{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T01:04:25Z","timestamp":1768266265471,"version":"3.49.0"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2022,6,23]],"date-time":"2022-06-23T00:00:00Z","timestamp":1655942400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,6,23]],"date-time":"2022-06-23T00:00:00Z","timestamp":1655942400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"DOI":"10.1007\/s10489-022-03772-1","type":"journal-article","created":{"date-parts":[[2022,6,23]],"date-time":"2022-06-23T23:02:53Z","timestamp":1656025373000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["An empirical study on the joint impact of feature selection and data resampling on imbalance classification"],"prefix":"10.1007","author":[{"given":"Chongsheng","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Paolo","family":"Soda","sequence":"additional","affiliation":[]},{"given":"Jingjun","family":"Bi","sequence":"additional","affiliation":[]},{"given":"Gaojuan","family":"Fan","sequence":"additional","affiliation":[]},{"given":"George","family":"Almpanidis","sequence":"additional","affiliation":[]},{"given":"Salvador","family":"Garc\u00eda","sequence":"additional","affiliation":[]},{"given":"Weiping","family":"Ding","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,6,23]]},"reference":[{"issue":"2\u20133","key":"3772_CR1","first-page":"255","volume":"17","author":"J Alcal\u00e1-Fdez","year":"2011","unstructured":"Alcal\u00e1-Fdez J, Fern\u00e1ndez A, Luengo J et al (2011) KEEL data-mining software tool: data set repository, integration of algorithms and experimental analysis framework. J Multiple-Valued Logic Soft Comput 17(2\u20133):255\u2013287","journal-title":"J Multiple-Valued Logic Soft Comput"},{"key":"3772_CR2","unstructured":"Asuncion A, Newman DJ (2007) UCI machine learning repository. http:\/\/www.ics.uci.edu\/mlearn\/MLRepository.html"},{"issue":"3","key":"3772_CR3","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1007\/s10044-003-0192-z","volume":"6","author":"R Barandela","year":"2003","unstructured":"Barandela R, Valdovinos RM, S\u00e1nchez JS (2003) New applications of ensembles of classifiers. Pattern Anal Applic 6(3):245\u2013256","journal-title":"Pattern Anal Applic"},{"key":"3772_CR4","doi-asserted-by":"crossref","unstructured":"Batista GE, Carvalho AC, Monard MC (2000) Applying one-sided selection to unbalanced datasets. Lect Notes Comput Sci, 315\u2013325","DOI":"10.1007\/10720076_29"},{"issue":"1","key":"3772_CR5","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1145\/1007730.1007735","volume":"6","author":"GEAPA Batista","year":"2004","unstructured":"Batista GEAPA, Prati RC, Monard MC (2004) A study of the behavior of several methods for balancing machine learning training data. SIGKDD Explor 6(1):20\u201329","journal-title":"SIGKDD Explor"},{"key":"3772_CR6","unstructured":"Cawley GC, Talbot NLC, Girolami MA (2006) Sparse multinomial logistic regression via bayesian L1 regularisation. In: Advances in neural information processing systems, 209\u2013216"},{"issue":"3","key":"3772_CR7","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"NV Chawla","year":"2002","unstructured":"Chawla NV, Bowyer KW, Hall LO, et al (2002) SMOTE: synthetic minority over-sampling technique. J Artif Intell Res 16(3):321\u2013357","journal-title":"J Artif Intell Res"},{"key":"3772_CR8","doi-asserted-by":"publisher","first-page":"1761","DOI":"10.1016\/j.patcog.2011.01.017","volume":"44","author":"M Galar","year":"2011","unstructured":"Galar M, Fern\u00e1ndez A, Barrenechea E et al (2011) An overview of ensemble methods for binary classifiers in multi-class problems: experimental study on one-vs-one and one-vs-all schemes. Pattern Recogn 44:1761\u20131776","journal-title":"Pattern Recogn"},{"key":"3772_CR9","doi-asserted-by":"crossref","unstructured":"Garc\u00eda V, Mollineda RA, S\u00e1nchez JS (2009) Index of balanced accuracy: a performance measure for skewed class distributions. In: Iberian conf on pattern recognition and image analysis, pp 441\u2013448","DOI":"10.1007\/978-3-642-02172-5_57"},{"key":"3772_CR10","doi-asserted-by":"crossref","unstructured":"G\u00fctlein M, Frank E, Hall MA, et al (2009) Large-scale attribute selection using wrappers. In: Proceedings of the IEEE symposium on computational intelligence and data mining, pp 