{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T14:08:47Z","timestamp":1772806127602,"version":"3.50.1"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031346736","type":"print"},{"value":"9783031346743","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\/978-3-031-34674-3_5","type":"book-chapter","created":{"date-parts":[[2023,6,7]],"date-time":"2023-06-07T20:32:15Z","timestamp":1686169935000},"page":"34-42","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A Data-Driven Methodology for\u00a0Guiding the\u00a0Selection of\u00a0Preprocessing Techniques in\u00a0a\u00a0Machine Learning Pipeline"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3174-083X","authenticated-orcid":false,"given":"Jorge","family":"Garc\u00eda-Carrasco","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7770-3693","authenticated-orcid":false,"given":"Alejandro","family":"Mat\u00e9","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0139-6724","authenticated-orcid":false,"given":"Juan","family":"Trujillo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,6,8]]},"reference":[{"key":"5_CR1","unstructured":"Data-Centric AI. https:\/\/datacentricai.org\/. Accessed 10 Mar 2023"},{"key":"5_CR2","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1007\/978-1-4842-6549-9_3","volume-title":"Beginning MLOps with MLFlow","author":"S Alla","year":"2021","unstructured":"Alla, S., Adari, S.K.: What Is MLOps? In: Alla, S., Adari, S.K. (eds.) Beginning MLOps with MLFlow, pp. 79\u2013124. Apress, Berkeley, CA (2021). https:\/\/doi.org\/10.1007\/978-1-4842-6549-9_3"},{"issue":"2","key":"5_CR3","doi-asserted-by":"publisher","first-page":"25","DOI":"10.18089\/tms.2017.13203","volume":"13","author":"N Antonio","year":"2017","unstructured":"Antonio, N., De Almeida, A., Nunes, L.: Predicting hotel booking cancellations to decrease uncertainty and increase revenue. Tour. Manag. Stud. 13(2), 25\u201339 (2017)","journal-title":"Tour. Manag. Stud."},{"key":"5_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-642-00296-0_5","volume-title":"Noise Reduction in Speech Processing","author":"J Benesty","year":"2009","unstructured":"Benesty, J., Chen, J., Huang, Y., Cohen, I.: Pearson correlation coefficient. In: Benesty, J., Chen, J., Huang, Y., Cohen, I. (eds.) Noise Reduction in Speech Processing, vol. 2, pp. 1\u20134. Springer, Heidelberg (2009). https:\/\/doi.org\/10.1007\/978-3-642-00296-0_5"},{"key":"5_CR5","volume-title":"Pattern Recognition and Machine Learning","author":"CM Bishop","year":"2006","unstructured":"Bishop, C.M., Nasrabadi, N.M.: Pattern Recognition and Machine Learning, vol. 4. Springer, New York (2006)"},{"issue":"2","key":"5_CR6","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1111\/j.2517-6161.1964.tb00553.x","volume":"26","author":"GE Box","year":"1964","unstructured":"Box, G.E., Cox, D.R.: An analysis of transformations. J. Roy. Stat. Soc.: Ser. B (Methodol.) 26(2), 211\u2013243 (1964)","journal-title":"J. Roy. Stat. Soc.: Ser. B (Methodol.)"},{"issue":"3","key":"5_CR7","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."},{"issue":"4","key":"5_CR8","doi-asserted-by":"crossref","first-page":"316","DOI":"10.1080\/00031305.1990.10475751","volume":"44","author":"RB D\u2019agostino","year":"1990","unstructured":"D\u2019agostino, R.B., Belanger, A., D\u2019Agostino, R.B., Jr.: A suggestion for using powerful and informative tests of normality. Am. Stat. 44(4), 316\u2013321 (1990)","journal-title":"Am. Stat."},{"key":"5_CR9","unstructured":"Feurer, M., Eggensperger, K., Falkner, S., Lindauer, M., Hutter, F.: Auto-sklearn 2.0: the next generation. arXiv preprint arXiv:2007.04074 (2020)"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Gon\u00e7alves, C.A., Gon\u00e7alves, C.T., Camacho, R., Oliveira, E.C.: The impact of pre-processing on the classification of MEDLINE documents. In: PRIS, pp. 53\u201361 (2010)","DOI":"10.5220\/0003028700530061"},{"key":"5_CR11","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016). http:\/\/www.deeplearningbook.org"},{"key":"5_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106622","volume":"212","author":"X He","year":"2021","unstructured":"He, X., Zhao, K., Chu, X.: AutoML: a survey of the state-of-the-art. Knowl.