{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T17:01:58Z","timestamp":1790787718326,"version":"4.1.0"},"reference-count":80,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2019,2,28]],"date-time":"2019-02-28T00:00:00Z","timestamp":1551312000000},"content-version":"tdm","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\/s40537-019-0181-8","type":"journal-article","created":{"date-parts":[[2019,2,28]],"date-time":"2019-02-28T01:09:40Z","timestamp":1551316180000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":47,"title":["The effects of class rarity on the evaluation of supervised healthcare fraud detection models"],"prefix":"10.1186","volume":"6","author":[{"given":"Matthew","family":"Herland","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richard A.","family":"Bauder","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taghi M.","family":"Khoshgoftaar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,2,28]]},"reference":[{"key":"181_CR1","first-page":"1263","volume":"9","author":"H He","year":"2008","unstructured":"He H, Garcia EA. Learning from imbalanced data. IEEE Trans Knowl Data Eng. 2008;9:1263\u201384.","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"181_CR2","unstructured":"Seiffert C, Khoshgoftaar TM, Van Hulse J, Napolitano A. Mining data with rare events: a case study. In: Ictai, 2007. Piscataway: IEEE. 2007; p. 132\u2013139."},{"issue":"2","key":"181_CR3","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1007\/s40747-017-0037-9","volume":"3","author":"A Fern\u00e1ndez","year":"2017","unstructured":"Fern\u00e1ndez A, del R\u00edo S, Chawla NV, Herrera F. An insight into imbalanced big data classification: outcomes and challenges. Complex Intell Syst. 2017;3(2):105\u201320.","journal-title":"Complex Intell Syst"},{"key":"181_CR4","unstructured":"Katal A, Wazid M, Goudar R. Big data: issues, challenges, tools and good practices. In: Sixth international conference on Contemporary computing (IC3), 2013. Piscataway: IEEE; p. 404\u2013409."},{"issue":"2","key":"181_CR5","doi-asserted-by":"publisher","first-page":"57","DOI":"10.11648\/j.ajtab.20180402.14","volume":"4","author":"S Senthilkumar","year":"2018","unstructured":"Senthilkumar S, Rai BK, Meshram AA, Gunasekaran A, Chandrakumarmangalam S. Big data in healthcare management: a review of literature. Am J Theor Appl Business. 2018;4(2):57\u201369.","journal-title":"Am J Theor Appl Business"},{"key":"181_CR6","unstructured":"OIG: Office of Inspector General Exclusion Authorities. \n                    https:\/\/oig.hhs.gov\/exclusions\/index.asp\n                    \n                   Accessed 14 July 2016."},{"key":"181_CR7","unstructured":"US Government, US Centers for Medicare & Medicaid Services: The Official US Government Site for Medicare. \n                    https:\/\/www.medicare.gov\/\n                    \n                  . Accessed 21 Jan 2017."},{"key":"181_CR8","unstructured":"CMS: Research, Statistics, Data, and Systems. \n                    https:\/\/www.cms.gov\/research-statistics-data-and-systems\/research-statistics-data-and-systems.html\n                    \n                  . Accessed 18 Nov 2018."},{"key":"181_CR9","unstructured":"Medicare.gov: What\u2019s Medicare."},{"issue":"1","key":"181_CR10","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1007\/s10742-016-0154-8","volume":"17","author":"R Bauder","year":"2017","unstructured":"Bauder R, Khoshgoftaar TM, Seliya N. A survey on the state of healthcare upcoding fraud analysis and detection. Health Serv Outcomes Res Methodol. 