{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T19:08:47Z","timestamp":1782846527287,"version":"3.54.5"},"reference-count":59,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2019,7,31]],"date-time":"2019-07-31T00:00:00Z","timestamp":1564531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2019,7,31]],"date-time":"2019-07-31T00:00:00Z","timestamp":1564531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Big Data"],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1186\/s40537-019-0231-2","type":"journal-article","created":{"date-parts":[[2019,7,31]],"date-time":"2019-07-31T11:02:34Z","timestamp":1564570954000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":38,"title":["Examining characteristics of predictive models with imbalanced big data"],"prefix":"10.1186","volume":"6","author":[{"given":"Tawfiq","family":"Hasanin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taghi M.","family":"Khoshgoftaar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7079-7540","authenticated-orcid":false,"given":"Joffrey L.","family":"Leevy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naeem","family":"Seliya","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,7,31]]},"reference":[{"key":"231_CR1","doi-asserted-by":"crossref","unstructured":"Katal A, Wazid M, Goudar R. Big data: issues, challenges, tools and good practices. In: 2013 sixth international conference on contemporary computing (IC3). 2013. p. 404\u20139.","DOI":"10.1109\/IC3.2013.6612229"},{"issue":"1","key":"231_CR2","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1186\/s40537-018-0151-6","volume":"5","author":"JL Leevy","year":"2018","unstructured":"Leevy JL, Khoshgoftaar TM, Bauder RA, Seliya N. A survey on addressing high-class imbalance in big data. J Big Data. 2018;5(1):42.","journal-title":"J Big Data"},{"key":"231_CR3","first-page":"194","volume":"2","author":"RC Soltysik","year":"2013","unstructured":"Soltysik RC, Yarnold PR. Megaoda large sample and big data time trials: separating the chaff. Optimal Data Anal. 2013;2:194\u20137.","journal-title":"Optimal Data Anal"},{"issue":"2","key":"231_CR4","doi-asserted-by":"publisher","first-page":"423","DOI":"10.2308\/acch-51068","volume":"29","author":"M Cao","year":"2015","unstructured":"Cao M, Chychyla R, Stewart T. Big data analytics in financial statement audits. Account Horizons. 2015;29(2):423\u20139.","journal-title":"Account Horizons"},{"key":"231_CR5","doi-asserted-by":"crossref","unstructured":"Bauder R, Khoshgoftaar T. Medicare fraud detection using random forest with class imbalanced big data. In: 2018 IEEE international conference on information reuse and integration (IRI). 2018. p. 80\u20137.","DOI":"10.1109\/IRI.2018.00019"},{"key":"231_CR6","doi-asserted-by":"crossref","unstructured":"Bauder RA, Khoshgoftaar TM, Hasanin T. An empirical study on class rarity in big data. In: 2018 17th IEEE international conference on machine learning and applications (ICMLA). 2018. p. 785\u201390.","DOI":"10.1109\/ICMLA.2018.00125"},{"key":"231_CR7","volume-title":"Data mining: practical machine learning tools and techniques","author":"IH Witten","year":"2016","unstructured":"Witten IH, Frank E, Hall MA, Pal CJ. Data mining: practical machine learning tools and techniques. Burlington: Morgan Kaufmann; 2016."},{"issue":"2","key":"231_CR8","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1086\/587826","volume":"83","author":"JD Olden","year":"2008","unstructured":"Olden JD, Lawler JJ, Poff NL. Machine learning methods without tears: a primer for ecologists. Quart Rev Biol. 2008;83(2):171\u201393.","journal-title":"Quart Rev Biol"},{"issue":"1","key":"231_CR9","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1023\/A:1008699112516","volume":"15","author":"J Galindo","year":"2000","unstructured":"Galindo J, Tamayo P. Credit risk assessment using statistical and machine learning: basic methodology and risk modeling applications. Comput Econ. 2000;15(1):107\u201343.","journal-title":"Comput Econ"},{"key":"231_CR10","doi-asserted-by":"crossref","unstructured":"Seliya N, Khoshgoftaar TM, Van\u00a0Hulse J. A study on the relationships of classifier performance metrics. In: 2009 21st IEEE international conference on tools with artificial intelligence. 