{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T14:45:17Z","timestamp":1782139517548,"version":"3.54.5"},"reference-count":113,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2022,12,14]],"date-time":"2022-12-14T00:00:00Z","timestamp":1670976000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,12,14]],"date-time":"2022-12-14T00:00:00Z","timestamp":1670976000000},"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":["Int J Data Sci Anal"],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1007\/s41060-022-00373-6","type":"journal-article","created":{"date-parts":[[2022,12,14]],"date-time":"2022-12-14T09:03:05Z","timestamp":1671008585000},"page":"225-248","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Stability of filter feature selection methods in data pipelines: a simulation study"],"prefix":"10.1007","volume":"17","author":[{"given":"Roberto","family":"Bertolini","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephen J.","family":"Finch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,12,14]]},"reference":[{"key":"373_CR1","unstructured":"Alelyani, S.: On feature selection stability: a data perspective. Doctoral Dissertation. Arizona State University, Tempe, Arizona (2013)"},{"key":"373_CR2","unstructured":"Alexandro, D.: Aiming for success: evaluating statistical and machine learning methods to predict high school student performance and improve early warning systems. Doctoral Dissertation. University of Connecticut, Storrs, Connecticut (2018)"},{"issue":"1","key":"373_CR3","first-page":"41","volume":"14","author":"T Almutiri","year":"2022","unstructured":"Almutiri, T., Saeed, F.: A hybrid feature selection method combining Gini index and support vector machine with recursive feature elimination for gene expression classification. Int. J. Data Min. Modell. Manag. 14(1), 41\u201362 (2022)","journal-title":"Int. J. Data Min. Modell. Manag."},{"issue":"10","key":"373_CR4","doi-asserted-by":"publisher","first-page":"1964","DOI":"10.1002\/asi.23110","volume":"65","author":"Y Aphinyanaphongs","year":"2014","unstructured":"Aphinyanaphongs, Y., Fu, L.D., Li, Z., Peskin, E.R., Efstathiadis, E., Aliferis, C.F., Statnikov, A.: A comprehensive empirical comparison of modern supervised classification and feature selection methods for text categorization. J Associat. Inform. Sci. Technol. 65(10), 1964\u20131987 (2014)","journal-title":"J Associat. Inform. Sci. Technol."},{"key":"373_CR5","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1016\/j.procs.2021.10.050","volume":"193","author":"IV Barabanova","year":"2021","unstructured":"Barabanova, I.V., Vychuzhanin, P., Nikitin, N.O.: Sensitivity analysis of the composite data-driven pipelines in the automated machine learning. Procedia Comp. Sci. 193, 484\u2013493 (2021)","journal-title":"Procedia Comp. Sci."},{"key":"373_CR6","unstructured":"Belanche, L.A., Gonz\u00e1lez, F.F.: Review and evaluation of feature selection algorithms in synthetic problems. arXiv preprint arXiv:1101.2320 (2011)"},{"issue":"3","key":"373_CR7","first-page":"1","volume":"11","author":"J Berens","year":"2018","unstructured":"Berens, J., Schneider, K., G\u00f6rtz, S., Oster, S., Burghoff, J.: Early detection of students at risk \u2013 predicting student dropouts using administrative student data and machine learning methods. J. Educat. Data Min. 11(3), 1\u201341 (2018)","journal-title":"J. Educat. Data Min."},{"key":"373_CR8","unstructured":"Bertolini, R.: Evaluating performance variability of data pipelines for binary classification with applications to predictive learning analytics. (Doctoral Dissertation). Stony Brook University, Stony Brook, New York (2021)"},{"issue":"3","key":"373_CR9","first-page":"217","volume":"14","author":"R Bertolini","year":"2022","unstructured":"Bertolini, R., Finch, S.J.: Synergistic effects between data corpora properties and machine learning performance in data pipelines. Int. J.Data Min., Modell. Manag. 14(3), 217\u2013233 (2022)","journal-title":"Int. J.Data Min., Modell. Manag."},{"issue":"1","key":"373_CR10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s41239-020-00238-7","volume":"18","author":"R Bertolini","year":"2021","unstructured":"Bertolini, R., Finch, S.J., Nehm, R.H.: Enhancing data pipelines for forecasting student performance: integrating feature selection with cross-validation. Int. J. Educat. Technol. Higher Educat. 18(1), 1\u201323 (2021)","journal-title":"Int. J. Educat. Technol. Higher Educat."},{"key":"373_CR11","first-page":"10067","volume":"3","author":"R Bertolini","year":"2022","unstructured":"Bertolini, R., Finch, S.J., Nehm, R.H.: Quantifying variability in predictions of student performance: examining the impact of bootstrap resampling in data pipelines. Comp. Educat.: Artif. Intell. 3, 10067 (2022)","journal-title":"Comp. Educat.: Artif. Intell."