{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T04:24:01Z","timestamp":1777695841189,"version":"3.51.4"},"reference-count":64,"publisher":"SAGE Publications","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IDA"],"published-print":{"date-parts":[[2020,2,18]]},"DOI":"10.3233\/ida-184415","type":"journal-article","created":{"date-parts":[[2020,2,25]],"date-time":"2020-02-25T11:20:49Z","timestamp":1582629649000},"page":"141-161","source":"Crossref","is-referenced-by-count":16,"title":["A study on rare fraud predictions with big Medicare claims fraud data"],"prefix":"10.1177","volume":"24","author":[{"given":"Richard A.","family":"Bauder","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taghi M.","family":"Khoshgoftaar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"key":"10.3233\/IDA-184415_ref7","unstructured":"H. Alhammady and K. Ramamohanarao, Using emerging patterns and decision trees in rare-class classification, in: Data Mining, 2004. ICDM\u201904. Fourth IEEE International Conference on, IEEE, 2004, pp. 315\u2013318."},{"issue":"3","key":"10.3233\/IDA-184415_ref8","first-page":"176","article-title":"Classification with class imbalance problem: a review","volume":"7","author":"Ali","year":"2015","journal-title":"Int J Adv Soft Comput Appl"},{"key":"10.3233\/IDA-184415_ref9","unstructured":"Association of American Retired Persons (AARP). Chronic conditions among older americans."},{"key":"10.3233\/IDA-184415_ref10","doi-asserted-by":"crossref","unstructured":"R.A. Bauder, R. Rosa and T.M. Khoshgoftaar, Identifying medicare provider fraud with unsupervised machine learning, in: 2018 IEEE International Conference on Information Reuse and Integration (IRI), IEEE, 2018, pp. 285\u2013292.","DOI":"10.1109\/IRI.2018.00051"},{"key":"10.3233\/IDA-184415_ref11","doi-asserted-by":"crossref","unstructured":"R.A. Bauder and T.M. Khoshgoftaar, A novel method for fraudulent medicare claims detection from expected payment deviations (application paper), in: Information Reuse and Integration (IRI), 2016 IEEE 17th International Conference on, IEEE, 2016, pp. 11\u201319.","DOI":"10.1109\/IRI.2016.11"},{"key":"10.3233\/IDA-184415_ref12","doi-asserted-by":"crossref","unstructured":"R.A. Bauder and T.M. Khoshgoftaar, Medicare fraud detection using machine learning methods, in: Machine Learning and Applications (ICMLA), 2017 16th IEEE International Conference on, IEEE, 2017, pp. 858\u2013865.","DOI":"10.1109\/ICMLA.2017.00-48"},{"issue":"3-4","key":"10.3233\/IDA-184415_ref13","doi-asserted-by":"crossref","first-page":"256","DOI":"10.1007\/s10742-017-0172-1","article-title":"Multivariate outlier detection in medicare claims payments applying probabilistic programming methods","volume":"17","author":"Bauder","year":"2017","journal-title":"Health Services and Outcomes Research Methodology"},{"key":"10.3233\/IDA-184415_ref14","doi-asserted-by":"crossref","unstructured":"R.A. Bauder and T.M. Khoshgoftaar, Medicare fraud detection using random forest with class imbalanced big data, in: Information Reuse and Integration (IRI), 2018 IEEE 19th International Conference on, IEEE, 2018, pp. 80\u201387.","DOI":"10.1109\/IRI.2018.00019"},{"key":"10.3233\/IDA-184415_ref15","doi-asserted-by":"crossref","unstructured":"R.A. Bauder and T.M. Khoshgoftaar, A survey of medicare data processing and integration for fraud detection, in: Information Reuse and Integration (IRI), 2018 IEEE 19th International Conference on, IEEE, 2018, pp. 9\u201314.","DOI":"10.1109\/IRI.2018.00010"},{"key":"10.3233\/IDA-184415_ref16","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1007\/s13755-018-0051-3","article-title":"The effects of varying class distribution on learner behavior for medicare fraud detection with imbalanced big data","volume":"6","author":"Bauder","year":"2018","journal-title":"Health Information Science and Systems"},{"key":"10.3233\/IDA-184415_ref17","doi-asserted-by":"crossref","unstructured":"R.A. Bauder, T.M. Khoshgoftaar and T. Hasanin, Data sampling approaches