-Based Syst. 212, 106622 (2021)","journal-title":"Knowl.-Based Syst."},{"key":"5_CR13","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-7138-7","volume-title":"An Introduction to Statistical Learning","author":"G James","year":"2013","unstructured":"James, G., Witten, D., Hastie, T., Tibshirani, R.: An Introduction to Statistical Learning, vol. 112. Springer, New York (2013). https:\/\/doi.org\/10.1007\/978-1-4614-7138-7"},{"key":"5_CR14","doi-asserted-by":"publisher","DOI":"10.1201\/9781315108230","volume-title":"Feature Engineering and Selection: A Practical Approach for Predictive Models","author":"M Kuhn","year":"2019","unstructured":"Kuhn, M., Johnson, K.: Feature Engineering and Selection: A Practical Approach for Predictive Models. CRC Press, Boca Raton (2019)"},{"key":"5_CR15","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-6849-3","volume-title":"Applied Predictive Modeling","author":"M Kuhn","year":"2013","unstructured":"Kuhn, M., Johnson, K., et al.: Applied Predictive Modeling, vol. 26. Springer, New York (2013). https:\/\/doi.org\/10.1007\/978-1-4614-6849-3"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Miao, Y.: Using machine learning algorithms to predict diabetes mellitus based on Pima Indians Diabetes dataset. In: 2021 the 5th International Conference on Virtual and Augmented Reality Simulations, pp. 47\u201353 (2021)","DOI":"10.1145\/3463914.3463922"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Pereira, P., Cunha, J., Fernandes, J.P.: On understanding data scientists. In: 2020 IEEE Symposium on Visual Languages and Human-Centric Computing (VL\/HCC), pp. 1\u20135. IEEE (2020)","DOI":"10.1109\/VL\/HCC50065.2020.9127269"},{"issue":"1","key":"5_CR18","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. Manag. 50(1), 104\u2013112 (2014)","journal-title":"Inf. Process. Manag."},{"issue":"1","key":"5_CR19","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1109\/4235.585893","volume":"1","author":"DH Wolpert","year":"1997","unstructured":"Wolpert, D.H., Macready, W.G.: No free lunch theorems for optimization. IEEE Trans. Evol. Comput. 1(1), 67\u201382 (1997)","journal-title":"IEEE Trans. Evol. Comput."},{"issue":"4","key":"5_CR20","doi-asserted-by":"publisher","first-page":"954","DOI":"10.1093\/biomet\/87.4.954","volume":"87","author":"IK Yeo","year":"2000","unstructured":"Yeo, I.K., Johnson, R.A.: A new family of power transformations to improve normality or symmetry. Biometrika 87(4), 954\u2013959 (2000)","journal-title":"Biometrika"}],"container-title":["Lecture Notes in Business Information Processing","Intelligent Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-34674-3_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T22:47:08Z","timestamp":1729550828000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-34674-3_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031346736","9783031346743"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-34674-3_5","relation":{},"ISSN":["1865-1348","1865-1356"],"issn-type":[{"value":"1865-1348","type":"print"},{"value":"1865-1356","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"8 June 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CAiSE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Advanced Information Systems Engineering","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zaragoza","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","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":"12 June 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 June 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"35","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"caise2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"161","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"36","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"22% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.63","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"For the CAISE 2023 Forum 18 papers have been accepted from a total of 25 submissions. For the CAISE workshops 10 full and 9 short papers have been accepted from 25 submissions.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}