CR33","unstructured":"Kitchenham B, Madeyski L, Budgen D, Keung J, Brereton P, Charters S, Gibbs S, Pohthong A (2016) Robust statistical methods for empirical software engineering. Empir Softw Eng:1\u201352"},{"issue":"2","key":"9633_CR34","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1109\/TSE.2011.27","volume":"38","author":"E Kocaguneli","year":"2012","unstructured":"Kocaguneli E, Menzies T, Bener A, Keung JW (2012) Exploiting the essential assumptions of analogy-based effort estimation. IEEE Trans Softw Eng 38 (2):425\u2013438","journal-title":"IEEE Trans Softw Eng"},{"issue":"8","key":"9633_CR35","doi-asserted-by":"publisher","first-page":"1040","DOI":"10.1109\/TSE.2012.88","volume":"39","author":"E Kocaguneli","year":"2013","unstructured":"Kocaguneli E, Menzies T, Keung J, Cok D, Madachy R (2013) Active learning and effort estimation: finding the essential content of software effort estimation data. IEEE Trans Softw Eng 39(8):1040\u20131053","journal-title":"IEEE Trans Softw Eng"},{"issue":"11","key":"9633_CR36","doi-asserted-by":"publisher","first-page":"990","DOI":"10.1016\/j.biopsych.2005.09.014","volume":"59","author":"HC Kraemer","year":"2006","unstructured":"Kraemer HC, Kupfer DJ (2006) Size of treatment effects and their importance to clinical research and practice. Biological Psych 59(11):990\u2013996","journal-title":"Biological Psych"},{"key":"9633_CR37","unstructured":"Kubat M, Matwin S et al (1997) Addressing the curse of imbalanced training sets: one-sided selection. In: ICML, vol 97, Nashville, USA, pp 179\u2013186"},{"key":"9633_CR38","unstructured":"Kuhn M, Wing J, Weston S, Williams A, Keefer C, Engelhardt A, Cooper T, Mayer Z (2014) Caret: classification and regression training. r package version 6.0\u201324"},{"key":"9633_CR39","doi-asserted-by":"publisher","first-page":"388","DOI":"10.1016\/j.infsof.2014.07.005","volume":"58","author":"IH Laradji","year":"2015","unstructured":"Laradji IH, Alshayeb M, Ghouti L (2015) Software defect prediction using ensemble learning on selected features. Inf Softw Technol 58:388\u2013402","journal-title":"Inf Softw Technol"},{"issue":"2","key":"9633_CR40","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1016\/S0167-9473(99)00095-X","volume":"34","author":"SS Lee","year":"2000","unstructured":"Lee SS (2000) Noisy replication in skewed binary classification. Comput Stat Data Anal 34(2):165\u2013191","journal-title":"Comput Stat Data Anal"},{"issue":"4","key":"9633_CR41","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1109\/TSE.2008.35","volume":"34","author":"S Lessmann","year":"2008","unstructured":"Lessmann S, Baesens B, Mues C, Pietsch S (2008) Benchmarking classification models for software defect prediction: a proposed framework and novel findings. IEEE Trans Softw Eng 34(4):485\u2013496","journal-title":"IEEE Trans Softw Eng"},{"issue":"2","key":"9633_CR42","doi-asserted-by":"publisher","first-page":"676","DOI":"10.1109\/TR.2014.2316951","volume":"63","author":"M Liu","year":"2014","unstructured":"Liu M, Miao L, Zhang D (2014) Two-stage cost-sensitive learning for software defect prediction. IEEE Trans Reliab 63(2):676\u2013686","journal-title":"IEEE Trans Reliab"},{"issue":"3","key":"9633_CR43","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1007\/s11219-014-9241-7","volume":"23","author":"L Madeyski","year":"2015","unstructured":"Madeyski L, Jureczko M (2015) Which process metrics can significantly improve defect prediction models? an empirical study. Softw Qual J 23(3):393\u2013422","journal-title":"Softw Qual J"},{"issue":"9","key":"9633_CR44","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1109\/TSE.2007.70721","volume":"33","author":"T Menzies","year":"2007","unstructured":"Menzies T, Dekhtyar A, Distefano J, Greenwald J (2007) Problems with precision: a response to comments on data mining static code attributes to learn defect predictors. IEEE Trans Softw Eng 33(9):637","journal-title":"IEEE Trans Softw Eng"},{"issue":"1","key":"9633_CR45","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1109\/TSE.2007.256941","volume":"33","author":"T Menzies","year":"2007","unstructured":"Menzies T, Greenwald J, Frank A (2007) Data mining static code attributes to learn defect predictors. IEEE Trans Softw Eng 33(1):2\u201313","journal-title":"IEEE Trans Softw Eng"},{"key":"9633_CR46","doi-asserted-by":"crossref","unstructured":"Menzies T, Turhan B, Bener A, Gay G, Cukic B, Jiang Y (2008) Implications of ceiling effects in defect predictors. In: Proceedings of the 4th international workshop on Predictor models in software engineering. ACM, pp 47\u201354","DOI":"10.1145\/1370788.1370801"},{"issue":"4","key":"9633_CR47","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1007\/s10515-010-0069-5","volume":"17","author":"T Menzies","year":"2010","unstructured":"Menzies T, Milton Z, Turhan B, Cukic B, Jiang Y, Bener AY (2010) Defect prediction from static code features: current results, limitations, new approaches. Autom Softw Eng 17(4):375\u2013407","journal-title":"Autom Softw Eng"},{"key":"9633_CR48","doi-asserted-by":"crossref","unstructured":"Moser R, Pedrycz W, Succi G (2008) A comparative analysis of the efficiency of change metrics and static code attributes for defect prediction. In: ACM\/IEEE 30th international conference on Software engineering, 2008. ICSE\u201908. IEEE, pp 181\u2013190","DOI":"10.1145\/1368088.1368114"},{"key":"9633_CR49","unstructured":"Nickerson A, Japkowicz N, Milios E (2001) Using unsupervised learning to guide resampling in imbalanced data sets. In: Proceedings of the Eighth International Workshop on AI and Statitsics, pp 261\u2013265"},{"key":"9633_CR50","doi-asserted-by":"crossref","unstructured":"Pazzani M, Merz C, Murphy P, Ali K, Hume T, Brunk C (1994) Reducing misclassification costs. In: Proceedings of the Eleventh International Conference on Machine Learning, pp 217\u2013225","DOI":"10.1016\/B978-1-55860-335-6.50034-9"},{"key":"9633_CR51","doi-asserted-by":"crossref","unstructured":"Pelayo L, Dick S (2007) Applying novel resampling strategies to software defect prediction. In: Annual meeting of the north american Fuzzy information processing society, 2007. NAFIPS\u201907. IEEE, pp 69\u201372","DOI":"10.1109\/NAFIPS.2007.383813"},{"key":"9633_CR52","unstructured":"Phung SL, Bouzerdoum A, Nguyen GH (2009) Learning pattern classification tasks with imbalanced data sets"},{"issue":"8","key":"9633_CR53","doi-asserted-by":"publisher","first-page":"1397","DOI":"10.1016\/j.infsof.2013.02.009","volume":"55","author":"D Radjenovic","year":"2013","unstructured":"Radjenovic D, Hericko M, Torkar R, \u017eivkovic A (2013) Software fault prediction metrics: a systematic literature review. Inf Softw Technol 55(8):1397\u20131418","journal-title":"Inf Softw Technol"},{"issue":"1","key":"9633_CR54","first-page":"67","volume":"2","author":"JC Riquelme","year":"2008","unstructured":"Riquelme JC, Ruiz R, Rodr\u00edguez D, Moreno J (2008) Finding defective modules from highly unbalanced datasets. Actas de los Talleres de las Jornadas de Ingenier\u00eda del Software y Bases de Datos 2(1):67\u201374","journal-title":"Actas de los Talleres de las Jornadas de Ingenier\u00eda del Software y Bases de Datos"},{"key":"9633_CR55","unstructured":"Shirabad JS, Menzies TJ (2005) The PROMISE repository of software engineering databases. School of Information Technology and Engineering, University of Ottawa, Canada"},{"issue":"1","key":"9633_CR56","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1109\/TSMCA.2009.2029559","volume":"40","author":"C Seiffert","year":"2010","unstructured":"Seiffert C, Khoshgoftaar TM, Hulse JV, Rusboost AN (2010) A hybrid approach to alleviating class imbalance. IEEE Trans Syst Man, and Cybernetics-Part A: Systems and Humans 40(1):185\u2013197","journal-title":"IEEE Trans Syst Man, and Cybernetics-Part A: Systems and Humans"},{"key":"9633_CR57","doi-asserted-by":"crossref","unstructured":"Shanab A, Khoshgoftaar TM, Wald R, Napolitano A (2012) Impact of noise and data sampling on stability of feature ranking techniques for biological datasets. In: 2012 IEEE 13th international conference on Information reuse and integration (IRI). IEEE, pp 415\u2013422","DOI":"10.1109\/IRI.2012.6303039"},{"key":"9633_CR58","doi-asserted-by":"crossref","unstructured":"Shatnawi R (2017) The application of roc analysis in threshold identification, data imbalance and metrics selection for software fault prediction. Innov Syst Softw Eng:1\u201317","DOI":"10.1007\/s11334-017-0295-0"},{"issue":"11","key":"9633_CR59","doi-asserted-by":"publisher","first-page":"1014","DOI":"10.1109\/32.965341","volume":"27","author":"M Shepperd","year":"2001","unstructured":"Shepperd M, Kadoda G (2001) Comparing software prediction techniques using simulation. IEEE Trans Softw Eng 27(11):1014\u20131022","journal-title":"IEEE Trans Softw