{"id":"https://openalex.org/W4409479077","doi":"https://doi.org/10.14428/esann/2025.es2025-191","title":"Encoding Matters: Impact of Categorical Variable Encoding on Performance and Bias","display_name":"Encoding Matters: Impact of Categorical Variable Encoding on Performance and Bias","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409479077","doi":"https://doi.org/10.14428/esann/2025.es2025-191"},"language":"en","primary_location":{"id":"doi:10.14428/esann/2025.es2025-191","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2025.es2025-191","pdf_url":"https://doi.org/10.14428/esann/2025.es2025-191","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2025 proceesdings","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.14428/esann/2025.es2025-191","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5117165700","display_name":"Daniel Kopp","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Daniel Kopp","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117165701","display_name":"Benjamin Maudet","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Benjamin Maudet","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051369578","display_name":"Lisheng Sun-Hosoya","orcid":"https://orcid.org/0000-0002-5335-1547"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lisheng Sun-Hosoya","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5048876983","display_name":"Kristin P. Bennett","orcid":"https://orcid.org/0000-0002-8782-105X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kristin Bennett","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5117165700"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0031,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84248695,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"603","last_page":"608"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11148","display_name":"Language, Metaphor, and Cognition","score":0.060600001364946365,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11148","display_name":"Language, Metaphor, and Cognition","score":0.060600001364946365,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.8427457809448242},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.7345299124717712},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5786004662513733},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.521084189414978},{"id":"https://openalex.org/keywords/omitted-variable-bias","display_name":"Omitted-variable bias","score":0.5038394331932068},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2692970633506775},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21185201406478882},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1446041762828827}],"concepts":[{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.8427457809448242},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.7345299124717712},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5786004662513733},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.521084189414978},{"id":"https://openalex.org/C6571938","wikidata":"https://www.wikidata.org/wiki/Q3274486","display_name":"Omitted-variable bias","level":2,"score":0.5038394331932068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2692970633506775},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21185201406478882},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1446041762828827},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14428/esann/2025.es2025-191","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2025.es2025-191","pdf_url":"https://doi.org/10.14428/esann/2025.es2025-191","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2025 proceesdings","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.14428/esann/2025.es2025-191","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2025.es2025-191","pdf_url":"https://doi.org/10.14428/esann/2025.es2025-191","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2025 proceesdings","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1045782842","display_name":null,"funder_award_id":"ANR-19-CHIA-0022","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G8318455765","display_name":null,"funder_award_id":"ANR-19","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409479077.pdf","grobid_xml":"https://content.openalex.org/works/W4409479077.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4390437797","https://openalex.org/W3121946870","https://openalex.org/W94371014","https://openalex.org/W4402228978","https://openalex.org/W2752499541","https://openalex.org/W2140615276","https://openalex.org/W3157073909","https://openalex.org/W3095817863","https://openalex.org/W2052000568","https://openalex.org/W2102731947"],"abstract_inverted_index":{"Encoding":[0],"categorical":[1,88],"variables":[2,51,89],"impacts":[3],"model":[4,36,48],"performance":[5,108],"and":[6,30,52,107],"can":[7],"introduce":[8],"bias":[9,80],"in":[10],"supervised":[11],"learning,":[12],"particularly":[13],"affecting":[14],"fairness":[15],"when":[16],"some":[17],"groups":[18],"are":[19],"under-represented.We":[20],"analyze":[21],"the":[22,69,73,102],"effects":[23],"of":[24,72,92],"different":[25],"encoding":[26,62,86],"methods":[27],"on":[28,38,50],"synthetic":[29],"real":[31],"datasets":[32],"to":[33,46,56,60],"mitigate":[34],"unintended":[35],"reliance":[37,49],"specific":[39],"variables.We":[40],"propose":[41],"CaVaR":[42],"(Categorical":[43],"Variable":[44],"Reliance)":[45],"quantify":[47],"an":[53],"Availability":[54,65,74],"Index":[55,75],"measure":[57],"CaVaR's":[58],"sensitivity":[59],"partial":[61],"changes.A":[63],"high":[64],"Disparity,":[66],"measured":[67],"by":[68,105],"standard":[70],"deviation":[71],"across":[76],"encodings,":[77],"highlights":[78],"potential":[79],"from":[81],"mixed":[82],"encodings.The":[83],"results":[84],"suggest":[85],"all":[87],"uniformly,":[90],"regardless":[91],"their":[93],"ordinal":[94],"or":[95],"nominal":[96],"nature,":[97],"may":[98],"reduce":[99],"bias,":[100],"with":[101],"choice":[103],"guided":[104],"computational":[106],"considerations.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}