{"id":"https://openalex.org/W3135957118","doi":"https://doi.org/10.1007/s10618-022-00856-x","title":"Robust subgroup discovery","display_name":"Robust subgroup discovery","publication_year":2022,"publication_date":"2022-08-12","ids":{"openalex":"https://openalex.org/W3135957118","doi":"https://doi.org/10.1007/s10618-022-00856-x","mag":"3135957118"},"language":"en","primary_location":{"id":"doi:10.1007/s10618-022-00856-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10618-022-00856-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10618-022-00856-x.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":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10618-022-00856-x.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068912127","display_name":"Hugo Manuel Proen\u00e7a","orcid":"https://orcid.org/0000-0001-7315-5925"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hugo M. Proen\u00e7a","raw_affiliation_strings":["LIACS, Niels Bohrweg 1, 2333, Leiden, CA, Netherlands"],"affiliations":[{"raw_affiliation_string":"LIACS, Niels Bohrweg 1, 2333, Leiden, CA, Netherlands","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079050279","display_name":"Peter Gr\u00fcnwald","orcid":"https://orcid.org/0000-0001-9832-9936"},"institutions":[{"id":"https://openalex.org/I1341640284","display_name":"Centrum Wiskunde & Informatica","ror":"https://ror.org/00x7ekv49","country_code":"NL","type":"facility","lineage":["https://openalex.org/I1341640284","https://openalex.org/I2800991832"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Peter Gr\u00fcnwald","raw_affiliation_strings":["CWI, Science Park 123, 1098, XG Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"CWI, Science Park 123, 1098, XG Amsterdam, Netherlands","institution_ids":["https://openalex.org/I1341640284"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062646838","display_name":"Thomas B\u00e4ck","orcid":"https://orcid.org/0000-0001-6768-1478"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas B\u00e4ck","raw_affiliation_strings":["LIACS, Niels Bohrweg 1, 2333, Leiden, CA, Netherlands"],"affiliations":[{"raw_affiliation_string":"LIACS, Niels Bohrweg 1, 2333, Leiden, CA, Netherlands","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022646570","display_name":"Matthijs van Leeuwen","orcid":"https://orcid.org/0000-0002-0510-3549"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matthijs van Leeuwen","raw_affiliation_strings":["LIACS, Niels Bohrweg 1, 2333, Leiden, CA, Netherlands"],"affiliations":[{"raw_affiliation_string":"LIACS, Niels Bohrweg 1, 2333, Leiden, CA, Netherlands","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5068912127"],"corresponding_institution_ids":[],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":1.9319,"has_fulltext":true,"cited_by_count":15,"citation_normalized_percentile":{"value":0.87608459,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"36","issue":"5","first_page":"1885","last_page":"1970"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9965999722480774,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9965999722480774,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.991599977016449,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9879999756813049,"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/univariate","display_name":"Univariate","score":0.6213455200195312},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5939158797264099},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5399641394615173},{"id":"https://openalex.org/keywords/minimum-description-length","display_name":"Minimum description length","score":0.519936740398407},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5000655651092529},{"id":"https://openalex.org/keywords/multinomial-distribution","display_name":"Multinomial distribution","score":0.468932181596756},{"id":"https://openalex.org/keywords/subgroup-analysis","display_name":"Subgroup analysis","score":0.4201778471469879},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3386678993701935},{"id":"https://openalex.org/keywords/multivariate-statistics","display_name":"Multivariate statistics","score":0.3276281952857971},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3206806480884552},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.27726081013679504},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.24039563536643982}],"concepts":[{"id":"https://openalex.org/C199163554","wikidata":"https://www.wikidata.org/wiki/Q1681619","display_name":"Univariate","level":3,"score":0.6213455200195312},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5939158797264099},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5399641394615173},{"id":"https://openalex.org/C87465248","wikidata":"https://www.wikidata.org/wiki/Q1417790","display_name":"Minimum description length","level":2,"score":0.519936740398407},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5000655651092529},{"id":"https://openalex.org/C192065140","wikidata":"https://www.wikidata.org/wiki/Q1147928","display_name":"Multinomial