332\u2013339","DOI":"10.1109\/CIDM.2009.4938668"},{"issue":"6","key":"3772_CR11","doi-asserted-by":"publisher","first-page":"1437","DOI":"10.1109\/TKDE.2003.1245283","volume":"15","author":"MA Hall","year":"2003","unstructured":"Hall MA, Holmes G (2003) Benchmarking attribute selection techniques for discrete class data mining. IEEE Trans Knowl Data Eng 15(6):1437\u20131447","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"3772_CR12","doi-asserted-by":"publisher","first-page":"515","DOI":"10.1109\/TIT.1968.1054155","volume":"14","author":"PE Hart","year":"1968","unstructured":"Hart PE (1968) The condensed nearest neighbor rule. IEEE Trans Inf Theory 14:515\u2013516","journal-title":"IEEE Trans Inf Theory"},{"key":"3772_CR13","unstructured":"He H, Bai Y, Garcia EA, et al (2008) ADASYN: adaptive synthetic sampling approach for imbalanced learning. In: Proceedings of the international joint conference on neural networks, pp 1322\u20131328"},{"key":"3772_CR14","doi-asserted-by":"crossref","unstructured":"Khoshgoftaar TM, Gao K, Seliya N (2010) Attribute selection and imbalanced data: problems in software defect prediction. In: 2010 22nd IEEE international conference on tools with artificial intelligence (ICTAI). IEEE, pp 137\u2013144","DOI":"10.1109\/ICTAI.2010.27"},{"issue":"5","key":"3772_CR15","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1007\/s10796-013-9430-0","volume":"16","author":"TM Khoshgoftaar","year":"2014","unstructured":"Khoshgoftaar TM, Gao K, Napolitano A et al (2014) A comparative study of iterative and non-iterative feature selection techniques for software defect prediction. Inf Syst Front 16(5):801\u2013822","journal-title":"Inf Syst Front"},{"issue":"4","key":"3772_CR16","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1007\/s13748-016-0094-0","volume":"5","author":"B Krawczyk","year":"2016","unstructured":"Krawczyk B (2016) Learning from imbalanced data: open challenges and future directions. Progress Artif Intell 5(4):221\u2013232","journal-title":"Progress Artif Intell"},{"issue":"6","key":"3772_CR17","doi-asserted-by":"publisher","first-page":"94:1","DOI":"10.1145\/3136625","volume":"50","author":"J Li","year":"2018","unstructured":"Li J, Cheng K, Wang S, et al (2018) Feature selection: a data perspective. ACM Comput Surv (CSUR) 50(6):94:1\u201394:45","journal-title":"ACM Comput Surv (CSUR)"},{"key":"3772_CR18","doi-asserted-by":"crossref","unstructured":"L\u00f3pez V, Fern\u00e1ndez A et al, Garc\u00eda S (2013) An insight into classification with imbalanced data: empirical results and current trends on using data intrinsic characteristics. Inform Sci 250:113\u2013141","DOI":"10.1016\/j.ins.2013.07.007"},{"key":"3772_CR19","doi-asserted-by":"publisher","first-page":"380","DOI":"10.1016\/j.asoc.2018.12.024","volume":"76","author":"S Maldonado","year":"2019","unstructured":"Maldonado S, L\u00f3pez J, Vairetti C (2019) An alternative SMOTE oversampling strategy for high-dimensional datasets. Appl Soft Comput 76:380\u2013389","journal-title":"Appl Soft Comput"},{"key":"3772_CR20","doi-asserted-by":"publisher","first-page":"108,511","DOI":"10.1016\/j.patcog.2021.108511","volume":"124","author":"S Maldonado","year":"2022","unstructured":"Maldonado S, Vairetti C, Fernandez A et al (2022) FW-SMOTE: a feature-weighted oversampling approach for imbalanced classification. Pattern Recogn 124:108,511","journal-title":"Pattern Recogn"},{"key":"3772_CR21","doi-asserted-by":"publisher","first-page":"1214","DOI":"10.1016\/j.ins.2019.10.048","volume":"512","author":"T Pan","year":"2020","unstructured":"Pan T, Zhao J, Wu W, et al (2020) Learning imbalanced datasets based on SMOTE and gaussian distribution. Inform Sci 512:1214\u20131233","journal-title":"Inform Sci"},{"key":"3772_CR22","doi-asserted-by":"crossref","unstructured":"Sheskin DJ (2003) Handbook of parametric and nonparametric statistical procedures. CRC Press","DOI":"10.1201\/9781420036268"},{"key":"3772_CR23","doi-asserted-by":"publisher","unstructured":"Shi H, Zhang Y, Chen Y et al (2022) Resampling algorithms based on sample concatenation for imbalance learning. Knowledge-Based Systems, https:\/\/doi.org\/10.1016\/j.knosys.2022.108592","DOI":"10.1016\/j.knosys.2022.108592"},{"key":"3772_CR24","doi-asserted-by":"crossref","unstructured":"Stefanowski J, Wilk S (2008) Selective pre-processing of imbalanced data for improving classification performance. In: the 10th int conf on data warehousing and knowledge discovery, pp 