{"id":"https://openalex.org/W2080555645","doi":"https://doi.org/10.1109/mis.2004.1274906","title":"Scoring levels of categorical variables with heterogeneous data","display_name":"Scoring levels of categorical variables with heterogeneous data","publication_year":2004,"publication_date":"2004-03-01","ids":{"openalex":"https://openalex.org/W2080555645","doi":"https://doi.org/10.1109/mis.2004.1274906","mag":"2080555645"},"language":"en","primary_location":{"id":"doi:10.1109/mis.2004.1274906","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mis.2004.1274906","pdf_url":null,"source":{"id":"https://openalex.org/S114241109","display_name":"IEEE Intelligent Systems","issn_l":"1541-1672","issn":["1541-1672","1941-1294"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Intelligent Systems","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/A5057019721","display_name":"Eugene Tuv","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"E. Tuv","raw_affiliation_strings":["Intel, USA","Anal. & Control Technol., Intel Corp., Chandler, AZ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel, USA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Anal. & Control Technol., Intel Corp., Chandler, AZ, USA","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002544391","display_name":"George C. Runger","orcid":"https://orcid.org/0000-0001-9460-6983"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"G.C. Runger","raw_affiliation_strings":["Arizona State University, USA","IAFSE-CIDSE: Industrial, Systems and Operations Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University, USA","institution_ids":["https://openalex.org/I55732556"]},{"raw_affiliation_string":"IAFSE-CIDSE: Industrial, Systems and Operations Engineering","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8077,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.85600518,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"19","issue":"2","first_page":"14","last_page":"19"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9878000020980835,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9878000020980835,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11871","display_name":"Advanced Statistical Methods and Models","score":0.9836999773979187,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9753000140190125,"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":0.9039193391799927},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7588304877281189},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5743889212608337},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5547599792480469},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.5140756368637085},{"id":"https://openalex.org/keywords/multivariate-statistics","display_name":"Multivariate statistics","score":0.49819445610046387},{"id":"https://openalex.org/keywords/covariance-matrix","display_name":"Covariance matrix","score":0.4860742390155792},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4806443750858307},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.43721258640289307},{"id":"https://openalex.org/keywords/data-type","display_name":"Data type","score":0.42271941900253296},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2080613672733307},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1779930293560028},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1507464051246643}],"concepts":[{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.9039193391799927},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7588304877281189},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5743889212608337},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5547599792480469},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.5140756368637085},{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.49819445610046387},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.4860742390155792},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4806443750858307},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.43721258640289307},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.42271941900253296},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2080613672733307},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1779930293560028},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1507464051246643},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mis.2004.1274906","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mis.2004.1274906","pdf_url":null,"source":{"id":"https://openalex.org/S114241109","display_name":"IEEE Intelligent Systems","issn_l":"1541-1672","issn":["1541-1672","1941-1294"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Intelligent Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1480376833","https://openalex.org/W1549514886","https://openalex.org/W1594031697","https://openalex.org/W1678356000","https://openalex.org/W1993867461","https://openalex.org/W2014944622","https://openalex.org/W2052696562","https://openalex.org/W2063059120","https://openalex.org/W2070493638","https://openalex.org/W2102201073","https://openalex.org/W2163952039","https://openalex.org/W2171033594","https://openalex.org/W2319576313","https://openalex.org/W2330820318","https://openalex.org/W2999729612","https://openalex.org/W3150156619"],"related_works":["https://openalex.org/W4386799044","https://openalex.org/W2773208253","https://openalex.org/W2560646951","https://openalex.org/W4297454206","https://openalex.org/W2886934452","https://openalex.org/W1489099099","https://openalex.org/W2024369332","https://openalex.org/W1974955043","https://openalex.org/W4245750691","https://openalex.org/W2378724343"],"abstract_inverted_index":{"Heterogeneous":[0],"(mixed-type)":[1],"data":[2,48],"present":[3],"significant":[4],"challenges":[5],"in":[6,84],"both":[7],"supervised":[8],"and":[9,74,98],"unsupervised":[10,36],"learning.":[11],"The":[12],"situation":[13],"is":[14,68,113],"even":[15],"more":[16],"complicated":[17],"when":[18],"nominal":[19],"variables":[20,29,80],"have":[21],"several":[22,38],"levels":[23],"(values)":[24],"that":[25],"make":[26],"using":[27],"indicator":[28],"(for":[30],"every":[31],"categorical":[32,79],"level)":[33],"infeasible.":[34],"With":[35],"learning,":[37],"fairly":[39],"involved,":[40],"computationally":[41,72],"intensive,":[42],"nonlinear":[43],"multivariate":[44],"techniques":[45],"iteratively":[46],"alternate":[47],"transformations":[49],"with":[50],"optimal":[51],"scoring.":[52],"These":[53],"seek":[54],"to":[55,69,81,89],"optimize":[56],"an":[57],"objective":[58,116],"on":[59,123],"the":[60,128],"basis":[61],"of":[62,108],"a":[63,71,114,118],"covariance":[64],"matrix.":[65],"Our":[66],"goal":[67],"find":[70],"efficient":[73],"flexible":[75],"method":[76,120],"for":[77,117],"mapping":[78],"numeric":[82],"scores":[83],"mixed-type":[85],"data.":[86],"We":[87],"attempt":[88],"go":[90],"beyond":[91],"optimizing":[92],"second-order":[93],"statistics":[94],"(such":[95],"as":[96],"covariance)":[97],"enable":[99],"distance-based":[100],"methods":[101],"by":[102],"exploring":[103],"mutual":[104],"relationships":[105],"or":[106],"bumps":[107],"dependencies":[109],"between":[110],"variables.":[111,130],"This":[112],"new":[115],"scoring":[119],"that's":[121],"based":[122],"patterns":[124],"learned":[125],"from":[126],"all":[127],"available":[129]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}