{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T07:52:41Z","timestamp":1762329161985,"version":"build-2065373602"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,10,18]],"date-time":"2025-10-18T00:00:00Z","timestamp":1760745600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,18]],"date-time":"2025-10-18T00:00:00Z","timestamp":1760745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Stat Comput"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s11222-025-10746-z","type":"journal-article","created":{"date-parts":[[2025,10,18]],"date-time":"2025-10-18T02:37:11Z","timestamp":1760755031000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Finding Interpretable Data Pockets in Tabular Data"],"prefix":"10.1007","volume":"35","author":[{"given":"Tushar","family":"Ojha","sequence":"first","affiliation":[]},{"given":"Don","family":"Hush","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,18]]},"reference":[{"issue":"1","key":"10746_CR1","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1002\/widm.1144","volume":"5","author":"M Atzmueller","year":"2015","unstructured":"Atzmueller, M.: Subgroup discovery. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery 5(1), 35\u201349 (2015). https:\/\/doi.org\/10.1002\/widm.1144","journal-title":"Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery"},{"key":"10746_CR2","doi-asserted-by":"crossref","unstructured":"Bay, SD.: Multivariate discretization of continuous variables for set mining. In: Proceedings of the sixth ACM SIGKDD international conference on Knowledge discovery and data mining, pp 315\u2013319 (2000)","DOI":"10.1145\/347090.347159"},{"key":"10746_CR3","doi-asserted-by":"crossref","unstructured":"Castanho, E.N., Aidos, H., Madeira, S.C.: Biclustering data analysis: a comprehensive survey. Brief Bioinform 25(4) (2024)","DOI":"10.1093\/bib\/bbae342"},{"key":"10746_CR4","doi-asserted-by":"publisher","unstructured":"Chong, I.G., Jun, C.H.: Flexible patient rule induction method for optimizing process variables in discrete type. Expert Syst. Appl. 34(4), 3014\u20133020 (2008). https:\/\/doi.org\/10.1016\/j.eswa.2007.05.04","DOI":"10.1016\/j.eswa.2007.05.04"},{"key":"10746_CR5","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1016\/j.envsoft.2013.05.013","volume":"48","author":"S Dalal","year":"2013","unstructured":"Dalal, S., Han, B., Lempert, R., et al.: Improving scenario discovery using orthogonal rotations. Environmental Modelling & Software 48, 49\u201364 (2013). https:\/\/doi.org\/10.1016\/j.envsoft.2013.05.013","journal-title":"Environmental Modelling & Software"},{"issue":"4","key":"10746_CR6","doi-asserted-by":"publisher","first-page":"900","DOI":"10.1198\/jcgs.2010.09029","volume":"19","author":"JE Dazard","year":"2010","unstructured":"Dazard, J.E., Rao, J.S.: Local sparse bump hunting. J. Comput. Graph. Stat. 19(4), 900\u2013929 (2010). https:\/\/doi.org\/10.1198\/jcgs.2010.09029","journal-title":"J. Comput. Graph. Stat."},{"key":"10746_CR7","doi-asserted-by":"publisher","unstructured":"D\u00edaz-Pach\u00f3n, D.A., Dazard, J.E., Rao, J.S.: Unsupervised Bump Hunting Using Principal Components, Springer International Publishing, Cham, pp 325\u2013345 (2017). https:\/\/doi.org\/10.1007\/978-3-319-41573-4_16","DOI":"10.1007\/978-3-319-41573-4_16"},{"issue":"2","key":"10746_CR8","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1002\/asmb.2430","volume":"35","author":"DA D\u00edaz-Pach\u00f3n","year":"2019","unstructured":"D\u00edaz-Pach\u00f3n, D.A., S\u00e1enz, J.P., Rao, J.S., et al.: Mode hunting through active information. Appl. Stoch. Model. Bus. Ind. 35(2), 376\u2013393 (2019). https:\/\/doi.org\/10.1002\/asmb.2430","journal-title":"Appl. Stoch. Model. Bus. Ind."},{"key":"10746_CR9","doi-asserted-by":"publisher","unstructured":"External-Kaggle:Diabetes Health Indicators Dataset. UCI Machine Learning Repository, (2023) https:\/\/doi.org\/10.24432\/C53919","DOI":"10.24432\/C53919"},{"key":"10746_CR10","doi-asserted-by":"crossref","unstructured":"Ferri, F.J., P. P, Hatef M, et al.: Comparative study of techniques for large-scale feature selection. Mach. Intelligence Pattern Recogn. 