with severely imbalanced big data for medicare fraud detection, in: 2018 IEEE 30th International Conference on Tools with Artificial Intelligence (ICTAI), IEEE, 2018, pp. 137\u2013142.","DOI":"10.1109\/ICTAI.2018.00030"},{"key":"10.3233\/IDA-184415_ref18","doi-asserted-by":"crossref","unstructured":"R.A. Bauder, T.M. Khoshgoftaar, A. Richter and M. Herland, Predicting medical provider specialties to detect anomalous insurance claims, in: Tools with Artificial Intelligence (ICTAI), 2016 IEEE 28th International Conference on, IEEE, 2016, pp. 784\u2013790.","DOI":"10.1109\/ICTAI.2016.0123"},{"issue":"1","key":"10.3233\/IDA-184415_ref19","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1007\/s10742-016-0154-8","article-title":"A survey on the state of healthcare upcoding fraud analysis and detection","volume":"17","author":"Bauder","year":"2017","journal-title":"Health Services and Outcomes Research Methodology"},{"key":"10.3233\/IDA-184415_ref20","doi-asserted-by":"crossref","unstructured":"M. Bekkar, H.K. Djemaa and T.A. Alitouche, Evaluation measures for models assessment over imbalanced data sets, Iournal of Information Engineering and Applications 3(10) (2013).","DOI":"10.5121\/ijdkp.2013.3402"},{"key":"10.3233\/IDA-184415_ref21","doi-asserted-by":"crossref","unstructured":"L.K. Branting, F. Reeder, J. Gold and T. Champney, Graph analytics for healthcare fraud risk estimation, in: Advances in Social Networks Analysis and Mining (ASONAM), 2016 IEEE\/ACM International Conference on, IEEE, 2016, pp.\u00a0845\u2013851.","DOI":"10.1109\/ASONAM.2016.7752336"},{"issue":"1","key":"10.3233\/IDA-184415_ref22","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Machine Learning"},{"issue":"5","key":"10.3233\/IDA-184415_ref23","doi-asserted-by":"crossref","first-page":"980","DOI":"10.1136\/amiajnl-2012-001409","article-title":"Using statistical text classification to identify health information technology incidents","volume":"20","author":"Chai","year":"2013","journal-title":"Journal of the American Medical Informatics Association"},{"key":"10.3233\/IDA-184415_ref24","doi-asserted-by":"crossref","unstructured":"V. Chandola, S.R. Sukumar and J.C. Schryver, Knowledge discovery from massive healthcare claims data, in: Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM, 2013, pp.\u00a01312\u20131320.","DOI":"10.1145\/2487575.2488205"},{"issue":"s1","key":"10.3233\/IDA-184415_ref25","doi-asserted-by":"crossref","first-page":"S87","DOI":"10.3233\/IDA-150771","article-title":"How much effort should be spent to detect fraudulent applications when engaged in classifier-based lending","volume":"19","author":"Chong","year":"2015","journal-title":"Intelligent Data Analysis"},{"key":"10.3233\/IDA-184415_ref26","unstructured":"CMS. Medicare provider utilization and payment data."},{"key":"10.3233\/IDA-184415_ref30","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."},{"key":"10.3233\/IDA-184415_ref31","unstructured":"CMS Office of Enterprise Data and Analytics. Medicare fee-for-service provider utilization & payment data physician and other supplier."},{"key":"10.3233\/IDA-184415_ref32","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."},{"issue":"10","key":"10.3233\/IDA-184415_ref35","doi-asserted-by":"crossref","first-page":"4915","DOI":"10.1016\/j.eswa.2014.02.026","article-title":"Learned lessons in credit card fraud detection from a practitioner perspective","volume":"41","author":"Pozzolo","year":"2014","journal-title":"Expert Systems with Applications"},{"key":"10.3233\/IDA-184415_ref36","doi-asserted-by":"crossref","unstructured":"Y. Demchenko, Z. Zhao, P. Grosso, A. Wibisono and C.D. Laat, Addressing big data challenges for scientific data infrastructure, in: Cloud Computing Technology and Science (CloudCom), 2012 IEEE 4th International Conference on, IEEE, 2012, pp. 614\u2013617.","DOI":"10.1109\/CloudCom.2012.6427494"},{"issue":"7","key":"10.3233\/IDA-184415_ref37","doi-asserted-by":"crossref","first-page":"1102","DOI":"10.26483\/ijarcs.v8i7.4530","article-title":"Rare class problem in data mining: review","volume":"8","author":"Dongre","year":"2017","journal-title":"International Journal of Advanced Research in Computer Science"},{"key":"10.3233\/IDA-184415_ref38","unstructured":"C. Drummond and R.C. Holte, C4.5, class imbalance, and cost sensitivity: why under-sampling beats over-sampling, in: Workshop on Learning from Imbalanced Datasets II, Citeseer, Vol. 11, 2003, pp. 1\u20138."