283\u2013292","DOI":"10.1007\/978-3-540-85836-2_27"},{"key":"3772_CR25","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1016\/j.ins.2017.10.017","volume":"425","author":"J Sun","year":"2018","unstructured":"Sun J, Lang J, Fujita H et al (2018) Imbalanced enterprise credit evaluation with DTE-SBD: decision tree ensemble based on smote and bagging with differentiated sampling rates. Inform Sci 425:76\u201391","journal-title":"Inform Sci"},{"key":"3772_CR26","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1016\/j.inffus.2019.07.006","volume":"54","author":"J Sun","year":"2020","unstructured":"Sun J, Li H, Fujita H et al (2020) Class-imbalanced dynamic financial distress prediction based on Adaboost-SVM ensemble combined with SMOTE and time weighting. Inform Fus 54:128\u2013144","journal-title":"Inform Fus"},{"key":"3772_CR27","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1016\/j.ins.2019.11.004","volume":"513","author":"F Thabtah","year":"2020","unstructured":"Thabtah F, Hammoud S, Kamalov F et al (2020) Data imbalance in classification: experimental evaluation. Inform Sci 513:429\u2013441","journal-title":"Inform Sci"},{"issue":"11","key":"3772_CR28","doi-asserted-by":"publisher","first-page":"1869","DOI":"10.1109\/TIFS.2014.2353996","volume":"9","author":"W Wang","year":"2014","unstructured":"Wang W, Wang X, Feng D et al (2014) Exploring permission-induced risk in android applications for malicious application detection. IEEE Trans Inform Forens Secur 9(11):1869\u20131882","journal-title":"IEEE Trans Inform Forens Secur"},{"issue":"10","key":"3772_CR29","doi-asserted-by":"publisher","first-page":"1388","DOI":"10.1109\/TKDE.2009.187","volume":"22","author":"M Wasikowski","year":"2010","unstructured":"Wasikowski M, Chen X (2010) Combating the small sample class imbalance problem using feature selection. IEEE Trans Knowl Data Eng 22(10):1388\u20131400","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"3772_CR30","volume-title":"Pattern recognition: human and mechanical","author":"S Watanabe","year":"1985","unstructured":"Watanabe S (1985) Pattern recognition: human and mechanical. Wiley, New York"},{"issue":"1","key":"3772_CR31","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1109\/4235.585893","volume":"1","author":"DH Wolpert","year":"1997","unstructured":"Wolpert DH, Macready WG (1997) No free lunch theorems for optimization. IEEE Trans Evol Comput 1(1):67\u201382","journal-title":"IEEE Trans Evol Comput"},{"key":"3772_CR32","doi-asserted-by":"crossref","unstructured":"Zhang C, Bi J, Soda P (2017) Feature selection and resampling in class imbalance learning: which comes first? An empirical study in the biological domain. In: 2017 IEEE International conference on bioinformatics and biomedicine (BIBM, 2017), pp 933\u2013938","DOI":"10.1109\/BIBM.2017.8217782"},{"key":"3772_CR33","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1016\/j.knosys.2019.03.001","volume":"174","author":"C Zhang","year":"2019","unstructured":"Zhang C, Bi J, Xu S, et al (2019) Multi-imbalance: an open-source software for multi-class imbalance learning. Knowl-Based Syst 174:137\u2013143","journal-title":"Knowl-Based Syst"}],"updated-by":[{"DOI":"10.1007\/s10489-022-03953-y","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2022,7,30]],"date-time":"2022-07-30T00:00:00Z","timestamp":1659139200000}}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-03772-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-022-03772-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-03772-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,30]],"date-time":"2022-07-30T08:14:55Z","timestamp":1659168895000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-022-03772-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6,23]]},"references-count":33,"alternative-id":["3772"],"URL":"https:\/\/doi.org\/10.1007\/s10489-022-03772-1","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6,23]]},"assertion":[{"value":"14 May 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 June 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 July 2022","order":3,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":4,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":5,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1007\/s10489-022-03953-y","URL":"https:\/\/doi.org\/10.1007\/s10489-022-03953-y","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}}]}}