},{"key":"373_CR12","doi-asserted-by":"publisher","DOI":"10.1002\/9781119821908.ch5","author":"N Bharathi","year":"2022","unstructured":"Bharathi, N., Rishiikeshwer, B.S., Shriram, T.A., Santhi, B., Brindha, G.R.: The significance of feature selection techniques in machine learning. Fund. Meth. Mach. Deep. Learn. Algorith. Tool. Appl. (2022). https:\/\/doi.org\/10.1002\/9781119821908.ch5","journal-title":"Fund. Meth. Mach. Deep. Learn. Algorith. Tool. Appl."},{"key":"373_CR13","doi-asserted-by":"crossref","unstructured":"Biswas, S., Wardat, M., Rajan, H.: The Art and Practice of Data Science Pipelines: A Comprehensive Study of Data Science Pipelines In Theory, In-The-Small, and In-The-Large. arXiv preprint arXiv:2112.01590 (2021)","DOI":"10.1145\/3510003.3510057"},{"issue":"3","key":"373_CR14","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/s10115-012-0487-8","volume":"34","author":"V Bol\u00f3n-Canedo","year":"2013","unstructured":"Bol\u00f3n-Canedo, V., S\u00e1nchez-Maro\u00f1o, N., Alonso-Betanzos, A.: A review of feature selection methods on synthetic data. Knowled. Infor. Sys. 34(3), 483\u2013519 (2013)","journal-title":"Knowled. Infor. Sys."},{"key":"373_CR15","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.knosys.2015.05.014","volume":"86","author":"V Bol\u00f3n-Canedo","year":"2015","unstructured":"Bol\u00f3n-Canedo, V., S\u00e1nchez-Maro\u00f1o, N., Alonso-Betanzos, A.: Recent advances and emerging challenges of feature selection in the context of big data. Knowl.-Based Sys. 86, 33\u201345 (2015)","journal-title":"Knowl.-Based Sys."},{"key":"373_CR16","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1016\/j.ins.2014.05.042","volume":"282","author":"V Bol\u00f3n-Canedo","year":"2014","unstructured":"Bol\u00f3n-Canedo, V., S\u00e1nchez-Maro\u00f1o, N., Alonso-Betanzos, A., Ben\u00edtez, J.M., Herrera, F.: A review of microarray datasets and applied feature selection methods. Infor. Sci. 282, 111\u2013135 (2014)","journal-title":"Infor. Sci."},{"key":"373_CR17","unstructured":"Bommert, A.M. Integration of feature selection stability in model fitting. Doctoral Dissertation. TU Dortmund University, Dortmund, Germany (2021)"},{"issue":"59","key":"373_CR18","doi-asserted-by":"publisher","first-page":"3010","DOI":"10.21105\/joss.03010","volume":"6","author":"AM Bommert","year":"2021","unstructured":"Bommert, A.M., Lang, M.: Stabm: stability measures for feature selection. J. Open Sour. Softw. 6(59), 3010 (2021)","journal-title":"J. Open Sour. Softw."},{"key":"373_CR19","doi-asserted-by":"crossref","unstructured":"Bommert, A.M., Rahnenf\u00fchrer, J.: Adjusted measures for feature selection stability for data sets with similar features. In: International conference on machine learning, optimization, and data science, pp. 203\u2013214. Springer, Cham (2020)","DOI":"10.1007\/978-3-030-64583-0_19"},{"key":"373_CR20","first-page":"7907163","volume":"2017","author":"AM Bommert","year":"2017","unstructured":"Bommert, A.M., Rahnenf\u00fchrer, J., Lang, M.: A multicriteria approach to find predictive and sparse models with stable feature selection for high-dimensional data. Comput. Math. Model. Med. 2017, 7907163 (2017)","journal-title":"Comput. Math. Model. Med."},{"key":"373_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.csda.2019.106839","volume":"143","author":"AM Bommert","year":"2020","unstructured":"Bommert, A.M., Sun, X., Bischl, B., Rahnenf\u00fchrer, J., Lang, M.: Benchmark for filter methods for feature selection in high-dimensional classification data. Comput. Stat. Data Anal. 143, 106839 (2020)","journal-title":"Comput. Stat. Data Anal."},{"issue":"1","key":"373_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1093\/bib\/bbab354","volume":"23","author":"AM Bommert","year":"2022","unstructured":"Bommert, A.M., Welchowski, T., Schmid, M., Rahnenf\u00fchrer, J.: Benchmark of filter methods for feature selection in high-dimensional gene expression survival data. Brief. Bioinfor. 23(1), 1\u201313 (2022)","journal-title":"Brief. Bioinfor."},{"key":"373_CR23","first-page":"3","volume":"8","author":"C Bonferroni","year":"1936","unstructured":"Bonferroni, C.: Teoria statistica delle classi e calcolo delle probabilita. Pubblicazioni del R Istituto Superiore di Scienze Economiche e Commericiali di Firenze 8, 3\u201362 (1936)","journal-title":"Pubblicazioni del R Istituto Superiore di Scienze Economiche e Commericiali di Firenze"},{"key":"373_CR24","unstructured":"Borda, J.C.: M\u00e9moire sur les \u00e9lections au scrutin. M\u00e9moires de l'Acad\u00e9mie royale des Sciences de Paris pour l\u2019Ann\u00e9e 1781, 657-665 (1781)"},{"issue":"5","key":"373_CR25","doi-asserted-by":"publisher","first-page":"556","DOI":"10.1093\/bib\/bbp034","volume":"10","author":"AL Boulesteix","year":"2009","unstructured":"Boulesteix, A.L., Slawski, M.: Stability and aggregation of ranked gene lists. Brief. Bioinfor. 10(5), 556\u2013568 (2009)","journal-title":"Brief. Bioinfor."