{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:01:11Z","timestamp":1760709671893,"version":"3.37.3"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2018,8,1]],"date-time":"2018-08-01T00:00:00Z","timestamp":1533081600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Data Sci Anal"],"published-print":{"date-parts":[[2019,6]]},"DOI":"10.1007\/s41060-018-0146-6","type":"journal-article","created":{"date-parts":[[2018,8,1]],"date-time":"2018-08-01T13:07:11Z","timestamp":1533128831000},"page":"259-276","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Classification and regression using augmented trees"],"prefix":"10.1007","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4865-7218","authenticated-orcid":false,"given":"Rajiv","family":"Sambasivan","sequence":"first","affiliation":[]},{"given":"Sourish","family":"Das","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,8,1]]},"reference":[{"key":"146_CR1","doi-asserted-by":"crossref","unstructured":"Bach, F.R., Lanckriet, G.R., Jordan, M.I.: Multiple kernel learning, conic duality, and the SMO algorithm. In: Proceedings of the Twenty-First International Conference on Machine Learning, p. 6. ACM (2004)","DOI":"10.1145\/1015330.1015424"},{"key":"146_CR2","doi-asserted-by":"crossref","unstructured":"Boser, B., Guyon, I., Vapnik, V.N.: A training algorithm for optimal margin classifiers. In: 5th Annual ACM Workshop on COLT, pp. 144\u2013152. ACM Press, Pittsburgh (1992)","DOI":"10.1145\/130385.130401"},{"key":"146_CR3","doi-asserted-by":"crossref","unstructured":"Bousquet, O., Boucheron, S., Lugosi, G.: Introduction to statistical learning theory. In: Bousquet, O., von Luxburg, U., R\u00e4tsch, G. (eds.) Advanced Lectures on Machine Learning, pp. 169\u2013207. Springer (2004)","DOI":"10.1007\/978-3-540-28650-9_8"},{"issue":"1","key":"146_CR4","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. 45(1), 5\u201332 (2001)","journal-title":"Mach. Learn."},{"key":"146_CR5","volume-title":"Classification and Regression Trees","author":"L Breiman","year":"1984","unstructured":"Breiman, L., Friedman, J., Stone, C.J., Olshen, R.A.: Classification and Regression Trees. CRC Press, Boca Raton (1984)"},{"issue":"4","key":"146_CR6","doi-asserted-by":"publisher","first-page":"1208","DOI":"10.1016\/j.csda.2008.10.033","volume":"53","author":"B Briand","year":"2009","unstructured":"Briand, B., Ducharme, G.R., Parache, V., Mercat-Rommens, C.: A similarity measure to assess the stability of classification trees. Comput. Stat. Data Anal. 53(4), 1208\u20131217 (2009)","journal-title":"Comput. Stat. Data Anal."},{"key":"146_CR7","unstructured":"Brochu, E., Cora, V.M., De Freitas, N.: A tutorial on Bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning. arXiv preprint arXiv:1012.2599 (2010)"},{"key":"146_CR8","doi-asserted-by":"crossref","unstructured":"Caruana, R., Lou, Y., Gehrke, J., Koch, P., Sturm, M., Elhadad, N.: Intelligible models for healthcare: predicting pneumonia risk and hospital 30-day readmission. In: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1721\u20131730. ACM (2015)","DOI":"10.1145\/2783258.2788613"},{"key":"146_CR9","doi-asserted-by":"crossref","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, pp. 785\u2013794. ACM (2016)","DOI":"10.1145\/2939672.2939785"},{"issue":"1","key":"146_CR10","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1023\/A:1008980332240","volume":"10","author":"H Chipman","year":"2000","unstructured":"Chipman, H., McCulloch, R.E.: Hierarchical priors for bayesian cart shrinkage. Stat. Comput. 10(1), 17\u201324 (2000)","journal-title":"Stat. Comput."},{"issue":"1","key":"146_CR11","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1023\/A:1013916107446","volume":"48","author":"HA Chipman","year":"2002","unstructured":"Chipman, H.A., George, E.I., McCulloch, R.E.: Bayesian treed models. Mach. Learn. 48(1), 299\u2013320 (2002)","journal-title":"Mach. Learn."},{"key":"146_CR12","volume-title":"Generalized Linear Models and Beyond: An Innovative Approach from Bayesian Perspective","author":"S Das","year":"2008","unstructured":"Das, S.: Generalized Linear Models and Beyond: An Innovative Approach from Bayesian Perspective. University of Connecticut, Storrs (2008)"},{"issue":"3","key":"146_CR13","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1198\/000313006X128150","volume":"60","author":"S Das","year":"2006","unstructured":"Das, S., Dey, D.K.: On bayesian analysis of generalized linear models using the Jacobian technique. Am. Stat. 60(3), 264\u2013268 (2006)","journal-title":"Am. Stat."},{"issue":"19","key":"146_CR14","doi-asserted-by":"publisher","first-page":"1492","DOI":"10.1016\/j.spl.2010.05.018","volume":"80","author":"S Das","year":"2010","unstructured":"Das, S., Dey, D.K.: On bayesian inference for generalized multivariate gamma distribution. Stat. Probab. Lett. 80(19), 1492\u20131499 (2010)","journal-title":"Stat. Probab. Lett."