},{"issue":"2","key":"10.3233\/IDA-184415_ref39","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1089\/big.2014.0060","article-title":"Does medical school training relate to practice? Evidence from big data","volume":"3","author":"Feldman","year":"2015","journal-title":"Big Data"},{"issue":"2","key":"10.3233\/IDA-184415_ref40","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1007\/s40747-017-0037-9","article-title":"An insight into imbalanced big data classification: outcomes and challenges","volume":"3","author":"Fern\u00e1ndez","year":"2017","journal-title":"Complex & Intelligent Systems"},{"issue":"1","key":"10.3233\/IDA-184415_ref42","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1214\/009053604000001048","article-title":"Analysis of variance \u2013 why it is more important than ever","volume":"33","author":"Gelman","year":"2005","journal-title":"The Annals of Statistics"},{"key":"10.3233\/IDA-184415_ref43","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1016\/j.eswa.2016.12.035","article-title":"learning from class-imbalanced data: Review of methods and applications","volume":"73","author":"Guo","year":"2017","journal-title":"Expert Systems with Applications"},{"key":"10.3233\/IDA-184415_ref44","doi-asserted-by":"crossref","unstructured":"T. Hasanin and T.M. Khoshgoftaar, The effects of random undersampling with simulated class imbalance for big data, in: 2018 IEEE International Conference on Information Reuse and Integration (IRI), IEEE, 2018, pp. 70\u201379.","DOI":"10.1109\/IRI.2018.00018"},{"issue":"9","key":"10.3233\/IDA-184415_ref45","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","article-title":"Learning from imbalanced data","volume":"21","author":"He","year":"2009","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10.3233\/IDA-184415_ref46","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1186\/s40537-018-0138-3","article-title":"Big data fraud detection using multiple medicare data sources","volume":"5","author":"Herland","year":"2018","journal-title":"Journal of Big Data"},{"key":"10.3233\/IDA-184415_ref47","doi-asserted-by":"crossref","unstructured":"L.A. Jeni, J.F. Cohn and F.D.L. Torre, Facing imbalanced data-recommendations for the use of performance metrics, in: Affective Computing and Intelligent Interaction (ACII), 2013 Humaine Association Conference on, IEEE, 2013, pp.\u00a0245\u2013251.","DOI":"10.1109\/ACII.2013.47"},{"key":"10.3233\/IDA-184415_ref49","doi-asserted-by":"crossref","unstructured":"A. Katal, M. Wazid and R.H. Goudar, Big data: issues, challenges, tools and good practices, in: Contemporary Computing (IC3), 2013 Sixth International Conference on, IEEE, 2013, pp. 404\u2013409.","DOI":"10.1109\/IC3.2013.6612229"},{"issue":"4","key":"10.3233\/IDA-184415_ref50","doi-asserted-by":"crossref","first-page":"902","DOI":"10.1109\/72.595888","article-title":"Application of neural networks to software quality modeling of a very large telecommunications system","volume":"8","author":"Khoshgoftaar","year":"1997","journal-title":"IEEE Transactions on Neural Networks"},{"key":"10.3233\/IDA-184415_ref51","doi-asserted-by":"crossref","unstructured":"T.M. Khoshgoftaar, M. Golawala and J. Van Hulse, An empirical study of learning from imbalanced data using random forest, in: Tools with Artificial Intelligence, 2007. ICTAI 2007. 