},{"key":"373_CR26","doi-asserted-by":"publisher","DOI":"10.1201\/9781315139470","volume-title":"Classification and regression trees","author":"L Breiman","year":"2017","unstructured":"Breiman, L., Friedman, J.H., Olshen, R.A., Stone, C.J.: Classification and regression trees. Routledge, London (2017)"},{"issue":"1","key":"373_CR27","first-page":"27","volume":"13","author":"G Brown","year":"2012","unstructured":"Brown, G., Pocock, A., Zhao, M.J., Luj\u00e1n, M.: Conditional likelihood maximisation: a unifying framework for information theoretic feature selection. J. Mach. Learn. Res. 13(1), 27\u201366 (2012)","journal-title":"J. Mach. Learn. Res."},{"key":"373_CR28","unstructured":"Burka, D., Puppe, C., Szepesv\u00e1ry, L., Tasn\u00e1di, A.: And the winner is... Chevalier de Borda: Neural networks vote according to Borda\u2019s Rule. In:\u00a0Proceedings of the Sixth International Workshop on Computational Social Choice (2016)"},{"issue":"2","key":"373_CR29","first-page":"249","volume":"22","author":"J Carletta","year":"1996","unstructured":"Carletta, J.: Assessing agreement on classification tasks: the kappa statistic. Comput. Ling. 22(2), 249\u2013254 (1996)","journal-title":"Comput. Ling."},{"issue":"10","key":"373_CR30","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0107957","volume":"9","author":"E Chaibub Neto","year":"2014","unstructured":"Chaibub Neto, E., Bare, J.C., Margolin, A.A.: Simulation studies as designed experiments: the comparison of penalized regression models in the \u201clarge p, small n\u201d setting. PloS one 9(10), e107957 (2014)","journal-title":"PloS one"},{"key":"373_CR31","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"NV Chawla","year":"2002","unstructured":"Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: SMOTE: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321\u2013357 (2002)","journal-title":"J. Artif. Intell. Res."},{"issue":"1","key":"373_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12859-018-2264-5","volume":"19","author":"R Couronn\u00e9","year":"2018","unstructured":"Couronn\u00e9, R., Probst, P., Boulesteix, A.L.: Random forest versus logistic regression: a large-scale benchmark experiment. BMC Bioinfor. 19(1), 1\u201314 (2018)","journal-title":"BMC Bioinfor."},{"issue":"3","key":"373_CR33","doi-asserted-by":"publisher","first-page":"131","DOI":"10.3233\/IDA-1997-1302","volume":"1","author":"M Dash","year":"1997","unstructured":"Dash, M., Liu, H.: Feature selection for classification. Intell. Data Anal. 1(3), 131\u2013156 (1997)","journal-title":"Intell. Data Anal."},{"issue":"19","key":"373_CR34","doi-asserted-by":"publisher","first-page":"2356","DOI":"10.1093\/bioinformatics\/btl400","volume":"22","author":"Davis CA, Gerick F, Hintermair V, Friedel CC, Fundel K, K\u00fcffner R, Zimmer R","year":"2006","unstructured":"Davis CA, Gerick F, Hintermair V, Friedel CC, Fundel K, K\u00fcffner R, Zimmer R: Reliable gene signatures for microarray classification: assessment of stability and performance. Bioinformatics 22(19), 2356\u20132363 (2006)","journal-title":"Bioinformatics"},{"key":"373_CR35","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511802843","volume-title":"Bootstrap methods and their application (No. 1)","author":"AC Davison","year":"1997","unstructured":"Davison, A.C., Hinkley, D.V.: Bootstrap methods and their application (No. 1). Cambridge University Press, Cambridge (1997)"},{"key":"373_CR36","unstructured":"Densmore, J.: Data pipeline pocket reference. O\u2019Reilly Media, Inc (2021)"},{"issue":"3","key":"373_CR37","doi-asserted-by":"publisher","first-page":"297","DOI":"10.2307\/1932409","volume":"26","author":"LR Dice","year":"1945","unstructured":"Dice, L.R.: Measures of the amount of ecologic association between species. Ecology 26(3), 297\u2013302 (1945)","journal-title":"Ecology"},{"key":"373_CR38","doi-asserted-by":"crossref","unstructured":"Dittman, D.J., Khoshgoftaar, T.M., Wald, R., Napolitano, A.: Similarity analysis of feature ranking techniques on imbalanced DNA microarray datasets. In: 2012 IEEE International conference on bioinformatics and biomedicine, pp. 1\u20135. IEEE (2012)","DOI":"10.1109\/BIBM.2012.6392708"},{"key":"373_CR39","unstructured":"Dittman, D.J., Khoshgoftaar, T.M., Wald, R., Napolitano, A.: Classification performance of rank aggregation techniques for ensemble gene selection. In: Proceedings of the twenty-sixth international FLAIRS conference, pp. 420-425 (2013)"},{"key":"373_CR40","doi-asserted-by":"crossref","unstructured":"Duangsoithong, R., Windeatt, T.: Bootstrap feature selection for ensemble classifiers. In: industrial conference on data mining, pp. 28-41. Springer, Berlin, Heidelberg (2010)","DOI":"10.1007\/978-3-642-14400-4_3"},{"key":"373_CR41","doi-asserted-by":"crossref","unstructured":"Dwork, C., Kumar, R., Naor, M., Sivakumar, D.: Rank aggregation methods for the web. In: Proceedings of the 10th International world wide web conference, pp. 613\u2013622. ACM (2001)","DOI":"10.1145\/371920.372165"},{"key":"373_CR42","doi-asserted-by":"publisher","first-page":"24649","DOI":"10.1109\/ACCESS.2019.2899578","volume":"7","author":"SH