{"id":"https://openalex.org/W4408175168","doi":"https://doi.org/10.1007/s10618-024-01084-1","title":"Efficient outlier detection in numerical and categorical data","display_name":"Efficient outlier detection in numerical and categorical data","publication_year":2025,"publication_date":"2025-03-07","ids":{"openalex":"https://openalex.org/W4408175168","doi":"https://doi.org/10.1007/s10618-024-01084-1"},"language":"en","primary_location":{"id":"doi:10.1007/s10618-024-01084-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10618-024-01084-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10618-024-01084-1.pdf","source":{"id":"https://openalex.org/S121920818","display_name":"Data Mining and Knowledge Discovery","issn_l":"1384-5810","issn":["1384-5810","1573-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Mining and Knowledge Discovery","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10618-024-01084-1.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052961812","display_name":"Eug\u00eanio F. Cabral","orcid":null},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Eug\u00eanio F. Cabral","raw_affiliation_strings":["Department of Computer Science, University of S\u00e3o Paulo, Av. Trabalhador S\u00e3o-Carlense, 400, S\u00e3o Carlos, SP, 13566, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of S\u00e3o Paulo, Av. Trabalhador S\u00e3o-Carlense, 400, S\u00e3o Carlos, SP, 13566, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028607094","display_name":"Braulio V. S\u00e1nchez Vinces","orcid":null},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Braulio V. S\u00e1nchez Vinces","raw_affiliation_strings":["Department of Computer Science, University of S\u00e3o Paulo, Av. Trabalhador S\u00e3o-Carlense, 400, S\u00e3o Carlos, SP, 13566, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of S\u00e3o Paulo, Av. Trabalhador S\u00e3o-Carlense, 400, S\u00e3o Carlos, SP, 13566, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027378656","display_name":"Guilherme D. F. Silva","orcid":null},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Guilherme D. F. Silva","raw_affiliation_strings":["Department of Computer Science, University of S\u00e3o Paulo, Av. Trabalhador S\u00e3o-Carlense, 400, S\u00e3o Carlos, SP, 13566, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of S\u00e3o Paulo, Av. Trabalhador S\u00e3o-Carlense, 400, S\u00e3o Carlos, SP, 13566, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021763337","display_name":"J\u00f6rg Sander","orcid":"https://orcid.org/0000-0003-4068-7268"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"J\u00f6rg Sander","raw_affiliation_strings":["Department of Computing Science, University of Alberta, Edmonton, AB, T6G 2R3, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing Science, University of Alberta, Edmonton, AB, T6G 2R3, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085964688","display_name":"Robson L. F. Cordeiro","orcid":"https://orcid.org/0000-0002-6795-3004"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Robson L. F. Cordeiro","raw_affiliation_strings":["School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, 15213, USA"],"raw_orcid":"https://orcid.org/0000-0002-6795-3004","affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5085964688"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":2.792,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.8990625,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":"39","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":1.0,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":1.0,"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/T11871","display_name":"Advanced Statistical Methods and Models","score":0.9966999888420105,"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/T11443","display_name":"Advanced Statistical Process Monitoring","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.8563397526741028},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.6857026815414429},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.6258435249328613},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5937187671661377},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5314957499504089},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43412765860557556},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3705594539642334},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.26868557929992676}],"concepts":[{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.8563397526741028},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.6857026815414429},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.6258435249328613},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5937187671661377},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5314957499504089},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43412765860557556},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3705594539642334},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26868557929992676}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10618-024-01084-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10618-024-01084-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10618-024-01084-1.pdf","source":{"id":"https://openalex.org/S121920818","display_name":"Data