2009. p. 59\u201366.","DOI":"10.1109\/ICTAI.2009.25"},{"issue":"1","key":"231_CR11","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1145\/1007730.1007735","volume":"6","author":"GE Batista","year":"2004","unstructured":"Batista GE, Prati RC, Monard MC. A study of the behavior of several methods for balancing machine learning training data. ACM SIGKDD Explorat Newslett. 2004;6(1):20\u20139.","journal-title":"ACM SIGKDD Explorat Newslett"},{"key":"231_CR12","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, Kegelmeyer WP. Smote: synthetic minority over-sampling technique. J Artif Intell Res. 2002;16:321\u201357.","journal-title":"J Artif Intell Res"},{"key":"231_CR13","unstructured":"Dittman DJ, Khoshgoftaar TM, Wald R, Napolitano A. Comparison of data sampling approaches for imbalanced bioinformatics data. In: The twenty-seventh international FLAIRS conference; 2014."},{"key":"231_CR14","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1016\/j.asoc.2014.11.023","volume":"27","author":"R Malhotra","year":"2015","unstructured":"Malhotra R. A systematic review of machine learning techniques for software fault prediction. Appl Soft Comput. 2015;27:504\u201318.","journal-title":"Appl Soft Comput"},{"issue":"01","key":"231_CR15","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1142\/S0218194015400057","volume":"25","author":"H Wang","year":"2015","unstructured":"Wang H, Khoshgoftaar TM, Napolitano A. An empirical investigation on wrapper-based feature selection for predicting software quality. Int J Softw Eng Knowl Eng. 2015;25(01):93\u2013114.","journal-title":"Int J Softw Eng Knowl Eng"},{"key":"231_CR16","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.neucom.2012.04.039","volume":"105","author":"L Yin","year":"2013","unstructured":"Yin L, Ge Y, Xiao K, Wang X, Quan X. Feature selection for high-dimensional imbalanced data. Neurocomputing. 2013;105:3\u201311.","journal-title":"Neurocomputing"},{"key":"231_CR17","first-page":"258","volume":"99","author":"D Mladenic","year":"1999","unstructured":"Mladenic D, Grobelnik M. Feature selection for unbalanced class distribution and naive bayes. ICML. 1999;99:258\u201367.","journal-title":"ICML"},{"issue":"1","key":"231_CR18","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1145\/1007730.1007741","volume":"6","author":"Z Zheng","year":"2004","unstructured":"Zheng Z, Wu X, Srihari R. Feature selection for text categorization on imbalanced data. ACM Sigkdd Expl Newslett. 2004;6(1):80\u20139.","journal-title":"ACM Sigkdd Expl Newslett"},{"key":"231_CR19","unstructured":"Evolutionary computation for big data and big learning workshop, data mining competition. 2014: self-deployment track. \n                    http:\/\/cruncher.ico2s.org\/bdcomp\/\n                    \n                  ."},{"key":"231_CR20","unstructured":"9th Community Wide Experiment on the Critical Assessment of Techniques for Protein Structure Prediction. \n                    http:\/\/predictioncenter.org\/casp9\/\n                    \n                  ."},{"key":"231_CR21","unstructured":"Calvert C, Khoshgoftaar TM, Kemp C, Najafabadi MM. Detecting slow http post dos attacks using netflow features. In: The thirty-second international FLAIRS conference. 2019."},{"key":"231_CR22","unstructured":"Calvert C, Khoshgoftaar TM, Kemp C, Najafabadi MM. Detection of slowloris attacks using netflow traffic. In: 24th ISSAT international conference on reliability and quality in design. 2018. p. 191\u20136."