2017;17(1):31\u201355.","journal-title":"Health Serv Outcomes Res Methodol"},{"key":"181_CR11","unstructured":"CMS: Medicare fraud & abuse: prevention, detection, AND reporting. \n                    https:\/\/www.cms.gov\/Outreach-and-Education\/Medicare-Learning-Network-MLN\/MLNProducts\/downloads\/Fraud_and_Abuse.pdf\n                    \n                  . Accessed 28 Sept 2018."},{"issue":"5","key":"181_CR12","doi-asserted-by":"publisher","first-page":"1351","DOI":"10.1377\/hlthaff.28.5.1351","volume":"28","author":"L Morris","year":"2009","unstructured":"Morris L. Combating fraud in health care: an essential component of any cost containment strategy. Health Affairs. 2009;28(5):1351\u20136.","journal-title":"Health Affairs"},{"key":"181_CR13","unstructured":"CMS: National Health Expenditure Projections 2017\u20132026. \n                    https:\/\/www.cms.gov\/Research-Statistics-Data-and-Systems\/Statistics-Trends-and-Reports\/NationalHealthExpendData\/Downloads\/ForecastSummary.pdf\n                    \n                   Accessed 27 Sept 2018."},{"key":"181_CR14","unstructured":"Kaiser Family Foundation: The facts on Medicare spending and financing. \n                    https:\/\/www.kff.org\/medicare\/issue-brief\/the-facts-on-medicare-spending-and-financing\/\n                    \n                   Accessed 27 Sept 2018."},{"key":"181_CR15","unstructured":"Bradley Sawyer and Cynthia Cox Kaiser Family Foundation: how does health spending in the US compare to other countries? \n                    https:\/\/www.healthsystemtracker.org\/chart-collection\/health-spending-u-s-compare-countries\/#item-relative-size-wealth-u-s-spends-disproportionate-amount-health\n                    \n                  . Accessed 27 Sept 2018."},{"key":"181_CR16","doi-asserted-by":"crossref","unstructured":"Sheshasaayee A, Thomas SS. A purview of the impact of supervised learning methodologies on health insurance fraud detection. In: Information systems design and intelligent applications. Singapore: Springer; 2018. p. 978\u2013984.","DOI":"10.1007\/978-981-10-7512-4_98"},{"issue":"6","key":"181_CR17","first-page":"4175","volume":"13","author":"SS Waghade","year":"2018","unstructured":"Waghade SS, Karandikar AM. A comprehensive study of healthcare fraud detection based on machine learning. Int J Appl Eng Res. 2018;13(6):4175\u20138.","journal-title":"Int J Appl Eng Res"},{"issue":"2","key":"181_CR18","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1089\/big.2014.0060","volume":"3","author":"K Feldman","year":"2015","unstructured":"Feldman K, Chawla NV. Does medical school training relate to practice? Evidence from big data. Big Data. 2015;3(2):103\u201313.","journal-title":"Big Data"},{"key":"181_CR19","doi-asserted-by":"publisher","DOI":"10.1007\/s10729-018-9460-8","author":"M Herland","year":"2018","unstructured":"Herland M, Bauder RA, Khoshgoftaar TM. Approaches for identifying us Medicare fraud in provider claims data. Health Care Manag Sci. 2018. \n                    https:\/\/doi.org\/10.1007\/s10729-018-9460-8\n                    \n                  .","journal-title":"Health Care Manag Sci"},{"key":"181_CR20","doi-asserted-by":"crossref","unstructured":"Bauder RA, Khoshgoftaar TM. The detection of Medicare fraud using machine learning methods with excluded provider labels. In: FLAIRS conference, 2018. p. 404\u2013409.","DOI":"10.1109\/ICMLA.2017.00-48"},{"key":"181_CR21","doi-asserted-by":"crossref","unstructured":"Chandola V, Sukumar SR, Schryver JC. Knowledge discovery from massive healthcare claims data. In: Proceedings of the 19th ACM SIGKDD international conference on knowledge discovery and data mining. New York: ACM; 2013. p. 1312\u20131320.","DOI":"10.1145\/2487575.2488205"},{"key":"181_CR22","unstructured":"Khurjekar N, Chou C-A, Khasawneh MT. Detection of fraudulent claims using hierarchical cluster analysis. In: IIE Proceedings annual conference. Peachtree Corners: Institute of Industrial and Systems Engineers (IISE); 2015. p. 2388."