{"id":"https://openalex.org/W7127597638","doi":"https://doi.org/10.1007/s41060-025-00886-w","title":"Categorical variable encoding methods for tabular data: a benchmarking study","display_name":"Categorical variable encoding methods for tabular data: a benchmarking study","publication_year":2026,"publication_date":"2026-02-04","ids":{"openalex":"https://openalex.org/W7127597638","doi":"https://doi.org/10.1007/s41060-025-00886-w"},"language":"en","primary_location":{"id":"doi:10.1007/s41060-025-00886-w","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s41060-025-00886-w","pdf_url":null,"source":{"id":"https://openalex.org/S4210195017","display_name":"International Journal of Data Science and Analytics","issn_l":"2364-415X","issn":["2364-415X","2364-4168"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319972","host_organization_name":"Springer International Publishing","host_organization_lineage":["https://openalex.org/P4310319972","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer International Publishing","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Data Science and Analytics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047682711","display_name":"Federico Clerici","orcid":"https://orcid.org/0009-0000-5388-2105"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Federico Clerici","raw_affiliation_strings":["Department of Mathematics, University of Padua, Padua, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, University of Padua, Padua, Italy","institution_ids":["https://openalex.org/I138689650"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040060014","display_name":"Navid Nobani","orcid":"https://orcid.org/0000-0001-9964-097X"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Navid Nobani","raw_affiliation_strings":["Department of Statistics and Quantitative Methods, University of Milan-Bicocca, Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics and Quantitative Methods, University of Milan-Bicocca, Milan, Italy","institution_ids":["https://openalex.org/I66752286"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5047682711"],"corresponding_institution_ids":["https://openalex.org/I138689650"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":null,"fwci":9.2305,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.95633294,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"22","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.31040000915527344,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.31040000915527344,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.10670000314712524,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.0771000012755394,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.821399986743927},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.6568999886512756},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5705000162124634},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5267999768257141},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5095999836921692},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4693000018596649},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.41359999775886536},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.41130000352859497}],"concepts":[{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.821399986743927},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7390000224113464},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6568999886512756},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6471999883651733},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6448000073432922},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5705000162124634},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5267999768257141},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5095999836921692},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4700999855995178},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4693000018596649},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.41359999775886536},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.41130000352859497},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.4065999984741211},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4065000116825104},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s41060-025-00886-w","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s41060-025-00886-w","pdf_url":null,"source":{"id":"https://openalex.org/S4210195017","display_name":"International Journal of Data Science and Analytics","issn_l":"2364-415X","issn":["2364-415X","2364-4168"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319972","host_organization_name":"Springer International Publishing","host_organization_lineage":["https://openalex.org/P4310319972","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer International Publishing","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Data Science and Analytics","raw_type":"journal-article"},{"id":"pmh:oai:boa.unimib.it:10281/589521","is_oa":false,"landing_page_url":"https://hdl.handle.net/10281/589521","pdf_url":null,"source":{"id":"https://openalex.org/S4306401259","display_name":"BOA (University of Milano-Bicocca)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66752286","host_organization_name":"University of Milano-Bicocca","host_organization_lineage":["https://openalex.org/I66752286"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W429766147","https://openalex.org/W1000639276","https://openalex.org/W1584444527","https://openalex.org/W1825662062","https://openalex.org/W1981457167","https://openalex.org/W1990037396","https://openalex.org/W1990836268","https://openalex.org/W2070996757","https://openalex.org/W2087574126","https://openalex.org/W2112195476","https://openalex.org/W2787894218","https://openalex.org/W2799900537","https://openalex.org/W2802170901","https://openalex.org/W2896310645","https://openalex.org/W2916086000","https://openalex.org/W2954052001","https://openalex.org/W2963092241","https://openalex.org/W2963105378","https://openalex.org/W2970019720","https://openalex.org/W3034856749","https://openalex.org/W3082157970","https://openalex.org/W3111640100","https://openalex.org/W3142848995","https://openalex.org/W3159303128","https://openalex.org/W3182079404","https://openalex.org/W3190574982","https://openalex.org/W3195971125","https://openalex.org/W3201969467","https://openalex.org/W3207353404","https://openalex.org/W3208745637","https://openalex.org/W4226502787","https://openalex.org/W4234726042","https://openalex.org/W4304701240","https://openalex.org/W4313823959","https://openalex.org/W4318193483","https://openalex.org/W4379259062","https://openalex.org/W4383199298","https://openalex.org/W4386781003","https://openalex.org/W4389483666","https://openalex.org/W4390946269","https://openalex.org/W4401702537","https://openalex.org/W4402024747","https://openalex.org/W4405939473","https://openalex.org/W6888840370","https://openalex.org/W6907674333","https://openalex.org/W6907784820","https://openalex.org/W6944960951","https://openalex.org/W6945111357","https://openalex.org/W6945436263","https://openalex.org/W6945598159","https://openalex.org/W6963918554","https://openalex.org/W6964177967","https://openalex.org/W6964248249"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2026-02-06T00:00:00"}