},{"issue":"10","key":"231_CR23","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-W. Combating the small sample class imbalance problem using feature selection. IEEE Trans Knowl Data Eng. 2010;22(10):1388\u2013400.","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"6","key":"231_CR24","doi-asserted-by":"publisher","first-page":"1808","DOI":"10.1016\/j.compeleceng.2012.09.001","volume":"38","author":"A Idris","year":"2012","unstructured":"Idris A, Rizwan M, Khan A. Churn prediction in telecom using random forest and pso based data balancing in combination with various feature selection strategies. Comput Elect Eng. 2012;38(6):1808\u201319.","journal-title":"Comput Elect Eng"},{"key":"231_CR25","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1016\/j.neucom.2012.08.018","volume":"101","author":"H Yu","year":"2013","unstructured":"Yu H, Ni J, Zhao J. Acosampling: an ant colony optimization-based undersampling method for classifying imbalanced dna microarray data. Neurocomputing. 2013;101:309\u201318.","journal-title":"Neurocomputing"},{"key":"231_CR26","doi-asserted-by":"publisher","unstructured":"Roy S, DeLoach J, Li Y, Herndon N, Caragea D, Ou X, Ranganath VP, Li H, Guevara N. Experimental study with real-world data for android app security analysis using machine learning. In: Proceedings of the 31st annual computer security applications conference. ACSAC 2015. New York: ACM; 2015. p. 81\u201390. \n                    https:\/\/doi.org\/10.1145\/2818000.2818038\n                    \n                  .","DOI":"10.1145\/2818000.2818038"},{"key":"231_CR27","doi-asserted-by":"crossref","unstructured":"Arp D, Spreitzenbarth M, Gascon H, Rieck K, Siemens C. Drebin: effective and explainable detection of android malware in your pocket; 2014.","DOI":"10.14722\/ndss.2014.23247"},{"key":"231_CR28","doi-asserted-by":"crossref","unstructured":"Zhang M, Duan Y, Yin H, Zhao Z. Semantics-aware android malware classification using weighted contextual api dependency graphs. In: Proceedings of the 2014 ACM SIGSAC conference on computer and communications security. New York: ACM; 2014. p. 1105\u201316.","DOI":"10.1145\/2660267.2660359"},{"key":"231_CR29","doi-asserted-by":"crossref","unstructured":"Rastogi AK, Narang N, Siddiqui ZA. Imbalanced big data classification: a distributed implementation of smote. In: Proceedings of the workshop program of the 19th international conference on distributed computing and networking. New York: ACM; 2018. p. 14.","DOI":"10.1145\/3170521.3170535"},{"key":"231_CR30","doi-asserted-by":"crossref","unstructured":"Richter AN, Khoshgoftaar TM. Melanoma risk prediction with structured electronic health records. In: Proceedings of the 2018 ACM international conference on bioinformatics, computational biology, and health informatics. New York: ACM; 2018. p. 194\u20139.","DOI":"10.1145\/3233547.3233561"},{"key":"231_CR31","doi-asserted-by":"crossref","unstructured":"Richter AN, Khoshgoftaar TM. Modernizing analytics for melanoma with a large-scale research dataset. In: 2017 IEEE international conference on information reuse and integration (IRI); 2017. p. 551\u20138.","DOI":"10.1109\/IRI.2017.45"},{"key":"231_CR32","first-page":"9","volume":"2016","author":"J Bian","year":"2016","unstructured":"Bian J, Peng X-G, Wang Y, Zhang H. An efficient cost-sensitive feature selection using chaos genetic algorithm for class imbalance problem. Math Prob Eng. 2016;2016:9.","journal-title":"Math Prob Eng"},{"key":"231_CR33","unstructured":"KDD Cup 1999 Data. \n                    https:\/\/kdd.ics.uci.edu\/databases\/kddcup99\/kddcup99\n                    \n                  ."},{"issue":"19","key":"231_CR34","doi-asserted-by":"publisher","first-page":"2449","DOI":"10.1093\/bioinformatics\/bts475","volume":"28","author":"P Di Lena","year":"2012","unstructured":"Di Lena P, Nagata K, Baldi P. Deep architectures for protein contact map prediction. Bioinformatics. 2012;28(19):2449\u201357.","journal-title":"Bioinformatics"},{"key":"231_CR35","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-68372-0","volume-title":"Computational methods for protein structure prediction and modeling volume 1: basic characterization","author":"Y Xu","year":"2007","unstructured":"Xu Y, Xu D, Liang J. Computational methods for protein structure prediction and modeling volume 1: basic characterization. Berlin: Springer; 2007."