},{"key":"181_CR23","doi-asserted-by":"crossref","unstructured":"Branting LK, Reeder F, Gold J, Champney T. Graph analytics for healthcare fraud risk estimation. In: IEEE\/ACM international conference on advances in social networks analysis and mining (ASONAM), 2016. Piscataway: IEEE; 2016. p. 845\u2013851.","DOI":"10.1109\/ASONAM.2016.7752336"},{"key":"181_CR24","doi-asserted-by":"crossref","unstructured":"Sadiq S, Tao Y, Yan Y, Shyu M-L. Mining anomalies in Medicare big data using patient rule induction method. In: IEEE third international conference On multimedia Big Data (BigMM), 2017. Piscataway: IEEE; 2017; p. 185\u2013192.","DOI":"10.1109\/BigMM.2017.56"},{"issue":"1","key":"181_CR25","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. \n                    https:\/\/doi.org\/10.1186\/s40537-018-0138-3\n                    \n                  .","journal-title":"J Big Data"},{"key":"181_CR26","unstructured":"CMS: National Provider Identifier Standard (NPI). \n                    https:\/\/www.cms.gov\/Regulations-and-Guidance\/Administrative-Simplification\/NationalProvIdentStand\/\n                    \n                  . Accessed 11 Aug 2016."},{"key":"181_CR27","unstructured":"Aetna: the facts about rising health care costs. \n                    http:\/\/www.aetna.com\/health-reform-connection\/aetnasvision\/facts-about-costs.html\n                    \n                  . Accessed 2015."},{"key":"181_CR28","doi-asserted-by":"crossref","unstructured":"Rao RB, Fung G, Rosales R. On the dangers of Cross-Validation. An experimental evaluation. In: Proceedings of the 2008 SIAM international conference on data mining, 2008. Philadelphia: SIAM; p. 588\u2013596.","DOI":"10.1137\/1.9781611972788.54"},{"key":"181_CR29","unstructured":"Prashant Gupta: Cross-Validation in machine learning. \n                    https:\/\/towardsdatascience.com\/cross-validation-in-machine-learning-72924a69872f\n                    \n                  . Accessed 10 Sept 2018."},{"key":"181_CR30","unstructured":"Zhang W, Kobeissi S, Tomko S, Challis C. Adaptive sampling scheme for learning in severely imbalanced large scale data. In: Asian conference on machine learning, 2017. p. 240\u2013247."},{"key":"181_CR31","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1016\/j.eswa.2016.12.035","volume":"73","author":"G Haixiang","year":"2017","unstructured":"Haixiang G, Yijing L, Shang J, Mingyun G, Yuanyue H, Bing G. Learning from class-imbalanced data: review of methods and applications. Expert Syst Appl. 2017;73:220\u201339.","journal-title":"Expert Syst Appl"},{"key":"181_CR32","doi-asserted-by":"crossref","unstructured":"Lin S-C, Wang C, Wu Z-Y, Chung Y-F. Detect rare events via mice algorithm with optimal threshold. In: Seventh international conference on innovative mobile and internet services in ubiquitous computing (IMIS), 2013. Piscataway: IEEE; 2013. p. 70\u201375.","DOI":"10.1109\/IMIS.2013.21"},{"key":"181_CR33","unstructured":"Alhammady H, Ramamohanarao K. Using emerging patterns and decision trees in rare-class classification. In: Null, 2004. Piscataway: IEEE; 2004. p. 315\u2013318."},{"issue":"7","key":"181_CR34","first-page":"0180830","volume":"12","author":"J Li","year":"2017","unstructured":"Li J, Liu L-S, Fong S, Wong RK, Mohammed S, Fiaidhi J, Sung Y, Wong KK. Adaptive swarm balancing algorithms for rare-event prediction in imbalanced healthcare data. PloS ONE. 2017;12(7):0180830.","journal-title":"PloS ONE"},{"key":"181_CR35","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.patcog.2016.08.023","volume":"62","author":"X Zhang","year":"2017","unstructured":"Zhang X, Li Y, Kotagiri R, Wu L, Tari Z, Cheriet M. Krnn: k rare-class nearest neighbour classification. Pattern Recogn. 