19th IEEE International Conference on, IEEE, Vol. 2, 2007, pp. 310\u2013317.","DOI":"10.1109\/ICTAI.2007.46"},{"key":"10.3233\/IDA-184415_ref52","doi-asserted-by":"crossref","unstructured":"T.M. Khoshgoftaar, C. Seiffert, J. Van Hulse, A. Napolitano and A. Folleco, Learning with limited minority class data, in: Machine Learning and Applications, 2007. ICMLA 2007. Sixth International Conference on, IEEE, 2007, pp. 348\u2013353.","DOI":"10.1109\/ICMLA.2007.76"},{"key":"10.3233\/IDA-184415_ref53","unstructured":"N. Khurjekar, C.-A. Chou and M.T. Khasawneh, Detection of fraudulent claims using hierarchical cluster analysis, in: IIE Annual Conference. Proceedings, Institute of Industrial and Systems Engineers (IISE), 2015, p. 2388."},{"issue":"5","key":"10.3233\/IDA-184415_ref54","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.1016\/j.urology.2014.11.054","article-title":"Variability in medicare utilization and payment among urologists","volume":"85","author":"Ko","year":"2015","journal-title":"Urology"},{"key":"10.3233\/IDA-184415_ref55","doi-asserted-by":"crossref","first-page":"191","DOI":"10.2307\/2347628","article-title":"Ridge estimators in logistic regression","author":"Cessie","year":"1992","journal-title":"Applied Statistics"},{"key":"10.3233\/IDA-184415_ref58","doi-asserted-by":"crossref","unstructured":"J. Li, L. Liu, S. Fong, R.K. Wong, S. Mohammed, J. Fiaidhi, Y. Sung and K.K.L. Wong, Adaptive swarm balancing algorithms for rare-event prediction in imbalanced healthcare data, PloS One 12(7) (2017), e0180830.","DOI":"10.1371\/journal.pone.0180830"},{"key":"10.3233\/IDA-184415_ref59","doi-asserted-by":"crossref","unstructured":"S.-C. Lin, C. Wang, Z.-Y. Wu and Y.-F. Chung, Detect rare events via mice algorithm with optimal threshold, in: Innovative Mobile and Internet Services in Ubiquitous Computing (IMIS), 2013 Seventh International Conference on, IEEE, 2013, pp. 70\u201375.","DOI":"10.1109\/IMIS.2013.21"},{"issue":"1","key":"10.3233\/IDA-184415_ref60","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1111\/coin.12123","article-title":"Logistic regression in large rare events and imbalanced data: a performance comparison of prior correction and weighting methods","volume":"34","author":"Maalouf","year":"2018","journal-title":"Computational Intelligence"},{"issue":"1","key":"10.3233\/IDA-184415_ref62","first-page":"1235","article-title":"Mllib: machine learning in apache spark","volume":"17","author":"Meng","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"10.3233\/IDA-184415_ref65","unstructured":"OIG. Office of inspector general exclusion authorities."},{"key":"10.3233\/IDA-184415_ref66","unstructured":"OIG. Office of inspector general exclusion authorities us department of health and human services."},{"issue":"1","key":"10.3233\/IDA-184415_ref67","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1108\/17506121311315391","article-title":"Physician medicare fraud: characteristics and consequences","volume":"7","author":"Pande","year":"2013","journal-title":"International Journal of Pharmaceutical and Healthcare Marketing"},{"issue":"1","key":"10.3233\/IDA-184415_ref68","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1186\/2047-2501-2-3","article-title":"Big data analytics in healthcare: promise and potential","volume":"2","author":"Raghupathi","year":"2014","journal-title":"Health Information Science and Systems"},{"key":"10.3233\/IDA-184415_ref69","doi-asserted-by":"crossref","unstructured":"A.K. Rastogi, N. Narang and Z.A. Siddiqui, 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, ACM, 2018, p. 14.","DOI":"10.1145\/3170521.3170535"},{"key":"10.3233\/IDA-184415_ref71","doi-asserted-by":"crossref","unstructured":"S. Sadiq, Y. Tao, Y. Yan and M.-L. Shyu, Mining anomalies in medicare big data using patient rule induction method, in: Multimedia Big Data (BigMM), 2017 IEEE Third International Conference on, IEEE, 2017, pp. 185\u2013192.","DOI":"10.1109\/BigMM.2017.56"},{"key":"10.3233\/IDA-184415_ref72","doi-asserted-by":"crossref","unstructured":"C. Seiffert, T.M. Khoshgoftaar, J. Van Hulse and A. Napolitano, Mining data with rare events: a case study, in: Tools with Artificial Intelligence, 2007. ICTAI 2007. 