},{"issue":"7","key":"231_CR36","doi-asserted-by":"publisher","first-page":"916","DOI":"10.1093\/bioinformatics\/btn050","volume":"24","author":"M Stout","year":"2008","unstructured":"Stout M, Bacardit J, Hirst JD, Krasnogor N. Prediction of recursive convex hull class assignments for protein residues. Bioinformatics. 2008;24(7):916\u201323.","journal-title":"Bioinformatics"},{"key":"231_CR37","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/j.knosys.2015.05.027","volume":"87","author":"I Triguero","year":"2015","unstructured":"Triguero I, del R\u00edo S, L\u00f3pez V, Bacardit J, Ben\u00edtez JM, Herrera F. Rosefw-rf: the winner algorithm for the ecbdl\u201914 big data competition: an extremely imbalanced big data bioinformatics problem. Knowl Based Syst. 2015;87:69\u201379.","journal-title":"Knowl Based Syst"},{"key":"231_CR38","doi-asserted-by":"crossref","unstructured":"Liu Y-H, Zhang H-Q, Yang Y-J. A dos attack situation assessment method based on qos. In: Proceedings of 2011 international conference on computer science and network technology. 2011. p. 1041\u20135.","DOI":"10.1109\/ICCSNT.2011.6182139"},{"key":"231_CR39","doi-asserted-by":"crossref","unstructured":"Yevsieieva O, Helalat SM. Analysis of the impact of the slow http dos and ddos attacks on the cloud environment. In: 2017 4th international scientific-practical conference problems of infocommunications. science and technology (PIC S&T). 2017. p. 519\u201323.","DOI":"10.1109\/INFOCOMMST.2017.8246453"},{"key":"231_CR40","doi-asserted-by":"crossref","unstructured":"Hirakaw T, Ogura K, Bista BB, Takata T. A defense method against distributed slow http dos attack. In: 2016 19th international conference on network-based information systems (NBiS)). 2016. p. 519\u201323.","DOI":"10.1109\/NBiS.2016.58"},{"key":"231_CR41","unstructured":"Slowloris.py. \n                    https:\/\/github.com\/gkbrk\/slowloris\n                    \n                  ."},{"key":"231_CR42","unstructured":"Apache Spark MLlib. \n                    https:\/\/spark.apache.org\/mllib\/\n                    \n                  ."},{"key":"231_CR43","first-page":"10","volume":"10","author":"M Zaharia","year":"2010","unstructured":"Zaharia M, Chowdhury M, Franklin MJ, Shenker S, Stoica I. Spark: cluster computing with working sets. HotCloud. 2010;10:10.","journal-title":"HotCloud"},{"issue":"34","key":"231_CR44","first-page":"1","volume":"17","author":"X Meng","year":"2016","unstructured":"Meng X, Bradley J, Yuvaz B, Sparks E, Venkataraman S, Liu D, Freeman J, Tsai D, Amde M, Owen S, et al. Mllib: machine learning in apache spark. JMLR. 2016;17(34):1\u20137.","journal-title":"JMLR"},{"key":"231_CR45","unstructured":"Apache Hadoop. \n                    http:\/\/hadoop.apache.org\/\n                    \n                  ."},{"key":"231_CR46","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4302-1943-9","volume-title":"Pro Hadoop","author":"J Venner","year":"2009","unstructured":"Venner J. Pro Hadoop. New York: Apress; 2009."},{"key":"231_CR47","volume-title":"Hadoop: the definitive guide","author":"T White","year":"2012","unstructured":"White T. Hadoop: the definitive guide. Sebastopol: O\u2019Reilly Media, Inc.; 2012."},{"key":"231_CR48","doi-asserted-by":"crossref","unstructured":"Shvachko K, Kuang H, Radia S, Chansler R. The hadoop distributed file system. In: 2010 IEEE 26th symposium on mass storage systems and technologies (MSST). 2010. p. 1\u201310.","DOI":"10.1109\/MSST.2010.5496972"},{"key":"231_CR49","doi-asserted-by":"crossref","unstructured":"Vavilapalli VK, Murthy AC, Douglas C, Agarwal S, Konar M, Evans R, Graves T, Lowe J, Shah H, Seth S, et al. Apache hadoop yarn: yet another resource negotiator. In: Proceedings of the 4th annual symposium on cloud computing. New York: ACM; 2013. p. 5.","DOI":"10.1145\/2523616.2523633"},{"issue":"1","key":"231_CR50","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1145\/1327452.1327492","volume":"51","author":"J Dean","year":"2008","unstructured":"Dean J, Ghemawat S. Mapreduce: simplified data processing on large clusters. Commun ACM. 2008;51(1):107\u201313.","journal-title":"Commun ACM"},{"key":"231_CR51","doi-asserted-by":"crossref","unstructured":"Bauder RA, Khoshgoftaar TM, Hasanin T. Data sampling approaches with severely imbalanced big data for medicare fraud detection. In: 2018 IEEE 30th international conference on tools with artificial intelligence (ICTAI); 2018. p. 137\u201342.","DOI":"10.1109\/ICTAI.2018.00030"},{"key":"231_CR52","volume-title":"Manual on setting up, using, and understanding random forests v3. 