2017;62:33\u201344.","journal-title":"Pattern Recogn"},{"issue":"11","key":"181_CR36","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1145\/2934664","volume":"59","author":"M Zaharia","year":"2016","unstructured":"Zaharia M, Xin RS, Wendell P, Das T, Armbrust M, Dave A, Meng X, Rosen J, Venkataraman S, Franklin MJ, et al. Apache spark: a unified engine for big data processing. Commun ACM. 2016;59(11):56\u201365.","journal-title":"Commun ACM"},{"key":"181_CR37","doi-asserted-by":"crossref","unstructured":"Dongre SS, Malik LG. Rare class problem in data mining. Int J Adv Res Comput Sci. 2017;8(7).","DOI":"10.26483\/ijarcs.v8i7.4530"},{"key":"181_CR38","doi-asserted-by":"crossref","unstructured":"Hasanin T, Khoshgoftaar TM. The effects of random undersampling with simulated class imbalance for big data. In: 2018 IEEE international conference on information reuse and integration (IRI). Piscataway: IEEE; 2018. p. 70\u201379.","DOI":"10.1109\/IRI.2018.00018"},{"issue":"1","key":"181_CR39","first-page":"1235","volume":"17","author":"X Meng","year":"2016","unstructured":"Meng X, Bradley J, Yavuz B, Sparks E, Venkataraman S, Liu D, Freeman J, Tsai D, Amde M, Owen S, et al. Mllib: Machine learning in apache spark. J Mach Learn Res. 2016;17(1):1235\u201341.","journal-title":"J Mach Learn Res"},{"key":"181_CR40","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, 2018. New York: ACM; 2018. p. 14."},{"key":"181_CR41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2832629","author":"Q Dong","year":"2018","unstructured":"Dong Q, Gong S, Zhu X. Imbalanced deep learning by minority class incremental rectification. IEEE Trans Pattern Anal Mach Intell. 2018. \n                    https:\/\/doi.org\/10.1109\/TPAMI.2018.2832629\n                    \n                  .","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"3","key":"181_CR42","doi-asserted-by":"publisher","first-page":"1009","DOI":"10.1007\/s13042-015-0478-7","volume":"8","author":"J Zhai","year":"2017","unstructured":"Zhai J, Zhang S, Wang C. The classification of imbalanced large data sets based on mapreduce and ensemble of elm classifiers. Int J Mach Learn Cybern. 2017;8(3):1009\u201317.","journal-title":"Int J Mach Learn Cybern"},{"issue":"12","key":"181_CR43","doi-asserted-by":"publisher","first-page":"3347","DOI":"10.1109\/TKDE.2015.2453171","volume":"27","author":"A Tayal","year":"2015","unstructured":"Tayal A, Coleman TF, Li Y. Rankrc: Large-scale nonlinear rare class ranking. IEEE Trans Knowl Data Eng. 2015;27(12):3347\u201359.","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"1","key":"181_CR44","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1111\/coin.12123","volume":"34","author":"M Maalouf","year":"2018","unstructured":"Maalouf M, Homouz D, Trafalis TB. Logistic regression in large rare events and imbalanced data: a performance comparison of prior correction and weighting methods. Comput Intell. 2018;34(1):161\u201374.","journal-title":"Comput Intell"},{"issue":"5","key":"181_CR45","doi-asserted-by":"publisher","first-page":"980","DOI":"10.1136\/amiajnl-2012-001409","volume":"20","author":"KE Chai","year":"2013","unstructured":"Chai KE, Anthony S, Coiera E, Magrabi F. Using statistical text classification to identify health information technology incidents. J Am Med Inform Assoc. 