distribution","level":2,"score":0.468932181596756},{"id":"https://openalex.org/C187960798","wikidata":"https://www.wikidata.org/wiki/Q7631152","display_name":"Subgroup analysis","level":3,"score":0.4201778471469879},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3386678993701935},{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.3276281952857971},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3206806480884552},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27726081013679504},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.24039563536643982},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1007/s10618-022-00856-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10618-022-00856-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10618-022-00856-x.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"},{"id":"pmh:oai:arXiv.org:2103.13686","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.13686","pdf_url":"https://arxiv.org/pdf/2103.13686","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:cwi.nl:32006","is_oa":true,"landing_page_url":"https://ir.cwi.nl/pub/32006","pdf_url":"https://ir.cwi.nl/pub/32006/32006.pdf","source":{"id":"https://openalex.org/S7407055335","display_name":"Centrum Wiskunde & Informatica (CWI), the national research institute for mathematics and computer science in the Netherlands","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data Mining and Knowledge Discovery vol. 36, pp. 1885-1970","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:scholarlypublications.universiteitleiden.nl:item_3486278","is_oa":true,"landing_page_url":"https://hdl.handle.net/1887/3486278","pdf_url":null,"source":{"id":"https://openalex.org/S4306400850","display_name":"Leiden Repository (Leiden University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I121797337","host_organization_name":"Leiden University","host_organization_lineage":["https://openalex.org/I121797337"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data Mining and Knowledge Discovery","raw_type":"Article / Letter to editor"},{"id":"pmh:ul:oai:scholarlypublications.universiteitleiden.nl:item_3486278","is_oa":true,"landing_page_url":"http://hdl.handle.net/1887/3486278","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data Mining and Knowledge Discovery, 36(5), 1885 - 1970. SPRINGER","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1007/s10618-022-00856-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10618-022-00856-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10618-022-00856-x.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":[{"id":"https://metadata.un.org/sdg/16","score":0.41999998688697815,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G629491556","display_name":null,"funder_award_id":"(NWO)","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G7372230341","display_name":null,"funder_award_id":"629.002.201","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3135957118.pdf","grobid_xml":"https://content.openalex.org/works/W3135957118.grobid-xml"},"referenced_works_count":107,"referenced_works":["https://openalex.org/W15476721","https://openalex.org/W94191208","https://openalex.org/W135524293","https://openalex.org/W1494581921","https://openalex.org/W1536950352","https://openalex.org/W1546338409","https://openalex.org/W1565746575","https://openalex.org/W1582408924","https://openalex.org/W1594541780","https://openalex.org/W1670263352","https://openalex.org/W1671614046","https://openalex.org/W1689258902","https://openalex.org/W1947056582","https://openalex.org/W1965555277","https://openalex.org/W1978662219","https://openalex.org/W1979462644","https://openalex.org/W1995875735","https://openalex.org/W1996356638","https://openalex.org/W2010472418","https://openalex.org/W2018097250","https://openalex.org/W2029538739","https://openalex.org/W2032558547","https://openalex.org/W2054658115","https://openalex.org/W2055400097","https://openalex.org/W2058815839","https://openalex.org/W2077442669","https://openalex.org/W2089763487","https://openalex.org/W2101460669","https://openalex.org/W2104017387","https://openalex.org/W2106571168","https://openalex.org/W2106596127","https://openalex.org/W2107617008","https://openalex.org/W2113340410","https://openalex.org/W2115155679","https://openalex.org/W2116396873","https://openalex.org/W2116821125","https://openalex.org/W2118022153","https://openalex.org/W2123730855","https://openalex.org/W2124066753","https://openalex.org/W2129027474","https://openalex.org/W2132452100","https://openalex.org/W2135367988","https://openalex.org/W2135445066","https://openalex.org/W2137107481","https://openalex.org/W2146438816","https://openalex.org/W2151280208","https://openalex.org/W2153504810","https://openalex.org/W2154642793","https://openalex.org/W2159123127","https://openalex.org/W2163661152","https://openalex.org/W2166559705","https://openalex.org/W2167681385","https://openalex.org/W2168175751","https://openalex.org/W2171666258","https://openalex.