{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T23:01:55Z","timestamp":1770332515086,"version":"3.49.0"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2021,5,8]],"date-time":"2021-05-08T00:00:00Z","timestamp":1620432000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,5,8]],"date-time":"2021-05-08T00:00:00Z","timestamp":1620432000000},"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":["SN COMPUT. SCI."],"published-print":{"date-parts":[[2021,7]]},"DOI":"10.1007\/s42979-021-00655-z","type":"journal-article","created":{"date-parts":[[2021,5,8]],"date-time":"2021-05-08T15:02:27Z","timestamp":1620486147000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":61,"title":["Gradient Boosted Decision Tree Algorithms for Medicare Fraud Detection"],"prefix":"10.1007","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0699-3042","authenticated-orcid":false,"given":"John T.","family":"Hancock","sequence":"first","affiliation":[]},{"given":"Taghi M.","family":"Khoshgoftaar","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,5,8]]},"reference":[{"key":"655_CR1","unstructured":"Medicare provider utilization and payment data: Physician and other supplier. 2019. https:\/\/www.cms.gov\/Research-Statistics-Data-and-Systems\/Statistics-Trends-and-Reports\/Medicare-Provider-Charge-Data\/Physician-and-Other-Supplier. Accessed 14 Mar 2021."},{"key":"655_CR2","unstructured":"Python package training parameters. 2020. https:\/\/catboost.ai\/docs\/concepts\/python-reference_parameters-list.html#python-reference_parameters-list. Accessed 15 Mar 2021"},{"key":"655_CR3","unstructured":"Transforming categorical features to numerical features. 2020. https:\/\/catboost.ai\/docs\/concepts\/algorithm-main-stages_cat-to-numberic.html#algorithm-main-stages_cat-to-numberic. Accessed 16 Mar 2021."},{"key":"655_CR4","unstructured":"Bagdoyan SJ. Testimony before the subcommittee on oversight, committee on ways and means, house of representatives. 2018. https:\/\/www.gao.gov\/assets\/700\/693156.pdf. Accessed 19 Mar 2021."},{"key":"655_CR5","doi-asserted-by":"publisher","unstructured":"Bauder RA, da Rosa R, Khoshgoftaar TM. Identifying medicare provider fraud with unsupervised machine learning. In: 2018 IEEE International conference on information reuse and integration (IRI); 2018. pp. 285\u2013292 . https:\/\/doi.org\/10.1109\/IRI.2018.00051.","DOI":"10.1109\/IRI.2018.00051"},{"issue":"10","key":"655_CR6","first-page":"27","volume":"3","author":"M Bekkar","year":"2013","unstructured":"Bekkar M, Djemaa HK, Alitouche TA. Evaluation measures for models assessment over imbalanced data sets. J Inf Eng Appl. 2013;3(10):27\u201338.","journal-title":"J Inf Eng Appl."},{"key":"655_CR7","doi-asserted-by":"publisher","unstructured":"Branting LK, Reeder F, Gold J, Champney T. Graph analytics for healthcare fraud risk estimation. In: 2016 IEEE\/ACM international conference on advances in social networks analysis and mining (ASONAM); 2016, pp. 845\u2013851 . https:\/\/doi.org\/10.1109\/ASONAM.2016.7752336.","DOI":"10.1109\/ASONAM.2016.7752336"},{"issue":"1","key":"655_CR8","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."},{"key":"655_CR9","unstructured":"Centers for Medicare & Medicaid Services: Get started with medicare. [Online]. https:\/\/www.medicare.gov\/sign-up-change-plans\/get-started-with-medicare. Accessed 16 Mar 2021.."},{"key":"655_CR10","unstructured":"Centers For Medicare & Medicaid Services: Trustees report & trust funds. 2018. https:\/\/www.cms.gov\/Research-Statistics-Data-and-Systems\/Statistics-Trends-and-Reports\/ReportsTrustFunds\/index.html. Accessed 16 Mar 2021."},{"key":"655_CR11","doi-asserted-by":"publisher","unstructured":"Chen T, Guestrin C. Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining\u2014KDD \u201916 (2016). https:\/\/doi.org\/10.1145\/2939672.2939785.","DOI":"10.1145\/2939672.2939785"},{"key":"655_CR12","unstructured":"CMS Office of Enterprise Data and Analytics: Medicare fee-for-service provider utilization & payment data physician and other supplier. 2017. 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. Accessed 14 Mar 2021."},{"key":"655_CR13","unstructured":"CMS Office of Enterprise Data and Analytics: Medicare fee-for service provider utilization & payment datapart d prescriber public use file:a methodological overview. 2020. https:\/\/www.cms.gov\/Research-Statistics-Data-and-Systems\/Statistics-Trends-and-Reports\/Medicare-Provider-Charge-Data\/Downloads\/Prescriber_Methods.pdf. Accessed 16 Mar 2021."},{"issue":"4","key":"655_CR14","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1016\/S0167-9473(01)00065-2","volume":"38","author":"JH Friedman","year":"2002","unstructured":"Friedman JH. Stochastic gradient boosting. Comput Stat Data Anal. 2002;38(4):367\u201378. https:\/\/doi.org\/10.1016\/S0167-9473(01)00065-2.","journal-title":"Comput Stat Data Anal"},{"key":"655_CR15","volume-title":"Deep learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow I, Bengio Y, Courville A. Deep learning. Cambridge: MIT Press; 2016."},{"key":"655_CR16","doi-asserted-by":"crossref","unstructured":"Hancock J, Khoshgoftaar TM. Performance of catboost and xgboost in medicare fraud detection. In: 19th IEEE international conference on machine learning and applications (ICMLA). IEEE 2020.","DOI":"10.1109\/ICMLA51294.2020.00095"},{"key":"655_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-019-0278-0","volume":"7","author":"JT Hancock","year":"2020","unstructured":"Hancock JT, Khoshgoftaar TM. Catboost for big data: an interdisciplinary review. J Big Data. 2020;7:1\u201345.","journal-title":"J Big Data."