1","author":"L Breiman","year":"2002","unstructured":"Breiman L. Manual on setting up, using, and understanding random forests v3. 1. 1st ed. Berkeley: Statistics Department University of California; 2002.","edition":"1"},{"key":"231_CR53","doi-asserted-by":"crossref","unstructured":"Van\u00a0Hulse J, Khoshgoftaar TM, Napolitano A. An empirical comparison of repetitive undersampling techniques. In: 2009 IEEE international conference on information reuse & integration. 2009. p. 29\u201334.","DOI":"10.1109\/IRI.2009.5211614"},{"issue":"1","key":"231_CR54","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1186\/1471-2105-8-25","volume":"8","author":"C Strobl","year":"2007","unstructured":"Strobl C, Boulesteix A-L, Zeileis A, Hothorn T. Bias in random forest variable importance measures: illustrations, sources and a solution. BMC Bioinform. 2007;8(1):25.","journal-title":"BMC Bioinform"},{"issue":"1","key":"231_CR55","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1023\/B:AMAI.0000018580.96245.c6","volume":"41","author":"LE Raileanu","year":"2004","unstructured":"Raileanu LE, Stoffel K. Theoretical comparison between the gini index and information gain criteria. Ann Math Artif Intell. 2004;41(1):77\u201393.","journal-title":"Ann Math Artif Intell"},{"key":"231_CR56","doi-asserted-by":"crossref","unstructured":"Friedman J, Hastie T, Tibshirani R. The elements of statistical learning, vol. 1. Springer series in statistics, 2001.","DOI":"10.1007\/978-0-387-21606-5_1"},{"issue":"1","key":"231_CR57","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1186\/s40537-018-0138-3","volume":"5","author":"M Herland","year":"2018","unstructured":"Herland M, Khoshgoftaar TM, Bauder RA. Big data fraud detection using multiple medicare data sources. J Big Data. 2018;5(1):29.","journal-title":"J Big Data"},{"key":"231_CR58","doi-asserted-by":"publisher","DOI":"10.4135\/9781412983327","volume-title":"Analysis of variance","author":"GR Iversen","year":"1987","unstructured":"Iversen GR, Wildt AR, Norpoth H, Norpoth HP. Analysis of variance. 1st ed. Thousand Oaks: Sage; 1987.","edition":"1"},{"key":"231_CR59","doi-asserted-by":"publisher","first-page":"99","DOI":"10.2307\/3001913","volume":"5","author":"JW Tukey","year":"1949","unstructured":"Tukey JW. Comparing individual means in the analysis of variance. Biometrics. 1949;5:99\u2013114.","journal-title":"Biometrics"}],"container-title":["Journal of Big Data"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-019-0231-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s40537-019-0231-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-019-0231-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,7,29]],"date-time":"2020-07-29T23:21:35Z","timestamp":1596064895000},"score":1,"resource":{"primary":{"URL":"https:\/\/journalofbigdata.springeropen.com\/articles\/10.1186\/s40537-019-0231-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,31]]},"references-count":59,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2019,12]]}},"alternative-id":["231"],"URL":"https:\/\/doi.org\/10.1186\/s40537-019-0231-2","relation":{},"ISSN":["2196-1115"],"issn-type":[{"value":"2196-1115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,7,31]]},"assertion":[{"value":"26 May 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 July 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 July 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Not applicable.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"69"}}