16, 403\u2013413 (1994)","DOI":"10.1016\/B978-0-444-81892-8.50040-7"},{"issue":"2","key":"10746_CR11","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1023\/A:1008894516817","volume":"9","author":"JH Friedman","year":"1999","unstructured":"Friedman, J.H., Fisher, N.I.: Bump hunting in high-dimensional data. Stat. Comput. 9(2), 123\u2013143 (1999). https:\/\/doi.org\/10.1023\/A:1008894516817","journal-title":"Stat. Comput."},{"key":"10746_CR12","volume-title":"Computers and Intractability: A Guide to the Theory of NP-Completeness","author":"MR Garey","year":"1979","unstructured":"Garey, M.R., Johnson, D.S.: Computers and Intractability: A Guide to the Theory of NP-Completeness. W. H, Freeman and Company, New York (1979)"},{"key":"10746_CR13","unstructured":"Hadka, D.: Patient Rule Induction Method for Python. Github, (2024). https:\/\/github.com\/Project-Platypus\/PRIM"},{"issue":"15","key":"10746_CR14","doi-asserted-by":"publisher","first-page":"2864","DOI":"10.1080\/02664763.2018.1444152","volume":"45","author":"A Hapfelmeier","year":"2018","unstructured":"Hapfelmeier, A., Ulm, K., Haller, B.: Subgroup identification by recursive segmentation. J. Appl. Stat. 45(15), 2864\u20132887 (2018). https:\/\/doi.org\/10.1080\/02664763.2018.1444152","journal-title":"J. Appl. Stat."},{"key":"10746_CR15","doi-asserted-by":"publisher","unstructured":"Hastie, T., Tibshirani, R., Friedman, J.H.: The elements of statistical learning: data mining, inference, and prediction, vol 2. Springer, New York, NY, (2009). https:\/\/doi.org\/10.1007\/978-0-387-84858-7","DOI":"10.1007\/978-0-387-84858-7"},{"key":"10746_CR16","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1016\/j.envsoft.2017.06.054","volume":"96","author":"JH Kwakkel","year":"2017","unstructured":"Kwakkel, J.H.: The exploratory modeling workbench: An open source toolkit for exploratory modeling, scenario discovery, and (multi-objective) robust decision making. Environmental Modelling & Software 96, 239\u2013250 (2017). https:\/\/doi.org\/10.1016\/j.envsoft.2017.06.054","journal-title":"Environmental Modelling & Software"},{"key":"10746_CR17","volume-title":"Comparing algorithms for scenario discovery","author":"RJ Lempert","year":"2008","unstructured":"Lempert, R.J., Bryant, B.P., Bankes, S.C.: Comparing algorithms for scenario discovery. RAND, Santa Monica, CA (2008)"},{"key":"10746_CR18","doi-asserted-by":"publisher","unstructured":"Letham, B., Rudin, C., McCormick, T.H., et al.: Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model. The Annals of Applied Statistics 9(3), 1350\u20131371 (2015). https:\/\/doi.org\/10.1214\/15-AOAS848","DOI":"10.1214\/15-AOAS848"},{"issue":"5","key":"10746_CR19","volume":"9","author":"WY Loh","year":"2019","unstructured":"Loh, W.Y., Cao, L., Zhou, P.: Subgroup identification for precision medicine: A comparative review of 13 methods. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery 9(5), e1326 (2019)","journal-title":"Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery"},{"issue":"1","key":"10746_CR20","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1109\/TCBB.2004.2","volume":"1","author":"S Madeira","year":"2004","unstructured":"Madeira, S., Oliveira, A.: Biclustering algorithms for biological data analysis: a survey. IEEE\/ACM Trans. Comput. Biol. Bioinf. 1(1), 24\u201345 (2004). https:\/\/doi.org\/10.1109\/TCBB.2004.2","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinf."},{"issue":"1","key":"10746_CR21","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 3(1), 27\u201332 (2001). https:\/\/doi.org\/10.1145\/507533.507538","journal-title":"SIGKDD Explor Newsl"},{"key":"10746_CR22","doi-asserted-by":"publisher","unstructured":"Moro, S., Cortez, P., Rita, P.: Bank Marketing. UCI Machine Learning Repository, (2014). https:\/\/doi.org\/10.24432\/C5K306","DOI":"10.24432\/C5K306"},{"issue":"8","key":"10746_CR23","doi-asserted-by":"publisher","first-page":"873","DOI":"10.1002\/(SICI)1097-0258(19980430)17:8<873::AID-SIM779>3.0.CO;2-I","volume":"17","author":"RG Newcombe","year":"1998","unstructured":"Newcombe, R.G.: Interval estimation for the difference between independent proportions: comparison of eleven methods. Stat. Med. 17(8), 873\u2013890 (1998). https:\/\/doi.org\/10.1002\/(SICI)1097-0258(19980430)17:8<873::AID-SIM779>3.0.CO;2-I","journal-title":"Stat. Med."