{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T15:51:12Z","timestamp":1772725872880,"version":"3.50.1"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031334979","type":"print"},{"value":"9783031334986","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-33498-6_14","type":"book-chapter","created":{"date-parts":[[2023,5,18]],"date-time":"2023-05-18T07:02:40Z","timestamp":1684393360000},"page":"202-213","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Preprocessing Matters: Automated Pipeline Selection for\u00a0Fair Classification"],"prefix":"10.1007","author":[{"given":"Vladimiro","family":"Gonz\u00e1lez-Zelaya","sequence":"first","affiliation":[]},{"given":"Juli\u00e1n","family":"Salas","sequence":"additional","affiliation":[]},{"given":"Dennis","family":"Prangle","sequence":"additional","affiliation":[]},{"given":"Paolo","family":"Missier","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,5,19]]},"reference":[{"issue":"3","key":"14_CR1","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1016\/S0731-7085(03)00583-1","volume":"34","author":"FO Andersson","year":"2004","unstructured":"Andersson, F.O., Kaiser, R., Jacobsson, S.P.: Data preprocessing by wavelets and genetic algorithms for enhanced multivariate analysis of LC peptide mapping. J. Pharm. Biomed. Anal. 34(3), 531\u2013541 (2004)","journal-title":"J. Pharm. Biomed. Anal."},{"issue":"1","key":"14_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s41747-020-00200-2","volume":"5","author":"OU Aydin","year":"2021","unstructured":"Aydin, O.U., et al.: On the usage of average Hausdorff distance for segmentation performance assessment: hidden error when used for ranking. Europ. Radiol. Exp. 5(1), 1\u20137 (2021)","journal-title":"Europ. Radiol. Exp."},{"issue":"4","key":"14_CR3","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0095693","volume":"9","author":"O Berger-Tal","year":"2014","unstructured":"Berger-Tal, O., Nathan, J., Meron, E., Saltz, D.: The exploration-exploitation dilemma: a multidisciplinary framework. PLoS ONE 9(4), e95693 (2014)","journal-title":"PLoS ONE"},{"key":"14_CR4","first-page":"3992","volume":"30","author":"F Calmon","year":"2017","unstructured":"Calmon, F., Wei, D., Vinzamuri, B., Natesan Ramamurthy, K., Varshney, K.R.: Optimized pre-processing for discrimination prevention. Adv. Neural. Inf. Process. Syst. 30, 3992\u20134001 (2017)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR5","unstructured":"Cason, T.E.: Titanic Dataset. http:\/\/biostat.app.vumc.org\/wiki\/Main\/DataSets (1999). Accessed 25 May 2021"},{"key":"14_CR6","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/978-3-540-39804-2_12","volume-title":"Knowledge Discovery in Databases: PKDD 2003","author":"NV Chawla","year":"2003","unstructured":"Chawla, N.V., Lazarevic, A., Hall, L.O., Bowyer, K.W.: SMOTEBoost: improving prediction of the minority class in boosting. In: Lavra\u010d, N., Gamberger, D., Todorovski, L., Blockeel, H. (eds.) PKDD 2003. LNCS (LNAI), vol. 2838, pp. 107\u2013119. Springer, Heidelberg (2003). https:\/\/doi.org\/10.1007\/978-3-540-39804-2_12"},{"key":"14_CR7","unstructured":"Chiappa, S., Gillam, T.P.: Path-specific counterfactual fairness. arXiv preprint arXiv:1802.08139 (2018)"},{"issue":"3","key":"14_CR8","doi-asserted-by":"publisher","first-page":"781","DOI":"10.1016\/j.ejor.2005.07.023","volume":"173","author":"SF Crone","year":"2006","unstructured":"Crone, S.F., Lessmann, S., Stahlbock, R.: The impact of preprocessing on data mining: an evaluation of classifier sensitivity in direct marketing. Eur. J. Oper. Res. 173(3), 781\u2013800 (2006)","journal-title":"Eur. J. Oper. Res."},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Danks, D., London, A.J.: Algorithmic bias in autonomous systems. In: IJCAI, vol. 17, pp. 4691\u20134697 (2017)","DOI":"10.24963\/ijcai.2017\/654"},{"key":"14_CR10","unstructured":"Dem\u0161ar, J., et al.: Orange: data mining toolbox in python. J. Mach. Learn. 