Ebenuwa","year":"2019","unstructured":"Ebenuwa, S.H., Sharif, M.S., Alazab, M., Al-Nemrat, A.: Variance ranking attributes selection techniques for binary classification problem in imbalance data. IEEE Access 7, 24649\u201324666 (2019)","journal-title":"IEEE Access"},{"key":"373_CR43","doi-asserted-by":"crossref","unstructured":"Ghai, B., Mishra, M., Mueller, K.: Cascaded debiasing: studying the cumulative effect of multiple fairness-enhancing interventions. arXiv preprint arXiv:2202.03734 (2022)","DOI":"10.1145\/3511808.3557155"},{"key":"373_CR44","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-319-98566-4_10","volume-title":"Natural computing for unsupervised learning","author":"S Goswami","year":"2019","unstructured":"Goswami, S., Chakraborty, S., Guha, P., Tarafdar, A., Kedia, A.: Filter-based feature selection methods using hill climbing approach. In: Natural computing for unsupervised learning, pp. 213\u2013234. Springer, Cham (2019)"},{"key":"373_CR45","doi-asserted-by":"crossref","unstructured":"Gulgezen, G., Cataltepe, Z., Yu, L.: Stable and accurate feature selection. In: Joint European Conference on machine learning and knowledge discovery in databases, pp. 455-468. Springer, Berlin, Heidelberg (2009)","DOI":"10.1007\/978-3-642-04180-8_47"},{"key":"373_CR46","doi-asserted-by":"crossref","unstructured":"Guzm\u00e1n-Martinez, R., Alaiz-Rodr\u00edguez, R.: Feature selection stability assessment based on the jensen-shannon divergence. In: Joint European conference on machine learning and knowledge discovery in databases, pp. 597-612. Springer, Berlin, Heidelberg (2011)","DOI":"10.1007\/978-3-642-23780-5_48"},{"key":"373_CR47","unstructured":"Hall, M.A.: Correlation-based feature selection for machine learning. Doctoral Dissertation. University of Waikato, Hamilton, Hamilton, New Zealand (1999)"},{"key":"373_CR48","unstructured":"Hopf, K., Reifenrath, S.: Filter methods for feature selection in supervised machine learning applications\u2013Review and benchmark. arXiv preprint arXiv:2111.12140 (2021)"},{"issue":"3","key":"373_CR49","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1016\/j.patcog.2008.08.001","volume":"42","author":"J Hua","year":"2009","unstructured":"Hua, J., Tembe, W.D., Dougherty, E.R.: Performance of feature-selection methods in the classification of high-dimension data. Patt. Recognit. 42(3), 409\u2013424 (2009)","journal-title":"Patt. Recognit."},{"issue":"1","key":"373_CR50","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12859-016-1228-x","volume":"17","author":"BF Huang","year":"2016","unstructured":"Huang, B.F., Boutros, P.C.: The parameter sensitivity of random forests. BMC Bioinform. 17(1), 1\u201313 (2016)","journal-title":"BMC Bioinform."},{"key":"373_CR51","first-page":"1","volume":"2021","author":"C Huang","year":"2021","unstructured":"Huang, C.: Feature selection and feature stability measurement method for high-dimensional small sample data based on big data technology. Computat. Intell. Neurosci. 2021, 1\u201312 (2021)","journal-title":"Computat. Intell. Neurosci."},{"key":"373_CR52","doi-asserted-by":"crossref","unstructured":"Izenman, A.J.: Modern multivariate statistical techniques. In: Springer Texts in Statistics, Springer, New York (2008)","DOI":"10.1007\/978-0-387-78189-1"},{"key":"373_CR53","first-page":"547","volume":"37","author":"P Jaccard","year":"1901","unstructured":"Jaccard, P.: \u00c9tude comparative de la distribution florale dans une portion des Alpes et des Jura. Bulletin de La Soci\u00e9t\u00e9 Vaudoise Des Sciences Naturelles 37, 547\u2013579 (1901)","journal-title":"Bulletin de La Soci\u00e9t\u00e9 Vaudoise Des Sciences Naturelles"},{"key":"373_CR54","doi-asserted-by":"publisher","DOI":"10.3389\/fgene.2021.632620","volume":"12","author":"D K\u00e4llberg","year":"2021","unstructured":"K\u00e4llberg, D., Vidman, L., Ryd\u00e9n, P.: Comparison of methods for feature selection in clustering of high-dimensional RNA-sequencing data to identify cancer subtypes. Front. Genet. 12, 632620 (2021)","journal-title":"Front. Genet."},{"issue":"1","key":"373_CR55","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1007\/s10115-006-0040-8","volume":"12","author":"A Kalousis","year":"2007","unstructured":"Kalousis, A., Prados, J., Hilario, M.: Stability of feature selection algorithms: a study on high-dimensional spaces. Knowl. Inform. Sys. 12(1), 95\u2013116 (2007)","journal-title":"Knowl. Inform. Sys."},{"issue":"2","key":"373_CR56","first-page":"271","volume":"2","author":"AG Karegowda","year":"2010","unstructured":"Karegowda, A.G., Manjunath, A.S., Jayaram, M.A.: Comparative study of attribute selection using gain ratio and correlation based feature selection. Int. J. Inform. Technol. Knowl. Manag. 2(2), 271\u2013277 (2010)","journal-title":"Int. J. Inform. Technol. Knowl. Manag."