19th IEEE International Conference on, IEEE, Vol. 2, 2007, pp. 132\u2013139.","DOI":"10.1109\/ICTAI.2007.71"},{"issue":"12","key":"10.3233\/IDA-184415_ref74","doi-asserted-by":"crossref","first-page":"3347","DOI":"10.1109\/TKDE.2015.2453171","article-title":"Rankrc: large-scale nonlinear rare class ranking","volume":"27","author":"Tayal","year":"2015","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10.3233\/IDA-184415_ref75","doi-asserted-by":"crossref","first-page":"99","DOI":"10.2307\/3001913","article-title":"Comparing individual means in the analysis of variance","author":"Tukey","year":"1949","journal-title":"Biometrics"},{"key":"10.3233\/IDA-184415_ref76","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1016\/j.accinf.2016.04.001","article-title":"Outlier detection in healthcare fraud: a case study in the medicaid dental domain","volume":"21","author":"van Capelleveen","year":"2016","journal-title":"International Journal of Accounting Information Systems"},{"issue":"12","key":"10.3233\/IDA-184415_ref77","doi-asserted-by":"crossref","first-page":"1513","DOI":"10.1016\/j.datak.2009.08.005","article-title":"Knowledge discovery from imbalanced and noisy data","volume":"68","author":"Van Hulse","year":"2009","journal-title":"Data & Knowledge Engineering"},{"key":"10.3233\/IDA-184415_ref78","doi-asserted-by":"crossref","unstructured":"J. Van Hulse, T.M. Khoshgoftaar and A. Napolitano, Experimental perspectives on learning from imbalanced data, in: Proceedings of the 24th International Conference on Machine Learning, ACM, 2007, pp. 935\u2013942.","DOI":"10.1145\/1273496.1273614"},{"issue":"6","key":"10.3233\/IDA-184415_ref79","first-page":"4175","article-title":"A comprehensive study of healthcare fraud detection based on machine learning","volume":"13","author":"Waghade","year":"2018","journal-title":"International Journal of Applied Engineering Research"},{"issue":"1","key":"10.3233\/IDA-184415_ref80","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1145\/1007730.1007734","article-title":"Mining with rarity: a unifying framework","volume":"6","author":"Weiss","year":"2004","journal-title":"ACM Sigkdd Explorations Newsletter"},{"key":"10.3233\/IDA-184415_ref81","unstructured":"M. Zaharia, M. Chowdhury, T. Das, A. Dave, J. Ma, M. McCauley, M.J. Franklin, S. Shenker and I. Stoica, Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing, in: Proceedings of the 9th USENIX Conference on Networked Systems Design and Implementation, USENIX Association, 2012, pp. 2\u20132."},{"issue":"11","key":"10.3233\/IDA-184415_ref82","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1145\/2934664","article-title":"Apache spark: a unified engine for big data processing","volume":"59","author":"Zaharia","year":"2016","journal-title":"Communications of the ACM"},{"issue":"3","key":"10.3233\/IDA-184415_ref83","doi-asserted-by":"crossref","first-page":"1009","DOI":"10.1007\/s13042-015-0478-7","article-title":"The classification of imbalanced large data sets based on mapreduce and ensemble of elm classifiers","volume":"8","author":"Zhai","year":"2017","journal-title":"International Journal of Machine Learning and Cybernetics"},{"key":"10.3233\/IDA-184415_ref84","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1016\/j.patcog.2016.08.023","article-title":"Krnn: k rare-class nearest neighbour classification","volume":"62","author":"Zhang","year":"2017","journal-title":"Pattern Recognition"}],"container-title":["Intelligent Data Analysis"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/IDA-184415","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:18:37Z","timestamp":1777454317000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/IDA-184415"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2,18]]},"references-count":64,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.3233\/ida-184415","relation":{},"ISSN":["1088-467X","1571-4128"],"issn-type":[{"value":"1088-467X","type":"print"},{"value":"1571-4128","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,2,18]]}}}