Mining and Knowledge Discovery","issn_l":"1384-5810","issn":["1384-5810","1573-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Mining and Knowledge Discovery","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10618-024-01084-1","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10618-024-01084-1","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10618-024-01084-1.pdf","source":{"id":"https://openalex.org/S121920818","display_name":"Data Mining and Knowledge Discovery","issn_l":"1384-5810","issn":["1384-5810","1573-756X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Data Mining and Knowledge Discovery","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310207","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33"},{"id":"https://openalex.org/F4320320997","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","ror":"https://ror.org/02ddkpn78"},{"id":"https://openalex.org/F4320321091","display_name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","ror":"https://ror.org/00x0ma614"},{"id":"https://openalex.org/F4320322025","display_name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","ror":"https://ror.org/03swz6y49"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4408175168.pdf"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W109218057","https://openalex.org/W353413754","https://openalex.org/W561833833","https://openalex.org/W1515636651","https://openalex.org/W1530232915","https://openalex.org/W1536741282","https://openalex.org/W1669302834","https://openalex.org/W1995443851","https://openalex.org/W2009233076","https://openalex.org/W2056972503","https://openalex.org/W2066219179","https://openalex.org/W2094662804","https://openalex.org/W2106596127","https://openalex.org/W2107779728","https://openalex.org/W2129281431","https://openalex.org/W2141806397","https://openalex.org/W2144182447","https://openalex.org/W2145134722","https://openalex.org/W2151326673","https://openalex.org/W2170902455","https://openalex.org/W2206412560","https://openalex.org/W2296719434","https://openalex.org/W2337344967","https://openalex.org/W2548218624","https://openalex.org/W2585477755","https://openalex.org/W2604759793","https://openalex.org/W2752257308","https://openalex.org/W2756637424","https://openalex.org/W2765732590","https://openalex.org/W2970207504","https://openalex.org/W3094440069","https://openalex.org/W3175358558","https://openalex.org/W4210466590","https://openalex.org/W4251805162","https://openalex.org/W4256141317","https://openalex.org/W4256177618","https://openalex.org/W4297888682"],"related_works":["https://openalex.org/W4386799044","https://openalex.org/W2773208253","https://openalex.org/W2560646951","https://openalex.org/W2499612753","https://openalex.org/W3111802945","https://openalex.org/W2122407924","https://openalex.org/W2946096271","https://openalex.org/W2295423552","https://openalex.org/W1598471830","https://openalex.org/W3107369729"],"abstract_inverted_index":{"Abstract":[0],"How":[1,16],"to":[2,17,65,74,124,143,171],"spot":[3],"outliers":[4],"in":[5,20,67,139,149],"a":[6,21,87,110],"large,":[7],"unlabeled":[8],"dataset":[9],"with":[10,106,122,181],"both":[11,81,176],"numerical":[12,94],"and":[13,23,90,95,109,178],"categorical":[14,76,96,182],"attributes?":[15],"do":[18],"it":[19,31],"fast":[22,89],"scalable":[24,91],"way?":[25],"Outlier":[26],"detection":[27],"has":[28],"many":[29,107],"applications;":[30],"is":[32,101],"covered":[33],"therefore":[34],"by":[35,83],"an":[36,160],"extensive":[37,161],"literature.":[38],"The":[39],"distance-based":[40],"detectors":[41],"are":[42],"the":[43,55,72,102,134,137,166],"most":[44],"popular":[45],"ones.":[46],"However,":[47],"they":[48],"still":[49],"have":[50],"two":[51],"major":[52],"drawbacks:":[53],"(a)":[54],"intensive":[56],"neighborhood":[57],"search":[58],"that":[59,164],"takes":[60],"hours":[61],"or":[62],"even":[63],"days":[64],"complete":[66],"large":[68,150],"data,":[69,151],"and;":[70],"(b)":[71],"inability":[73],"process":[75],"attributes.":[77,114,183],"This":[78],"paper":[79],"tackles":[80],"problems":[82],"presenting":[84],"HySortOD":[85,129],":":[86],"new,":[88],"detector":[92],"for":[93],"data.":[97],"Our":[98],"main":[99],"focus":[100],"analysis":[103],"of":[104,113,118,136,146,168],"datasets":[105,121,180],"instances,":[108],"low-to-moderate":[111],"number":[112],"We":[115],"studied":[116],"dozens":[117],"real,":[119],"benchmark":[120],"up":[123,142],"one":[125],"million":[126],"instances":[127],";":[128],"outperformed":[130],"nine":[131],"competitors":[132],"from":[133,175],"state":[135],"art":[138],"runtime,":[140],"being":[141],"six":[144],"orders":[145],"magnitude":[147],"faster":[148],"while":[152],"maintaining":[153],"high":[154],"accuracy.":[155],"Finally,":[156],"we":[157],"also":[158],"performed":[159],"experimental":[162],"evaluation":[163],"confirms":[165],"ability":[167],"our":[169],"method":[170],"obtain":[172],"high-quality":[173],"results":[174],"real":[177],"synthetic":[179]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}