},{"key":"146_CR15","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1007\/s11009-011-9255-6","volume":"15","author":"S Das","year":"2013","unstructured":"Das, S., Dey, D.K.: On dynamic generalized linear models with applications. Methodol. Comput. Appl. Probab. 15, 407\u2013421 (2013)","journal-title":"Methodol. Comput. Appl. Probab."},{"issue":"11","key":"146_CR16","doi-asserted-by":"crossref","first-page":"1250","DOI":"10.1002\/sim.3878","volume":"29","author":"S Das","year":"2010","unstructured":"Das, S., Harel, O., Dey, D.K., Covault, J., Kranzler, H.R.: Analysis of extreme drinking in patients with alcohol dependence using Pareto regression. Stat. Med. 29(11), 1250\u20131258 (2010)","journal-title":"Stat. Med."},{"key":"146_CR17","doi-asserted-by":"publisher","unstructured":"Das, S., Roy, S., Sambasivan, R.: Fast Gaussian process regression for big data. Big Data Research (2018). https:\/\/doi.org\/10.1016\/j.bdr.2018.06.002 . http:\/\/www.sciencedirect.com\/science\/article\/pii\/S2214579617301909","DOI":"10.1016\/j.bdr.2018.06.002"},{"key":"146_CR18","volume-title":"The Elements of Statistical Learning. Springer Series in Statistics","author":"J Friedman","year":"2001","unstructured":"Friedman, J., Hastie, T., Tibshirani, R.: The Elements of Statistical Learning. Springer Series in Statistics, vol. 1. Springer, New York (2001)"},{"key":"146_CR19","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511790942","volume-title":"Data Analysis Using Regression and Multilevel\/Hierarchical Models","author":"A Gelman","year":"2006","unstructured":"Gelman, A., Hill, J.: Data Analysis Using Regression and Multilevel\/Hierarchical Models. Cambridge University Press, Cambridge (2006)"},{"issue":"1","key":"146_CR20","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s10994-006-6226-1","volume":"63","author":"P Geurts","year":"2006","unstructured":"Geurts, P., Ernst, D., Wehenkel, L.: Extremely randomized trees. Mach. Learn. 63(1), 3\u201342 (2006)","journal-title":"Mach. Learn."},{"key":"146_CR21","unstructured":"Gini, C.: Variability and mutability, contribution to the study of statistical distributions and relations. studieconomico-giuridici della r. universita de cagliari (1912). Reviewed in: Light, R.J., Margolin, B.H.: An analysis of variance for categorical data. J. Am. Stat. Assoc. 66, 534\u2013544 (1971)"},{"issue":"483","key":"146_CR22","doi-asserted-by":"publisher","first-page":"1119","DOI":"10.1198\/016214508000000689","volume":"103","author":"RB Gramacy","year":"2008","unstructured":"Gramacy, R.B., Lee, H.K.H.: Bayesian treed Gaussian process models with an application to computer modeling. J. Am. Stat. Assoc. 103(483), 1119\u20131130 (2008)","journal-title":"J. Am. Stat. Assoc."},{"key":"146_CR23","unstructured":"Hoeffding, W.: Probability inequalities for sums of bounded random variables. J. Am. Stat. Assoc. 58(301), 13\u201330 (1963). http:\/\/www.jstor.org\/stable\/2282952"},{"key":"146_CR24","unstructured":"kaggle: The home of data science and machine learning. http:\/\/www.kaggle.com\/"},{"key":"146_CR25","unstructured":"kaggle: The playground (2016). http:\/\/blog.kaggle.com\/2013\/09\/25\/the-playground\/"},{"key":"146_CR26","unstructured":"Karali\u010d, A.: Employing linear regression in regression tree leaves. In: Proceedings of the 10th European Conference on Artificial Intelligence, pp. 440\u2013441. Wiley (1992)"},{"key":"146_CR27","unstructured":"Kohavi, R.: Scaling up the accuracy of Naive\u2013Bayes classifiers: a decision-tree hybrid. In: KDD, vol. 96, pp. 202\u2013207 (1996)"},{"key":"146_CR28","doi-asserted-by":"crossref","first-page":"619","DOI":"10.1111\/j.2517-6161.1996.tb02105.x","volume":"58","author":"Y Lee","year":"1996","unstructured":"Lee, Y., Nelder, J.A.: Hierarchical generalized linear models. J. R. Stat. Soc. Ser. B (Methodol.) 58, 619\u2013678 (1996)","journal-title":"J. R. Stat. Soc. Ser. B (Methodol.)"