},{"key":"655_CR18","doi-asserted-by":"crossref","unstructured":"Hancock JT, Khoshgoftaar TM. Medicare fraud detection using catboost. In: 2020 IEEE 21st international conference on information reuse and integration for data science (IRI), pp. 97\u2013103. IEEE Computer Society; 2020.","DOI":"10.1109\/IRI49571.2020.00022"},{"key":"655_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-019-0278-0","volume":"7","author":"JT Hancock","year":"2020","unstructured":"Hancock JT, Khoshgoftaar TM. Survey on categorical data for neural networks. J Big Data. 2020;7:1\u201341.","journal-title":"J Big Data"},{"issue":"1","key":"655_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-019-0181-8","volume":"6","author":"M Herland","year":"2019","unstructured":"Herland M, Bauder RA, Khoshgoftaar TM. The effects of class rarity on the evaluation of supervised healthcare fraud detection models. J Big Data. 2019;6(1):1.","journal-title":"J Big Data"},{"issue":"1","key":"655_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/2196-1115-1-2","volume":"1","author":"M Herland","year":"2014","unstructured":"Herland M, Khoshgoftaar TM, Wald R. A review of data mining using big data in health informatics. J Big data. 2014;1(1):1\u201335.","journal-title":"J Big data"},{"key":"655_CR22","doi-asserted-by":"crossref","unstructured":"Iversen GR, Norpoth H, Norpoth HP. Analysis of variance. 1. Sage; 1987.","DOI":"10.4135\/9781412983327"},{"key":"655_CR23","unstructured":"Ke G, Meng Q, Finley T, Wang T, Chen W, Ma W, Ye Q, Liu TY. Lightgbm: a highly efficient gradient boosting decision tree. In: Guyon I, Luxburg UV, Bengio S, Wallach H, Fergus R, Vishwanathan S, Garnett R (eds) Advances in neural information processing systems, vol. 30, pp. 3146\u20133154. Curran Associates, Inc.; 2017. http:\/\/papers.nips.cc\/paper\/6907-lightgbm-a-highly-efficient-gradient-boosting-decision-tree.pdf. Accessed 12 Mar 2021."},{"key":"655_CR24","volume-title":"Logistic regression","author":"DG Kleinbaum","year":"2002","unstructured":"Kleinbaum DG, Dietz K, Gail M, Klein M, Klein M. Logistic regression. New York: Springer; 2002."},{"key":"655_CR25","first-page":"1","volume":"1","author":"JL Leevy","year":"2020","unstructured":"Leevy JL, Khoshgoftaar TM, Bauder RA. NaeemSeliya: Investigating the relationship between time and predictive model maintenance. J Big Data. 2020;1:1\u201319.","journal-title":"J Big Data."},{"key":"655_CR26","unstructured":"LEIE: Office of inspector general leie downloadable databases. 2017. https:\/\/oig.hhs.gov\/exclusions\/index.asp. Accessed 15 Mar 2021."},{"issue":"1","key":"655_CR27","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1145\/507533.507538","volume":"3","author":"D Micci-Barreca","year":"2001","unstructured":"Micci-Barreca D. A preprocessing scheme for high-cardinality categorical attributes in classification and prediction problems. SIGKDD Explor Newsl. 2001;3(1):27\u201332.","journal-title":"SIGKDD Explor Newsl"},{"issue":"Oct","key":"655_CR28","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, et al. Scikit-learn: machine learning in python. J Mach Learn Res. 2011;12(Oct):2825\u201330.","journal-title":"J Mach Learn Res"},{"key":"655_CR29","unstructured":"Prokhorenkova L, Gusev G, Vorobev A, Dorogush AV, Gulin A. Catboost: unbiased boosting with categorical features. In: Bengio S, Wallach H, Larochelle H, Grauman K, Cesa-Bianchi N, Garnett R (eds) Advances in neural information processing systems, vol. 31, pp. 6638\u20136648. Curran Associates, Inc.; 2018. http:\/\/papers.nips.cc\/paper\/7898-catboost-unbiased-boosting-with-categorical-features.pdf. Accessed 18 Mar 2021."},{"key":"655_CR30","unstructured":"Provost F, Fawcett T. Analysis and visualization of classifier performance: comparison under imprecise class and cost distributions. In: Proc of the 3rd international conference on knowledge discovery and data mining; 1997."},{"key":"655_CR31","doi-asserted-by":"publisher","first-page":"99","DOI":"10.2307\/3001913","volume":"1949","author":"JW Tukey","year":"1949","unstructured":"Tukey JW. Comparing individual means in the analysis of variance. Biometrics 1949;1949:99\u2013114.","journal-title":"Biometrics"}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-021-00655-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-021-00655-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-021-00655-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,6,26]],"date-time":"2021-06-26T20:18:52Z","timestamp":1624738732000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-021-00655-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,8]]},"references-count":31,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,7]]}},"alternative-id":["655"],"URL":"https:\/\/doi.org\/10.1007\/s42979-021-00655-z","relation":{},"ISSN":["2662-995X","2661-8907"],"issn-type":[{"value":"2662-995X","type":"print"},{"value":"2661-8907","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,8]]},"assertion":[{"value":"24 December 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 April 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 May 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"On behalf of all authors, the corresponding author states that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"268"}}