14(1), 2349\u20132353 (2013)"},{"key":"14_CR11","unstructured":"Dua, D., Graff, C.: UCI machine learning repository (2017). http:\/\/archive.ics.uci.edu\/ml\/"},{"issue":"4","key":"14_CR12","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1145\/3433949","volume":"64","author":"SA Friedler","year":"2021","unstructured":"Friedler, S.A., Scheidegger, C., Venkatasubramanian, S.: The (im) possibility of fairness: different value systems require different mechanisms for fair decision making. Commun. ACM 64(4), 136\u2013143 (2021)","journal-title":"Commun. ACM"},{"issue":"1","key":"14_CR13","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1186\/s41044-016-0014-0","volume":"1","author":"S Garc\u00eda","year":"2016","unstructured":"Garc\u00eda, S., Ram\u00edrez-Gallego, S., Luengo, J., Ben\u00edtez, J.M., Herrera, F.: Big data preprocessing: methods and prospects. Big Data Anal. 1(1), 9 (2016). https:\/\/doi.org\/10.1186\/s41044-016-0014-0","journal-title":"Big Data Anal."},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Gonz\u00e1lez-Zelaya, V.: Towards explaining the effects of data preprocessing on machine learning. In: 2019 IEEE 35th International Conference on Data Engineering (ICDE), pp. 2086\u20132090. IEEE (2019)","DOI":"10.1109\/ICDE.2019.00245"},{"key":"14_CR15","unstructured":"Gonz\u00e1lez-Zelaya, V., Salas, J., Prangle, D., Missier, P.: Optimising fairness through parametrised data sampling. In: Proceedings of the 2021 EDBT Conference (2021)"},{"issue":"12","key":"14_CR16","doi-asserted-by":"publisher","first-page":"390","DOI":"10.3390\/info10120390","volume":"10","author":"A Hassanat","year":"2019","unstructured":"Hassanat, A., Almohammadi, K., Alkafaween, E., Abunawas, E., Hammouri, A., Prasath, V.: Choosing mutation and crossover ratios for genetic algorithms-a review with a new dynamic approach. Information 10(12), 390 (2019)","journal-title":"Information"},{"key":"14_CR17","unstructured":"Ishibuchi, H., Tsukamoto, N., Nojima, Y.: Evolutionary many-objective optimization: A short review. In: 2008 IEEE congress on evolutionary computation (IEEE world congress on computational intelligence), pp. 2419\u20132426. IEEE (2008)"},{"issue":"1","key":"14_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10115-011-0463-8","volume":"33","author":"F Kamiran","year":"2012","unstructured":"Kamiran, F., Calders, T.: Data preprocessing techniques for classification without discrimination. Knowl. Inf. Syst. 33(1), 1\u201333 (2012)","journal-title":"Knowl. Inf. Syst."},{"key":"14_CR19","unstructured":"Kusner, M., Loftus, J., Russell, C., Silva, R.: Counterfactual fairness. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 4069\u20134079 (2017)"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"La Cava, W., Moore, J.H.: Genetic programming approaches to learning fair classifiers. In: Proceedings of the 2020 Genetic and Evolutionary Computation Conference, pp. 967\u2013975 (2020)","DOI":"10.1145\/3377930.3390157"},{"key":"14_CR21","unstructured":"Larson, J., Mattu, S., Kirchner, L., Angwin, J.: How we analyzed the compas recidivism algorithm. ProPublica 5, 9 (2016)"},{"key":"14_CR22","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/j.artint.2015.06.007","volume":"228","author":"M Li","year":"2015","unstructured":"Li, M., Yang, S., Liu, X.: Bi-goal evolution for many-objective optimization problems. Artif. Intell. 228, 45\u201365 (2015)","journal-title":"Artif. Intell."},{"key":"14_CR23","unstructured":"Menon, A.K., Williamson, R.C.: The cost of fairness in binary classification. In: Conference on Fairness, Accountability and Transparency, pp. 107\u2013118. PMLR (2018)"},{"key":"14_CR24","unstructured":"Olson, R.S., Moore, J.H.: TPOT: a tree-based pipeline optimization tool for automating machine learning. In: Workshop on Automatic Machine Learning, pp. 66\u201374. PMLR (2016)"},{"key":"14_CR25","unstructured":"Pyle, D.: Data preparation for data mining. Morgan Kaufmann (1999)"},{"key":"14_CR26","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1007\/978-3-030-57524-3_24","volume-title":"Modeling Decisions for Artificial Intelligence","author":"J Salas","year":"2020","unstructured":"Salas, J., Gonz\u00e1lez-Zelaya, V.: Fair-MDAV: an algorithm for fair privacy by microaggregation. In: Torra, V., Narukawa, Y., Nin, J., Agell, N. (eds.) MDAI 2020. LNCS (LNAI), vol. 12256, pp. 286\u2013297. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-57524-3_24"},{"issue":"4","key":"14_CR27","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1109\/TEVC.2011.2161872","volume":"16","author":"O Schutze","year":"2012","unstructured":"Schutze, O., Esquivel, X., Lara, A., Coello, C.A.C.: Using the averaged Hausdorff distance as a performance measure in evolutionary multiobjective optimization. IEEE Trans. Evol. Comput. 16(4), 504\u2013522 (2012)","journal-title":"IEEE Trans. Evol. Comput."},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Smith, M.J., Sala, C., Kanter, J.M., Veeramachaneni, K.: The machine learning bazaar: Harnessing the ml ecosystem for effective system development. In: Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data, pp. 785\u2013800 (2020)","DOI":"10.1145\/3318464.3386146"},{"issue":"12","key":"14_CR29","doi-asserted-by":"publisher","first-page":"3474","DOI":"10.14778\/3415478.3415570","volume":"13","author":"J Stoyanovich","year":"2020","unstructured":"Stoyanovich, J., Howe, B., Jagadish, H.: Responsible data management. Proceed. VLDB Endow. 13(12), 3474\u20133488 (2020)","journal-title":"Proceed. VLDB Endow."},{"issue":"12","key":"14_CR30","doi-asserted-by":"publisher","first-page":"2165","DOI":"10.14778\/3229863.3240494","volume":"11","author":"J Stoyanovich","year":"2018","unstructured":"Stoyanovich, J., Howe, B., Jagadish, H., Miklau, G.: Panel: a debate on data and algorithmic ethics. Proceed. VLDB Endow. 11(12), 2165\u20132167 (2018)","journal-title":"Proceed. VLDB Endow."},{"issue":"2","key":"14_CR31","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. Comput. 12(2), 111\u2013120 (2008)","journal-title":"Soft. Comput."},{"issue":"1","key":"14_CR32","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1016\/j.ipm.2013.08.006","volume":"50","author":"AK Uysal","year":"2014","unstructured":"Uysal, A.K., Gunal, S.: The impact of preprocessing on text classification. Inf. Process. Manage. 50(1), 104\u2013112 (2014)","journal-title":"Inf. Process. Manage."},{"key":"14_CR33","unstructured":"Virtanen, P., et al.: SciPy 1.0: fundamental algorithms for scientific computing in python. Nat. Methods 17(3), 261\u2013272 (2020)"},{"issue":"2","key":"14_CR34","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1007\/BF00175354","volume":"4","author":"D Whitley","year":"1994","unstructured":"Whitley, D.: A genetic algorithm tutorial. Stat. Comput. 4(2), 65\u201385 (1994)","journal-title":"Stat. Comput."},{"key":"14_CR35","unstructured":"Yang, K., Huang, B., Stoyanovich, J., Schelter, S.: Fairness-aware instrumentation of preprocessing pipelines for machine learning. In: Workshop on Human-In-the-Loop Data Analytics (HILDA2020) (2020)"},{"key":"14_CR36","doi-asserted-by":"crossref","unstructured":"Yoo, S., Harman, M.: Pareto efficient multi-objective test case selection. In: Proceedings of the 2007 International Symposium on Software Testing and Analysis, pp. 140\u2013150 (2007)","DOI":"10.1145\/1273463.1273483"}],"container-title":["Lecture Notes in Computer Science","Modeling Decisions for Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-33498-6_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,21]],"date-time":"2023-05-21T23:17:33Z","timestamp":1684711053000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-33498-6_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031334979","9783031334986"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-33498-6_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"19 May 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MDAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Modeling Decisions for Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ume\u00e5","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 June 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 June 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mdai2022b","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}