},{"key":"146_CR29","unstructured":"Lichman, M.: UCI machine learning repository (2016). http:\/\/archive.ics.uci.edu\/ml"},{"key":"146_CR30","unstructured":"Liu, F.T., Ting, K.M., Zhou, Z.H.: Isolation forest. In: Eighth IEEE International Conference on Data Mining, 2008. ICDM\u201908, pp. 413\u2013422. IEEE (2008)"},{"key":"146_CR31","volume-title":"A Probabilistic Theory of Pattern Recognition. Springer Series in Statistics","author":"LG Luc\u00a0Devroye","year":"1996","unstructured":"Luc\u00a0Devroye, L.G.: A Probabilistic Theory of Pattern Recognition. Springer Series in Statistics, vol. 1. Springer, New York (1996)"},{"key":"146_CR32","unstructured":"Nowak, R.: Introduction to classification and regression (2009). http:\/\/nowak.ece.wisc.edu\/SLT09\/lecture2.pdf"},{"key":"146_CR33","volume-title":"C4.5: Programs for Machine Learning","author":"JR Quinlan","year":"2014","unstructured":"Quinlan, J.R.: C4.5: Programs for Machine Learning. Elsevier, Amsterdam (2014)"},{"key":"146_CR34","doi-asserted-by":"crossref","unstructured":"Sambasivan, R., Das, S.: Big data regression using tree based segmentation. In: Proceedings of the 14th IEEE India Council International Conference. IEEE (2017)","DOI":"10.1109\/INDICON.2017.8488137"},{"issue":"3","key":"146_CR35","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1214\/10-STS330","volume":"25","author":"G Shmueli","year":"2010","unstructured":"Shmueli, G., et al.: To explain or to predict? Stat. Sci. 25(3), 289\u2013310 (2010)","journal-title":"Stat. Sci."},{"key":"146_CR36","unstructured":"Snoek, J., Larochelle, H., Adams, R.P.: Practical Bayesian optimization of machine learning algorithms. In: Proceedings of the 25th International Conference on Neural Information Processing Systems - Volume 2. NIPS\u201912, Lake Tahoe, Nevada, pp.\u00a02951\u20132959. Curran Associates Inc., USA (2012)"},{"key":"146_CR37","unstructured":"Targo, L.: Large regression datasets (2016). http:\/\/www.transtats.bts.gov\/DL_SelectFields.asp?Table_ID=236"},{"key":"146_CR38","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","volume":"58","author":"R Tibshirani","year":"1996","unstructured":"Tibshirani, R.: Regression shrinkage and selection via the lasso. J. R. Stat. Soc. Ser B (Methodol.) 58, 267\u2013288 (1996)","journal-title":"J. R. Stat. Soc. Ser B (Methodol.)"},{"key":"146_CR39","first-page":"385","volume":"97","author":"L Torgo","year":"1997","unstructured":"Torgo, L.: Functional models for regression tree leaves. ICML 97, 385\u2013393 (1997)","journal-title":"ICML"},{"issue":"2","key":"146_CR40","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1080\/10255810305042","volume":"5","author":"K Tumer","year":"2003","unstructured":"Tumer, K., Ghosh, J.: Bayes error rate estimation using classifier ensembles. Int. J. Smart Eng. Syst. Des. 5(2), 95\u2013109 (2003)","journal-title":"Int. J. Smart Eng. Syst. Des."},{"key":"146_CR41","unstructured":"USDOT, B.: Rita airline delay data download (2016). http:\/\/www.transtats.bts.gov\/DL_SelectFields.asp?Table_ID=236"},{"key":"146_CR42","unstructured":"Waterhouse, S., MacKay, D., Robinson, T.: Bayesian methods for mixtures of experts. In: Advances in Neural Information Processing Systems, pp. 351\u2013357. MIT Press (1996)"},{"issue":"3","key":"146_CR43","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1109\/TKDE.2006.46","volume":"18","author":"H Xiong","year":"2006","unstructured":"Xiong, H., Pandey, G., Steinbach, M., Kumar, V.: Enhancing data analysis with noise removal. IEEE Trans. Knowl. Data Eng. 18(3), 304\u2013319 (2006)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"146_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, T.: Solving large scale linear prediction problems using stochastic gradient descent algorithms. In: Proceedings of the Twenty-First International Conference on Machine Learning, p. 116. ACM (2004)","DOI":"10.1145\/1015330.1015332"},{"issue":"2","key":"146_CR45","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1111\/j.1467-9868.2005.00503.x","volume":"67","author":"H Zou","year":"2005","unstructured":"Zou, H., Hastie, T.: Regularization and variable selection via the elastic net. J. R. Stat. Soc. Ser. B (Stat. Methodol.) 67(2), 301\u2013320 (2005)","journal-title":"J. R. Stat. Soc. Ser. B (Stat. Methodol.)"}],"container-title":["International Journal of Data Science and Analytics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s41060-018-0146-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s41060-018-0146-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s41060-018-0146-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T21:22:13Z","timestamp":1720473733000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s41060-018-0146-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8,1]]},"references-count":45,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2019,6]]}},"alternative-id":["146"],"URL":"https:\/\/doi.org\/10.1007\/s41060-018-0146-6","relation":{},"ISSN":["2364-415X","2364-4168"],"issn-type":[{"type":"print","value":"2364-415X"},{"type":"electronic","value":"2364-4168"}],"subject":[],"published":{"date-parts":[[2018,8,1]]},"assertion":[{"value":"19 January 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 July 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 August 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"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"}}]}}