2013;20(5):980\u20135.","journal-title":"J Am Med Inform Assoc"},{"key":"181_CR46","unstructured":"CMS: Medicare provider utilization and payment data: physician and other supplier. \n                    https:\/\/www.cms.gov\/Research-Statistics-Data-and-Systems\/Statistics-Trends-and-Reports\/Medicare-Provider-Charge-Data\/Physician-and-Other-Supplier.html\n                    \n                  . Accessed 16 Aug 2016."},{"key":"181_CR47","unstructured":"CMS: Medicare provider utilization and payment data: Part D prescriber. \n                    https:\/\/www.cms.gov\/Research-Statistics-Data-and-Systems\/Statistics-Trends-and-Reports\/Medicare-Provider-Charge-Data\/Part-D-Prescriber.html\n                    \n                  . Accessed 21 Dec 2017."},{"key":"181_CR48","unstructured":"CMS: Medicare provider utilization and payment data: referring durable medical equipment, prosthetics, orthotics and supplies. \n                    https:\/\/www.cms.gov\/Research-Statistics-Data-and-Systems\/Statistics-Trends-and-Reports\/Medicare-Provider-Charge-Data\/DME.html\n                    \n                  . Accessed 21 Dec 2017."},{"key":"181_CR49","unstructured":"CMS Office of Enterprise Data and Analytics: Medicare Fee-For-Service Provider Utilization & Payment Data Physician and other supplier. \n                    https:\/\/www.cms.gov\/Research-Statistics-Data-and-Systems\/Statistics-Trends-and-Reports\/Medicare-Provider-Charge-Data\/Downloads\/Medicare-Physician-and-Other-Supplier-PUF-Methodology.pdf\n                    \n                  . Accessed 04 Sept 2018."},{"key":"181_CR50","unstructured":"CMS office of Enterprise Data and Analytics: Medicare Fee-For Service Provider Utilization & Payment Data Part D Prescriber public use file: a methodological overview. \n                    https:\/\/www.cms.gov\/Research-Statistics-Data-and-Systems\/Statistics-Trends-and-Reports\/Medicare-Provider-Charge-Data\/Downloads\/Prescriber_Methods.pdf\n                    \n                  . Accessed 04 Sept 2018."},{"key":"181_CR51","unstructured":"CMS Office of Enterprise Data and Analytics: Medicare Fee-For-Service Provider Utilization & Payment Data referring durable medical equipment, prosthetics, orthotics and supplies public use file: a methodological overview. \n                    https:\/\/www.cms.gov\/Research-Statistics-Data-and-Systems\/Statistics-Trends-and-Reports\/Medicare-Provider-Charge-Data\/Downloads\/DME_Methodology.pdf\n                    \n                  . Accessed 04 Sept 2018."},{"key":"181_CR52","unstructured":"CMS: HCPCS\u2014general information. \n                    https:\/\/www.cms.gov\/Medicare\/Coding\/MedHCPCSGenInfo\/index.html\n                    \n                  . Accessed 13 Jan 2018."},{"key":"181_CR53","unstructured":"OIG: Office of Inspector General Exclusion Authorities US Department of Health and Human Services. \n                    https:\/\/oig.hhs.gov\/\n                    \n                  . Accessed 05 Jan 2018."},{"key":"181_CR54","unstructured":"LEIE: Office of Inspector General LEIE Downloadable Databases. \n                    https:\/\/oig.hhs.gov\/exclusions\/authorities.asp\n                    \n                  . Accessed 14 July 2016."},{"issue":"1","key":"181_CR55","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1108\/17506121311315391","volume":"7","author":"V Pande","year":"2013","unstructured":"Pande V, Maas W. Physician Medicare fraud: characteristics and consequences. Int J Pharm Healthcare Market. 