},{"key":"373_CR57","doi-asserted-by":"crossref","unstructured":"Karunakaran, V., Rajasekar, V., Joseph, S.: exploring a filter and wrapper feature selection techniques in machine learning. In: Computational vision and bio-inspired computing, pp. 497-506. Springer, Singapore (2021)","DOI":"10.1007\/978-981-33-6862-0_40"},{"issue":"4","key":"373_CR58","first-page":"1060","volume":"34","author":"UM Khaire","year":"2019","unstructured":"Khaire, U.M., Dhanalakshmi, R.: Stability of feature selection algorithm: a review. J. King Saud Univer. Comp. Inf. Sci. 34(4), 1060\u20131073 (2019)","journal-title":"J. King Saud Univer. Comp. Inf. Sci."},{"key":"373_CR59","doi-asserted-by":"crossref","unstructured":"Khoshgoftaar, T.M., Gao, K., Seliya, N.: Attribute selection and imbalanced data: Problems in software defect prediction. In: 2010 22nd IEEE International conference on tools with artificial intelligence, pp. 137-144. IEEE (2010)","DOI":"10.1109\/ICTAI.2010.27"},{"key":"373_CR60","doi-asserted-by":"crossref","unstructured":"Khoshgoftaar, T.M., Golawala, M., Van Hulse, J.: An empirical study of learning from imbalanced data using random forest. In: 19th IEEE International conference on tools with artificial intelligence, pp. 310-317. IEEE (2007)","DOI":"10.1109\/ICTAI.2007.46"},{"key":"373_CR61","unstructured":"Kohavi, R.: A study of cross-validation and bootstrap for accuracy estimation and model selection. In:\u00a0International joint conference on artificial intelligence, pp. 1137-1145 (1995)"},{"key":"373_CR62","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/j.knosys.2015.02.017","volume":"82","author":"I Koprinska","year":"2015","unstructured":"Koprinska, I., Rana, M., Agelidis, V.G.: Correlation and instance based feature selection for electricity load forecasting. Knowl.-Based Sys. 82, 29\u201340 (2015)","journal-title":"Knowl.-Based Sys."},{"key":"373_CR63","doi-asserted-by":"crossref","unstructured":"Kr\u00edzek, P., Kittler, J., & Hlav\u00e1c, V.: Improving stability of feature selection methods. In: International conference on computer analysis of images and patterns, pp. 929-936. Springer, Berlin, Heidelberg (2007)","DOI":"10.1007\/978-3-540-74272-2_115"},{"key":"373_CR64","unstructured":"Kuhn, M.: Caret: classification and regression training.\u00a0Astrophysics Source Code Library, ascl-1505 (2015)"},{"key":"373_CR65","doi-asserted-by":"crossref","unstructured":"Kujawska, H., Slavkovik, M., R\u00fcckmann, J. J.: Predicting the winners of Borda, Kemeny and Dodgson elections with supervised machine learning. In: Multi-Agent Systems and Agreement Technologies, pp. 440-458. Springer, Cham (2020)","DOI":"10.1007\/978-3-030-66412-1_28"},{"issue":"7","key":"373_CR66","doi-asserted-by":"publisher","first-page":"746","DOI":"10.3390\/math9070746","volume":"9","author":"J Laborda","year":"2021","unstructured":"Laborda, J., Ryoo, S.: Feature selection in a credit scoring model. Mathematics 9(7), 746 (2021)","journal-title":"Mathematics"},{"issue":"1","key":"373_CR67","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1007\/s00180-011-0284-y","volume":"28","author":"L Lausser","year":"2013","unstructured":"Lausser, L., M\u00fcssel, C., Maucher, M., Kestler, H.A.: Measuring and visualizing the stability of biomarker selection techniques. Comput. Stat. 28(1), 51\u201365 (2013)","journal-title":"Comput. Stat."},{"issue":"4","key":"373_CR68","doi-asserted-by":"publisher","first-page":"1106","DOI":"10.1109\/TCBB.2012.33","volume":"9","author":"C Lazar","year":"2012","unstructured":"Lazar, C., Taminau, J., Meganck, S., Steenhoff, D., Coletta, A., Molter, C., de Schaetzen, V., Duque, R., Bersini, H., Nowe, A.: A survey on filter techniques for feature selection in gene expression microarray analysis. IEEE\/ACM Trans. Comput. Biol. Bioinform. 9(4), 1106\u20131119 (2012)","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinform."},{"key":"373_CR69","unstructured":"Liu, H.:\u00a0Algorithms for Scalability and Security in Adversarial Environments. Doctoral Dissertation. The University of Arizona, Tucson, Arizona (2021)"},{"key":"373_CR70","unstructured":"Lustgarten, J. L., Gopalakrishnan, V., Visweswaran, S.: Measuring stability of feature selection in biomedical datasets. In AMIA Annual Symposium Proceeding, p. 406. American Medical Informatics Association (2009)"},{"issue":"3","key":"373_CR71","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/s40192-018-0109-8","volume":"7","author":"A Mangal","year":"2018","unstructured":"Mangal, A., Holm, E.A.: A comparative study of feature selection methods for stress hotspot classification in materials. Integrat. Mater. Manuf. Innovat. 7(3), 87\u201395 (2018)","journal-title":"Integrat. Mater. Manuf. Innovat."},{"issue":"1","key":"373_CR72","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1471-2288-10-1","volume":"10","author":"A Marshall","year":"2010","unstructured":"Marshall, A., Altman, D.G., Royston, P., Holder, R.L.: Comparison of techniques for handling missing covariate data within prognostic modelling studies: a simulation study. BMC Med. Resear. Methodol. 