{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T16:09:58Z","timestamp":1776442198470,"version":"3.51.2"},"publisher-location":"Cham","reference-count":15,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030726560","type":"print"},{"value":"9783030726577","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-72657-7_14","type":"book-chapter","created":{"date-parts":[[2021,4,22]],"date-time":"2021-04-22T13:04:28Z","timestamp":1619096668000},"page":"146-155","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Benchmark of Encoders of Nominal Features for Regression"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2652-3718","authenticated-orcid":false,"given":"Diogo","family":"Seca","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9081-2728","authenticated-orcid":false,"given":"Jo\u00e3o","family":"Mendes-Moreira","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,4,23]]},"reference":[{"key":"14_CR1","unstructured":"An, S.: 11 categorical encoders and benchmark, August 2020. https:\/\/kaggle.com\/subinium\/11-categorical-encoders-and-benchmark"},{"key":"14_CR2","unstructured":"Arel-Bundock, V.: A collection of datasets originally distributed in various R packages, May 2020. https:\/\/vincentarelbundock.github.io\/Rdatasets\/index.html"},{"key":"14_CR3","unstructured":"Bhalla, D.: Weight of evidence (WOE) and information value (IV) explained, March 2015. https:\/\/www.listendata.com\/2015\/03\/weight-of-evidence-woe-and-information.html"},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Cerda, P., Varoquaux, G.: Encoding high-cardinality string categorical variables. IEEE Trans. Knowl. Data Eng. 1 (2020)","DOI":"10.1109\/TKDE.2020.2992529"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Cerda, P.R.: Statistical learning with high-cardinality string categorical variables. Ph.D. thesis, Universit\u00e9 Paris-Saclay (2019)","DOI":"10.1109\/TKDE.2020.2992529"},{"issue":"1","key":"14_CR6","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1007\/s10796-018-9850-y","volume":"21","author":"E Golinko","year":"2019","unstructured":"Golinko, E., Zhu, X.: Generalized feature embedding for supervised, unsupervised, and online learning tasks. Inf. Syst. Front. 21(1), 125\u2013142 (2019)","journal-title":"Inf. Syst. Front."},{"issue":"1","key":"14_CR7","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1186\/s40537-020-00305-w","volume":"7","author":"JT Hancock","year":"2020","unstructured":"Hancock, J.T., Khoshgoftaar, T.M.: Survey on categorical data for neural networks. J. Big Data 7(1), 28 (2020)","journal-title":"J. Big Data"},{"key":"14_CR8","unstructured":"Ma, C., Tschiatschek, S., Hern\u00e1ndez-Lobato, J.M., Turner, R., Zhang, C.: VAEM: a deep generative model for heterogeneous mixed type data. arXiv:2006.11941, June 2020"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"McGinnis, W.D., Siu, C., Andre, S., Huang, H.: Category encoders: a scikit-learn-contrib package of transformers for encoding categorical data. J. Open Source Softw. 3(21), 501 (2018)","DOI":"10.21105\/joss.00501"},{"key":"14_CR10","unstructured":"Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., Galstyan, A.: A survey on bias and fairness in machine learning. arXiv:1908.09635, August 2019"},{"key":"14_CR11","unstructured":"Pargent, F., Bischl, B., Thomas, J.: A benchmark experiment on how to encode categorical features in predictive modeling (2019)"},{"key":"14_CR12","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., et al.: Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)","journal-title":"J. Mach. Learn. Res."},{"issue":"4","key":"14_CR13","doi-asserted-by":"publisher","first-page":"7","DOI":"10.5120\/ijca2017915495","volume":"175","author":"K Potdar","year":"2017","unstructured":"Potdar, K., Pardawala, T.S., Pai, C.D.: A comparative study of categorical variable encoding techniques for neural network classifiers. IJCAI 175(4), 7\u20139 (2017)","journal-title":"IJCAI"},{"key":"14_CR14","unstructured":"Vorotyntsev, D.: Benchmarking categorical encoders - towards data science, July 2019. https:\/\/towardsdatascience.com\/benchmarking-categorical-encoders-9c322bd77ee8"},{"issue":"1","key":"14_CR15","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."}],"container-title":["Advances in Intelligent Systems and Computing","Trends and Applications in Information Systems and Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-72657-7_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,22]],"date-time":"2021-04-22T13:22:45Z","timestamp":1619097765000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-72657-7_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030726560","9783030726577"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-72657-7_14","relation":{},"ISSN":["2194-5357","2194-5365"],"issn-type":[{"value":"2194-5357","type":"print"},{"value":"2194-5365","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"23 April 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"WorldCIST","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"World Conference on Information Systems and Technologies","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Terceira Island","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 March 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 April 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"worldcist2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/worldcist.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}