2013;7(1):8\u201333.","journal-title":"Int J Pharm Healthcare Market"},{"key":"181_CR56","doi-asserted-by":"crossref","unstructured":"Van\u00a0Hulse J, Khoshgoftaar TM, Napolitano A. Experimental perspectives on learning from imbalanced data. In: Proceedings of the 24th international conference on machine learning, 2007. New York: ACM; 2007. p. 935\u2013942.","DOI":"10.1145\/1273496.1273614"},{"key":"181_CR57","doi-asserted-by":"crossref","unstructured":"Japkowicz N. Concept-learning in the presence of between-class and within-class imbalances. In: Conference of the Canadian society for computational studies of intelligence, 2001. Berlin: Springer; 2001. p. 67\u201377.","DOI":"10.1007\/3-540-45153-6_7"},{"issue":"1","key":"181_CR58","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1145\/1007730.1007734","volume":"6","author":"GM Weiss","year":"2004","unstructured":"Weiss GM. Mining with rarity: a unifying framework. ACM Sigkdd Explorations Newslett. 2004;6(1):7\u201319.","journal-title":"ACM Sigkdd Explorations Newslett"},{"key":"181_CR59","doi-asserted-by":"crossref","unstructured":"Chawla NV. Data mining for imbalanced datasets: an overview. In: Data mining and knowledge discovery handbook. Boston: Springer; 2009. p. 875\u2013886.","DOI":"10.1007\/978-0-387-09823-4_45"},{"key":"181_CR60","doi-asserted-by":"crossref","unstructured":"Bauder RA, Khoshgoftaar TM, Hasanin T. Data sampling approaches with severely imbalanced big data for Medicare fraud detection. In: IEEE 30th international conference On tools with artificial intelligence (ICTAI), 2018. Piscataway: IEEE; 2018.","DOI":"10.1109\/ICTAI.2018.00030"},{"key":"181_CR61","doi-asserted-by":"crossref","unstructured":"Bauder RA, Khoshgoftaar TM. Medicare fraud detection using Random Forest with class imbalanced big data. In: 2018 IEEE International conference on information reuse and integration (IRI), 2018. Piscataway: IEEE; 2018. p. 80\u201387.","DOI":"10.1109\/IRI.2018.00019"},{"issue":"Sep","key":"181_CR62","first-page":"1089","volume":"5","author":"Y Bengio","year":"2004","unstructured":"Bengio Y, Grandvalet Y. No unbiased estimator of the variance of k-fold Cross-Validation. J Mach Learn Res. 2004;5(Sep):1089\u2013105.","journal-title":"J Mach Learn Res"},{"key":"181_CR63","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1016\/j.neuroimage.2017.06.061","volume":"180","author":"G Varoquaux","year":"2018","unstructured":"Varoquaux G. Cross-validation failure: small sample sizes lead to large error bars. Neuroimage. 2018;180:68\u201377.","journal-title":"Neuroimage"},{"key":"181_CR64","unstructured":"Justin D: Overfitting, model selection, cross validation, bias-variance. \n                    https:\/\/people.cs.umass.edu\/~domke\/courses\/sml2011\/02overfitting.pdf\n                    \n                  . Accessed 27 Sept 2018."},{"key":"181_CR65","unstructured":"Apache: Apache Spark. \n                    http:\/\/spark.apache.org\/\n                    \n                  . Accessed 24 May 2018."},{"key":"181_CR66","unstructured":"Apache: Apache Hadoop. \n                    http:\/\/hadoop.apache.org\/\n                    \n                  . Accessed 24 May 2018."},{"key":"181_CR67","unstructured":"Apache: Spark Release 2.3.0. \n                    http:\/\/spark.apache.org\/releases\/spark-release-2-3-0.html\n                    \n                  . Accessed 29 Nov 2018."},{"key":"181_CR68","unstructured":"Apache: classification and regression. \n                    https:\/\/spark.apache.org\/docs\/2.3.0\/ml-classification-regression.html\n                    \n                  . Accessed 19 Sept 2018."},{"key":"181_CR69","unstructured":"Apache: linear methods-RDD-based API. \n                    https:\/\/spark.apache.org\/docs\/latest\/mllib-linear-methods.html\n                    \n                  . Accessed 10 Sept 2017."},{"key":"181_CR70","unstructured":"Apache Spark: ensembles-RDD-based API. \n                    https:\/\/spark.apache.org\/docs\/2.3.0\/mllib-ensembles.html\n                    \n                  . Accessed 24 May 2018."