10(1), 1\u201316 (2010)","journal-title":"BMC Med. Resear. Methodol."},{"issue":"4","key":"373_CR73","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1080\/0952813X.2015.1042530","volume":"28","author":"XB Meng","year":"2016","unstructured":"Meng, X.B., Gao, X.Z., Lu, L., Liu, Y., Zhang, H.: A new bio-inspired optimisation algorithm: Bird Swarm Algorithm. J. Exper. Theoret. Artif. Intell. 28(4), 673\u2013687 (2016)","journal-title":"J. Exper. Theoret. Artif. Intell."},{"issue":"3","key":"373_CR74","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1109\/JSTSP.2008.923858","volume":"2","author":"PE Meyer","year":"2008","unstructured":"Meyer, P.E., Schretter, C., Bontempi, G.: Information-theoretic feature selection in microarray data using variable complementarity. IEEE J. Select. Top. Sign. Process. 2(3), 261\u2013274 (2008)","journal-title":"IEEE J. Select. Top. Sign. Process."},{"key":"373_CR75","doi-asserted-by":"crossref","unstructured":"Mohd Yusof, M., Mohamed, R., Wahid, N.: Benchmark of feature selection techniques with machine learning algorithms for cancer datasets. In: Proceedings of the international conference on artificial intelligence and robotics and the International conference on automation, control, and robotics engineering, pp. 1\u20135 (2016)","DOI":"10.1145\/2952744.2952753"},{"key":"373_CR76","unstructured":"Montgomery, D.C.: Design and Analysis of Experiments. John Wiley & Sons (2017)"},{"issue":"9","key":"373_CR77","doi-asserted-by":"publisher","first-page":"1425","DOI":"10.1002\/sim.1750","volume":"23","author":"E Moons","year":"2004","unstructured":"Moons, E., Aerts, M., Wets, G.: A tree based lack-of-fit test for multiple logistic regression. Stat. Med. 23(9), 1425\u20131438 (2004)","journal-title":"Stat. Med."},{"key":"373_CR78","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1016\/j.neucom.2021.05.107","volume":"470","author":"L Mor\u00e1n-Fern\u00e1ndez","year":"2022","unstructured":"Mor\u00e1n-Fern\u00e1ndez, L., B\u00f3lon-Canedo, V., Alonso-Betanzos, A.: How important is data quality? Best classifiers vs best features. Neurocomputing 470, 365\u2013375 (2022)","journal-title":"Neurocomputing"},{"issue":"8","key":"373_CR79","doi-asserted-by":"publisher","first-page":"5745","DOI":"10.1007\/s11227-019-02975-7","volume":"76","author":"DJ Munirathinam","year":"2020","unstructured":"Munirathinam, D.J., Ranganadhan, M.: A new improved filter based feature selection model for high-dimensional data. J. Supercomp. 76(8), 5745\u20135762 (2020)","journal-title":"J. Supercomp."},{"key":"373_CR80","unstructured":"Nogueira, S.: Quantifying the stability of feature selection. Doctoral dissertation. The University of Manchester, Manchester, United Kingdom (2018)"},{"key":"373_CR81","doi-asserted-by":"crossref","unstructured":"Nogueira, S., Brown, G.: Measuring the stability of feature selection. In: Joint European conference on machine learning and knowledge discovery in databases, pp. 442\u2013457. Springer, Cham (2016)","DOI":"10.1007\/978-3-319-46227-1_28"},{"issue":"1","key":"373_CR82","first-page":"6345","volume":"18","author":"S Nogueira","year":"2017","unstructured":"Nogueira, S., Sechidis, K., Brown, G.: On the stability of feature selection algorithms. J. Mach. Learn. Res. 18(1), 6345\u20136398 (2017)","journal-title":"J. Mach. Learn. Res."},{"key":"373_CR83","doi-asserted-by":"crossref","unstructured":"Novovi\u010dov\u00e1, J., Somol, P., Pudil, P.: A new measure of feature selection algorithms\u2019 stability. In: 2009 IEEE International conference on data mining workshops, pp. 382\u2013387. IEEE (2009)","DOI":"10.1109\/ICDMW.2009.32"},{"key":"373_CR84","doi-asserted-by":"crossref","unstructured":"Rajbahadur, G.K., Oliva, G.A., Hassan, A.E., Dingel, J.: Pitfalls analyzer: quality control for model-driven data science pipelines. In: 2019 ACM\/IEEE 22nd international conference on model driven engineering languages and systems (MODELS), pp. 12\u201322. IEEE (2019)","DOI":"10.1109\/MODELS.2019.00-19"},{"issue":"1","key":"373_CR85","first-page":"7","volume":"1","author":"MR Ramaswami","year":"2009","unstructured":"Ramaswami, M.R., Bhaskaran, R.: A study on feature selection techniques in educational data mining. J. Comput. 1(1), 7\u201311 (2009)","journal-title":"J. Comput."},{"key":"373_CR86","doi-asserted-by":"publisher","DOI":"10.1016\/j.jhydrol.2020.124897","volume":"586","author":"K Ren","year":"2020","unstructured":"Ren, K., Fang, W., Qu, J., Zhang, X., Shi, X.: Comparison of eight filter-based feature selection methods for monthly streamflow forecasting\u2014three case studies on CAMELS data sets. J. Hydrol. 586, 124897 (2020)","journal-title":"J. Hydrol."