org/W2182722412","https://openalex.org/W2338621248","https://openalex.org/W2511911140","https://openalex.org/W2523484136","https://openalex.org/W2564078846","https://openalex.org/W2566871804","https://openalex.org/W2586011290","https://openalex.org/W2591589908","https://openalex.org/W2597108375","https://openalex.org/W2622193037","https://openalex.org/W2744365997","https://openalex.org/W2745281314","https://openalex.org/W2754504587","https://openalex.org/W2767443199","https://openalex.org/W2900628640","https://openalex.org/W2902255491","https://openalex.org/W2913723957","https://openalex.org/W2914584367","https://openalex.org/W2943554161","https://openalex.org/W2955704562","https://openalex.org/W2963849998","https://openalex.org/W2964112969","https://openalex.org/W2984055850","https://openalex.org/W2990009472","https://openalex.org/W2997546679","https://openalex.org/W2998574808","https://openalex.org/W2998617017","https://openalex.org/W3008214279","https://openalex.org/W3020030945","https://openalex.org/W3034397712","https://openalex.org/W3045909935","https://openalex.org/W3087280012","https://openalex.org/W3098044966","https://openalex.org/W3103529187","https://openalex.org/W3104533862","https://openalex.org/W3118013975","https://openalex.org/W3120740533","https://openalex.org/W3123545922","https://openalex.org/W3124792046","https://openalex.org/W3134032527","https://openalex.org/W3197173234","https://openalex.org/W3197848353","https://openalex.org/W3201881723","https://openalex.org/W3208469385","https://openalex.org/W4212971335","https://openalex.org/W4235234743","https://openalex.org/W4236791902","https://openalex.org/W4248524623","https://openalex.org/W4255582690","https://openalex.org/W4256358309","https://openalex.org/W4286695923","https://openalex.org/W4298304654","https://openalex.org/W4388317804"],"related_works":["https://openalex.org/W1828158523","https://openalex.org/W2049578243","https://openalex.org/W2000145235","https://openalex.org/W2122079181","https://openalex.org/W1985848810","https://openalex.org/W2889939530","https://openalex.org/W2399195672","https://openalex.org/W3121881699","https://openalex.org/W2748838164","https://openalex.org/W2066015000"],"abstract_inverted_index":{"Abstract":[0],"We":[1],"introduce":[2],"the":[3,52,58,65,76,117,125,170,177,187,204],"problem":[4,118],"of":[5,14,17,80,86,96,119,233],"robust":[6,47,121],"subgroup":[7,81,104,122,151,165,173,205,228,240],"discovery":[8,105,123,229],",":[9],"i.e.,":[10,83],"finding":[11,149],"a":[12,69,159,196,212],"set":[13],"interpretable":[15],"descriptions":[16],"subsets":[18],"that":[19,93,162,169,224],"1)":[20],"stand":[21],"out":[22],"with":[23],"respect":[24],"to":[25,43,50,60,115,134,176,192,195],"one":[26],"or":[27,49,98,201],"more":[28],"target":[29,209],"attributes,":[30],"2)":[31],"are":[32,57],"statistically":[33],"robust,":[34],"and":[35,90,139,144,167,206,239],"3)":[36],"non-redundant.":[37],"Many":[38],"attempts":[39],"have":[40],"been":[41],"made":[42],"mine":[44],"either":[45],"locally":[46],"subgroups":[48],"tackle":[51],"pattern":[53],"explosion,":[54],"but":[55],"we":[56,74,132,156,218],"first":[59],"address":[61],"both":[62],"challenges":[63],"at":[64],"same":[66],"time":[67],"from":[68],"global":[70],"modelling":[71],"perspective.":[72],"First,":[73],"formulate":[75],"broad":[77],"model":[78,111],"class":[79,112],"lists,":[82],"ordered":[84],"sets":[85],"subgroups,":[87],"for":[88,142],"univariate":[89],"multivariate":[91],"targets":[92],"can":[94],"consist":[95],"nominal":[97,143],"numeric":[99,145],"variables,":[100],"including":[101],"traditional":[102],"top-1":[103],"in":[106,182,231],"its":[107],"definition.":[108],"This":[109],"novel":[110],"allows":[113],"us":[114],"formalise":[116],"optimal":[120,135,150],"using":[124],"Minimum":[126],"Description":[127],"Length":[128],"(MDL)":[129],"principle,":[130],"where":[131],"resort":[133],"Normalised":[136],"Maximum":[137],"Likelihood":[138],"Bayesian":[140,197],"encodings":[141],"targets,":[146],"respectively.":[147],"Second,":[148],"lists":[152,166],"is":[153,180,190],"NP-hard.":[154],"Therefore,":[155],"propose":[157],"SSD++,":[158],"greedy":[160,188],"heuristic":[161],"finds":[163],"good":[164],"guarantees":[168],"most":[171],"significant":[172],"found":[174],"according":[175],"MDL":[178],"criterion":[179],"added":[181],"each":[183],"iteration.":[184],"In":[185],"fact,":[186],"gain":[189],"shown":[191],"be":[193],"equivalent":[194],"one-sample":[198],"proportion,":[199],"multinomial,":[200],"t-test":[202],"between":[203],"dataset":[207],"marginal":[208],"distributions":[210],"plus":[211],"multiple":[213],"hypothesis":[214],"testing":[215],"penalty.":[216],"Furthermore,":[217],"empirically":[219],"show":[220],"on":[221,236],"54":[222],"datasets":[223],"SSD++":[225],"outperforms":[226],"previous":[227],"methods":[230],"terms":[232],"quality,":[234],"generalisation":[235],"unseen":[237],"data,":[238],"list":[241],"size.":[242]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2021-03-29T00:00:00"}