},{"key":"181_CR71","doi-asserted-by":"crossref","unstructured":"Bekkar M, Djemaa HK, Alitouche TA. Evaluation measures for models assessment over imbalanced data sets. J Inf Eng Appl. 2013;3(10).","DOI":"10.5121\/ijdkp.2013.3402"},{"key":"181_CR72","doi-asserted-by":"crossref","unstructured":"Seliya N, Khoshgoftaar TM, Van\u00a0Hulse J. A study on the relationships of classifier performance metrics. In: 21st international conference on tools with artificial intelligence, ICTAI\u201909, 2009. Piscataway: IEEE; 2009. p. 59\u201366.","DOI":"10.1109\/ICTAI.2009.25"},{"key":"181_CR73","doi-asserted-by":"crossref","unstructured":"Jeni LA, Cohn JF, De\u00a0La\u00a0Torre F. Facing imbalanced data\u2013recommendations for the use of performance metrics. In: Humaine association conference on affective computing and intelligent interaction (ACII), 2013. Piscataway: IEEE; 2013. p. 245\u2013251.","DOI":"10.1109\/ACII.2013.47"},{"issue":"1","key":"181_CR74","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1214\/009053604000001048","volume":"33","author":"A Gelman","year":"2005","unstructured":"Gelman A, et al. Analysis of variance-why it is more important than ever. Ann Stat. 2005;33(1):1\u201353.","journal-title":"Ann Stat"},{"issue":"2","key":"181_CR75","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(2):99\u2013114.","journal-title":"Biometrics"},{"issue":"1","key":"181_CR76","first-page":"191","volume":"41","author":"S Cessie Le","year":"1992","unstructured":"Le Cessie S, Van Houwelingen JC. Ridge estimators in logistic regression. J Roy Stat Soc: Ser C (Appl Stat). 1992;41(1):191\u2013201.","journal-title":"J Roy Stat Soc: Ser C (Appl Stat)"},{"issue":"1","key":"181_CR77","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1145\/1656274.1656278","volume":"11","author":"M Hall","year":"2009","unstructured":"Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten IH. The weka data mining software: an update. ACM SIGKDD Explorations Newslett. 2009;11(1):10\u20138.","journal-title":"ACM SIGKDD Explorations Newslett"},{"key":"181_CR78","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":"1","key":"181_CR79","doi-asserted-by":"publisher","first-page":"191","DOI":"10.2307\/2347628","volume":"41","author":"S Cessie le","year":"1992","unstructured":"le Cessie S, van Houwelingen JC. Ridge estimators in logistic regression. Appl Stat. 1992;41(1):191\u2013201.","journal-title":"Appl Stat"},{"issue":"1","key":"181_CR80","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L. Random Forests. Mach Learn. 2001;45(1):5\u201332.","journal-title":"Mach Learn"}],"container-title":["Journal of Big Data"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-019-0181-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s40537-019-0181-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s40537-019-0181-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,2,27]],"date-time":"2020-02-27T19:08:14Z","timestamp":1582830494000},"score":1,"resource":{"primary":{"URL":"https:\/\/journalofbigdata.springeropen.com\/articles\/10.1186\/s40537-019-0181-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2,28]]},"references-count":80,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2019,12]]}},"alternative-id":["181"],"URL":"https:\/\/doi.org\/10.1186\/s40537-019-0181-8","relation":{},"ISSN":["2196-1115"],"issn-type":[{"value":"2196-1115","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,2,28]]},"assertion":[{"value":"11 December 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 February 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 February 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"21"}}