},{"key":"373_CR87","unstructured":"Romanski, P., Kotthoff, L., Kotthoff, M.L.: Package \u2018FSelector\u2019. URL: http:\/\/cran\/r-project.org\/web\/packages\/FSelector\/index.html (2013)"},{"issue":"1","key":"373_CR88","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-022-00607-1","volume":"9","author":"R Salman","year":"2022","unstructured":"Salman, R., Alzaatreh, A., Sulieman, H.: The stability of different aggregation techniques in ensemble feature selection. J. Big Data 9(1), 1\u201323 (2022)","journal-title":"J. Big Data"},{"key":"373_CR89","doi-asserted-by":"crossref","unstructured":"S\u00e1nchez-Maro\u00f1o, N., Alonso-Betanzos, A., Tombilla-Sanrom\u00e1n, M.: Filter methods for feature selection \u2013 a comparative study. In: international conference on intelligent data engineering and automated learning, pp. 178-187. Springer, Berlin, Heidelberg (2007)","DOI":"10.1007\/978-3-540-77226-2_19"},{"issue":"3","key":"373_CR90","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1080\/08839514.2014.883903","volume":"28","author":"C Sarkar","year":"2014","unstructured":"Sarkar, C., Cooley, S., Srivastava, J.: Robust feature selection technique using rank aggregation. Appl. Artif. Intell. 28(3), 243\u2013257 (2014)","journal-title":"Appl. Artif. Intell."},{"issue":"4","key":"373_CR91","doi-asserted-by":"publisher","first-page":"771","DOI":"10.3390\/make3040038","volume":"3","author":"R Sen","year":"2021","unstructured":"Sen, R., Mandal, A.K., Chakraborty, B.: A critical study on stability measures of feature selection with a novel extension of lustgarten index. Mach. Learn. Knowl. Extract. 3(4), 771\u2013787 (2021)","journal-title":"Mach. Learn. Knowl. Extract."},{"key":"373_CR92","doi-asserted-by":"crossref","unstructured":"Sen, R., Mandal, A.K., Chakraborty, B.: Performance analysis of extended lustgarten index for stability of feature selection. In: 2021 IEEE international conference on service operations and logistics, and informatics (SOLI), pp. 1\u20135. IEEE (2021)","DOI":"10.1109\/SOLI54607.2021.9672357"},{"issue":"11","key":"373_CR93","doi-asserted-by":"publisher","first-page":"1921","DOI":"10.1109\/TPAMI.2010.34","volume":"32","author":"P Somol","year":"2010","unstructured":"Somol, P., Novovi\u010dov\u00e1, J.: Evaluating stability and comparing output of feature selectors that optimize feature subset cardinality. IEEE Trans. Patt. Anal. Mach. Intell. 32(11), 1921\u20131939 (2010)","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell."},{"key":"373_CR94","doi-asserted-by":"crossref","unstructured":"Skiena, S.S.: The Data Science Design Manual. Springer (2017)","DOI":"10.1007\/978-3-319-55444-0"},{"key":"373_CR95","doi-asserted-by":"crossref","unstructured":"Skurichina, M., Duin, R.P. (2005). Combining feature subsets in feature selection. In: International workshop on multiple classifier systems, pp. 165\u2013175. Springer, Berlin, Heidelberg (2005)","DOI":"10.1007\/11494683_17"},{"issue":"1","key":"373_CR96","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1471-2105-9-307","volume":"9","author":"C Strobl","year":"2008","unstructured":"Strobl, C., Boulesteix, A.L., Kneib, T., Augustin, T., Zeileis, A.: Conditional variable importance for random forests. BMC Bioinform. 9(1), 1\u201311 (2008)","journal-title":"BMC Bioinform."},{"issue":"1","key":"373_CR97","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1471-2105-8-25","volume":"8","author":"C Strobl","year":"2007","unstructured":"Strobl, C., Boulesteix, A.L., Zeileis, A., Hothorn, T.: Bias in random forest variable importance measures: illustrations, sources, and a solution. BMC Bioinform. 8(1), 1\u201321 (2007)","journal-title":"BMC Bioinform."},{"key":"373_CR98","doi-asserted-by":"crossref","unstructured":"Subbian K, Melville P.: Supervised rank aggregation for predicting influence in networks.\u00a0arXiv preprint arXiv:1108.4801 (2011)","DOI":"10.1109\/PASSAT\/SocialCom.2011.167"},{"issue":"1","key":"373_CR99","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1109\/TFUZZ.2020.2989098","volume":"29","author":"L Sun","year":"2020","unstructured":"Sun, L., Wang, L., Ding, W., Qian, Y., Xu, J.: Feature selection using fuzzy neighborhood entropy-based uncertainty measures for fuzzy neighborhood multigranulation rough sets. IEEE Trans. Fuzzy Sys. 29(1), 19\u201333 (2020)","journal-title":"IEEE Trans. Fuzzy Sys."},{"issue":"2","key":"373_CR100","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1007\/s00500-007-0193-8","volume":"12","author":"F Tan","year":"2008","unstructured":"Tan, F., Fu, X., Zhang, Y., Bourgeois, A.G.: A genetic algorithm-based method for feature subset selection. Soft Comp. 12(2), 111\u2013120 (2008)","journal-title":"Soft Comp."},{"issue":"14","key":"373_CR101","doi-asserted-by":"publisher","first-page":"1986","DOI":"10.1093\/bioinformatics\/btr300","volume":"27","author":"L Tolo\u015fi","year":"2011","unstructured":"Tolo\u015fi, L., Lengauer, T.: Classification with correlated features: unreliability of feature ranking and solutions. Bioinform. 27(14), 1986\u20131994 (2011)","journal-title":"Bioinform."},{"key":"373_CR102","first-page":"1","volume":"1","author":"A Tsanas","year":"2010","unstructured":"Tsanas, A., Little, M.A., McSharry, P.E.: A simple filter benchmark for feature selection. J. Mach. Learn. Resea. 