Eng"},{"issue":"12","key":"9633_CR60","doi-asserted-by":"publisher","first-page":"3358","DOI":"10.1016\/j.patcog.2007.04.009","volume":"40","author":"Y Sun","year":"2007","unstructured":"Sun Y, Kamel MS, Wong AKC, Wang Y (2007) Cost-sensitive boosting for classification of imbalanced data. Pattern Recogn 40(12):3358\u20133378","journal-title":"Pattern Recogn"},{"issue":"6","key":"9633_CR61","doi-asserted-by":"publisher","first-page":"1806","DOI":"10.1109\/TSMCC.2012.2226152","volume":"42","author":"Z Sun","year":"2012","unstructured":"Sun Z, Song Q, Zhu X (2012) Using coding-based ensemble learning to improve software defect prediction. IEEE Trans Syst, Man, Cybern, Part C (Appl Rev) 42(6):1806\u20131817","journal-title":"IEEE Trans Syst, Man, Cybern, Part C (Appl Rev)"},{"issue":"1","key":"9633_CR62","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1109\/TSMCB.2008.2002909","volume":"39","author":"Y Tang","year":"2009","unstructured":"Tang Y, Zhang Y-Q, Chawla NV, Krasser S (2009) Svms modeling for highly imbalanced classification. IEEE Trans Syst, Man, Cybern, Part B (Cybernetics) 39(1):281\u2013288","journal-title":"IEEE Trans Syst, Man, Cybern, Part B (Cybernetics)"},{"key":"9633_CR63","unstructured":"R Core Team (2012) R: a language and environment for statistical computing. Vienna, Austria: R Foundation for Statistical Computing"},{"issue":"2","key":"9633_CR64","doi-asserted-by":"publisher","first-page":"434","DOI":"10.1109\/TR.2013.2259203","volume":"62","author":"S Wang","year":"2013","unstructured":"Wang S, Yao X (2013) Using class imbalance learning for software defect prediction. IEEE Trans Reliab 62(2):434\u2013443","journal-title":"IEEE Trans Reliab"},{"key":"9633_CR65","unstructured":"Weiss GM, Provost F (2001) The effect of class distribution on classifier learning: an empirical study. Rutgers Univ"},{"key":"9633_CR66","unstructured":"Weiss GM, Provost F (2003) Learning when training data are costly: the effect of class distribution on tree induction. J Artif Intell Res:315\u2013354"},{"key":"9633_CR67","unstructured":"Wilcox RR, Sch\u00f6nbrodt FD (2014) The wrs package for robust statistics in r (version 0.26). Available: Retrieved from \n                    https:\/\/github.com\/nicebread\/WRS"},{"key":"9633_CR68","doi-asserted-by":"crossref","unstructured":"Wong GY, Leung FHF, Ling S-H (2013) A novel evolutionary preprocessing method based on over-sampling and under-sampling for imbalanced datasets. In: 2013-39th annual conference of the IEEE Industrial electronics society, IECON. IEEE, pp 2354\u20132359","DOI":"10.1109\/IECON.2013.6699499"},{"key":"9633_CR69","unstructured":"Yan M, Fang Y, Lo D, Xia X, Zhang X (2017) File-level defect prediction: unsupervised vs. supervised models. In: 2017 ACM\/IEEE international symposium on Empirical software engineering and measurement (ESEM). IEEE, pp 344\u2013353"},{"issue":"3","key":"9633_CR70","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1007\/s00521-007-0089-7","volume":"16","author":"K Yoon","year":"2007","unstructured":"Yoon K, Kwek S (2007) A data reduction approach for resolving the imbalanced data issue in functional genomics. Neural Comput Appl 16(3):295\u2013306","journal-title":"Neural Comput Appl"},{"issue":"6","key":"9633_CR71","doi-asserted-by":"publisher","first-page":"4537","DOI":"10.1016\/j.eswa.2009.12.056","volume":"37","author":"J Zheng","year":"2010","unstructured":"Zheng J (2010) Cost-sensitive boosting neural networks for software defect prediction. Expert Syst Appl 37(6):4537\u20134543","journal-title":"Expert Syst Appl"}],"container-title":["Empirical Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-018-9633-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10664-018-9633-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-018-9633-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,20]],"date-time":"2019-09-20T05:38:46Z","timestamp":1568957926000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10664-018-9633-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6,21]]},"references-count":71,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2019,4]]}},"alternative-id":["9633"],"URL":"https:\/\/doi.org\/10.1007\/s10664-018-9633-6","relation":{},"ISSN":["1382-3256","1573-7616"],"issn-type":[{"value":"1382-3256","type":"print"},{"value":"1573-7616","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,6,21]]},"assertion":[{"value":"21 June 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}