},{"key":"10746_CR24","doi-asserted-by":"publisher","first-page":"5271091","DOI":"10.1155\/2017\/5271091","volume":"1","author":"A Ott","year":"2017","unstructured":"Ott, A.: Hapfelmeier A (2017) Nonparametric subgroup identification by prim and cart: A simulation and application study. Comput. Math. Methods Med. 1, 5271091 (2017). https:\/\/doi.org\/10.1155\/2017\/5271091","journal-title":"Comput. Math. Methods Med."},{"key":"10746_CR25","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., Varoquaux, G., Gramfort, A., et al.: Scikit-learn: Machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)","journal-title":"J. Mach. Learn. Res."},{"issue":"3","key":"10746_CR26","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1016\/j.jmva.2009.08.010","volume":"101","author":"W Polonik","year":"2010","unstructured":"Polonik, W., Wang, Z.: Prim analysis. J. Multivar. Anal. 101(3), 525\u2013540 (2010). https:\/\/doi.org\/10.1016\/j.jmva.2009.08.010","journal-title":"J. Multivar. Anal."},{"issue":"116","key":"10746_CR27","doi-asserted-by":"publisher","first-page":"1119","DOI":"10.1016\/0167-8655(94)90127-9","volume":"115","author":"P Pudil","year":"1994","unstructured":"Pudil, P., Novovicova, J., Kittler, J.: Floating search methods in feature selection. Pattern Recogn. Lett. 115(116), 1119\u20131125 (1994)","journal-title":"Pattern Recogn. Lett."},{"key":"10746_CR28","doi-asserted-by":"publisher","unstructured":"Rudin, C., Chen, C., Chen, Z., et\u00a0al.: Interpretable machine learning: Fundamental principles and 10 grand challenges. Statistics Surveys 16(none):1 \u2013 85 (2022). https:\/\/doi.org\/10.1214\/21-SS133","DOI":"10.1214\/21-SS133"},{"issue":"12","key":"10746_CR29","doi-asserted-by":"publisher","first-page":"1213","DOI":"10.1145\/7902.7906","volume":"29","author":"C Stanfill","year":"1986","unstructured":"Stanfill, C., Waltz, D.: Toward memory-based reasoning. Commun. ACM 29(12), 1213\u20131228 (1986)","journal-title":"Commun. ACM"},{"key":"10746_CR30","volume-title":"Bayesian model-assisted prim algorithm","author":"L Wu","year":"2003","unstructured":"Wu, L., Chipman, H.: Bayesian model-assisted prim algorithm. Tech. rep, Technical Report (2003)"},{"issue":"4","key":"10746_CR31","doi-asserted-by":"publisher","first-page":"1450","DOI":"10.1093\/bib\/bby014","volume":"20","author":"J Xie","year":"2018","unstructured":"Xie, J., Ma, A., Fennell, A., et al.: It is time to apply biclustering: a comprehensive review of biclustering applications in biological and biomedical data. Brief. Bioinform. 20(4), 1450\u20131465 (2018). https:\/\/doi.org\/10.1093\/bib\/bby014","journal-title":"Brief. Bioinform."},{"issue":"4","key":"10746_CR32","doi-asserted-by":"publisher","first-page":"1205","DOI":"10.1016\/j.cie.2008.07.012","volume":"56","author":"G Xu","year":"2009","unstructured":"Xu, G., Papageorgiou, L.G.: A mixed integer optimisation model for data classification. Computers & Industrial Engineering 56(4), 1205\u20131215 (2009). https:\/\/doi.org\/10.1016\/j.cie.2008.07.012","journal-title":"Computers & Industrial Engineering"}],"container-title":["Statistics and Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11222-025-10746-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11222-025-10746-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11222-025-10746-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T07:18:07Z","timestamp":1762327087000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11222-025-10746-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,18]]},"references-count":32,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["10746"],"URL":"https:\/\/doi.org\/10.1007\/s11222-025-10746-z","relation":{},"ISSN":["0960-3174","1573-1375"],"issn-type":[{"type":"print","value":"0960-3174"},{"type":"electronic","value":"1573-1375"}],"subject":[],"published":{"date-parts":[[2025,10,18]]},"assertion":[{"value":"16 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The corresponding author is employed by the University of New Mexico.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Employment"}},{"value":"The authors declare they have no financial interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Financial Interests"}},{"value":"The authors declare they have no non-financial interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Non-financial Interests"}}],"article-number":"214"}}