1, 1\u201324 (2010)","journal-title":"J. Mach. Learn. Resea."},{"key":"373_CR103","doi-asserted-by":"publisher","DOI":"10.1016\/j.petrol.2020.107630","volume":"195","author":"AT Tunkiel","year":"2020","unstructured":"Tunkiel, A.T., Sui, D., Wiktorski, T.: Data-driven sensitivity analysis of complex machine learning models: a case study of directional drilling. J. Petrol. Sci. Eng. 195, 107630 (2020)","journal-title":"J. Petrol. Sci. Eng."},{"key":"373_CR104","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1016\/j.jbi.2018.07.014","volume":"85","author":"RJ Urbanowicz","year":"2018","unstructured":"Urbanowicz, R.J., Meeker, M., La Cava, W., Olson, R.S., Moore, J.H.: Relief-based feature selection: introduction and review. J. Biomed. Inform. 85, 189\u2013203 (2018)","journal-title":"J. Biomed. Inform."},{"issue":"2","key":"373_CR105","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1007\/s10115-020-01519-3","volume":"63","author":"A Urkullu","year":"2021","unstructured":"Urkullu, A., P\u00e9rez, A., Calvo, B.: Statistical model for reproducibility in ranking-based feature selection. Knowl. Inform. Sys. 63(2), 379\u2013410 (2021)","journal-title":"Knowl. Inform. Sys."},{"issue":"1","key":"373_CR106","first-page":"1","volume":"45","author":"S Van Buuren","year":"2011","unstructured":"Van Buuren, S., Groothuis-Oudshoorn, K.: mice: multivariate imputation by chained equations in R. J. Stat. Softw. 45(1), 1\u201367 (2011)","journal-title":"J. Stat. Softw."},{"issue":"1","key":"373_CR107","first-page":"329","volume":"26","author":"YB Wah","year":"2018","unstructured":"Wah, Y.B., Ibrahim, N., Hamid, H.A., Abdul-Rahman, S., Fong, S.: Feature selection methods: case of filter and wrapper approaches for maximising classification accuracy. Pertanika J. Sci. Technol. 26(1), 329\u2013340 (2018)","journal-title":"Pertanika J. Sci. Technol."},{"key":"373_CR108","doi-asserted-by":"crossref","unstructured":"Wald, R., Khoshgoftaar, T.M., Dittman, D., Awada, W., Napolitano, A.: An extensive comparison of feature ranking aggregation techniques in bioinformatics. In: 2012 IEEE 13th international conference on information reuse & integration (IRI), pp. 377\u2013384. IEEE (2012)","DOI":"10.1109\/IRI.2012.6303034"},{"key":"373_CR109","doi-asserted-by":"crossref","unstructured":"Wald, R., Khoshgoftaar, T.M., Dittman, D.: Mean aggregation versus robust rank aggregation for ensemble gene selection. In: 2012 11th International conference on machine learning and applications, pp. 63\u201369. IEEE (2012)","DOI":"10.1109\/ICMLA.2012.20"},{"key":"373_CR110","doi-asserted-by":"crossref","unstructured":"Wald, R., Khoshgoftaar, T. M., & Napolitano, A.: Stability of filter- and wrapper based feature subset selection. In: 2013 IEEE 25th International conference on tools with artificial intelligence, pp. 374\u2013380. IEEE (2013)","DOI":"10.1109\/ICTAI.2013.63"},{"key":"373_CR111","unstructured":"Ying, C., Klein, A., Christiansen, E., Real, E., Murphy, K., Hutter, F.: Nas-bench-101: Towards reproducible neural architecture search. In: International conference on machine learning, pp. 7105\u20137114. PMLR (2019)"},{"key":"373_CR112","doi-asserted-by":"crossref","unstructured":"Yu, L., Ding, C., & Loscalzo, S.: Stable feature selection via dense feature groups. In: Proceedings of the 14th ACM SIGKDD International conference on knowledge discovery and data mining, pp. 803-811. ACM (2008)","DOI":"10.1145\/1401890.1401986"},{"issue":"20","key":"373_CR113","doi-asserted-by":"publisher","first-page":"2700","DOI":"10.1093\/bioinformatics\/btp460","volume":"25","author":"V Zuber","year":"2009","unstructured":"Zuber, V., Strimmer, K.: Gene ranking and biomarker discovery under correlation. Bioinformatics 25(20), 2700\u20132707 (2009)","journal-title":"Bioinformatics"}],"container-title":["International Journal of Data Science and Analytics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41060-022-00373-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41060-022-00373-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41060-022-00373-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,20]],"date-time":"2024-02-20T18:19:10Z","timestamp":1708453150000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s41060-022-00373-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,14]]},"references-count":113,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,3]]}},"alternative-id":["373"],"URL":"https:\/\/doi.org\/10.1007\/s41060-022-00373-6","relation":{},"ISSN":["2364-415X","2364-4168"],"issn-type":[{"value":"2364-415X","type":"print"},{"value":"2364-4168","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,14]]},"assertion":[{"value":"25 August 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 November 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 December 2022","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"}}]}}