{"id":"https://openalex.org/W3087280012","doi":"https://doi.org/10.1007/s10618-020-00703-x","title":"For real: a thorough look at numeric attributes in subgroup discovery","display_name":"For real: a thorough look at numeric attributes in subgroup discovery","publication_year":2020,"publication_date":"2020-09-21","ids":{"openalex":"https://openalex.org/W3087280012","doi":"https://doi.org/10.1007/s10618-020-00703-x","mag":"3087280012"},"language":"en","primary_location":{"id":"doi:10.1007/s10618-020-00703-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10618-020-00703-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10618-020-00703-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":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10618-020-00703-x.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052942587","display_name":"Marvin Meeng","orcid":"https://orcid.org/0000-0002-6996-0478"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Marvin Meeng","raw_affiliation_strings":["LIACS, Leiden University, Leiden, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-6996-0478","affiliations":[{"raw_affiliation_string":"LIACS, Leiden University, Leiden, The Netherlands","institution_ids":["https://openalex.org/I121797337"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062278926","display_name":"Arno Knobbe","orcid":"https://orcid.org/0000-0002-0335-5099"},"institutions":[{"id":"https://openalex.org/I121797337","display_name":"Leiden University","ror":"https://ror.org/027bh9e22","country_code":"NL","type":"education","lineage":["https://openalex.org/I121797337"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Arno Knobbe","raw_affiliation_strings":["LIACS, Leiden University, Leiden, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-0335-5099","affiliations":[{"raw_affiliation_string":"LIACS, Leiden University, Leiden, The Netherlands","institution_ids":["https://openalex.org/I121797337"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5052942587"],"corresponding_institution_ids":["https://openalex.org/I121797337"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":3.0766,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.93254088,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"35","issue":"1","first_page":"158","last_page":"212"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9936000108718872,"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/computer-science","display_name":"Computer science","score":0.6274521946907043},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5769850015640259},{"id":"https://openalex.org/keywords/exploratory-data-analysis","display_name":"Exploratory data analysis","score":0.5544431209564209},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5459080338478088},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.543249249458313},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.52657151222229},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.47969648241996765},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.45316898822784424},{"id":"https://openalex.org/keywords/association-rule-learning","display_name":"Association rule learning","score":0.44161564111709595},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4356330335140228},{"id":"https://openalex.org/keywords/outcome","display_name":"Outcome (game theory)","score":0.42882031202316284},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39388328790664673},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35894009470939636},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3513597548007965},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19131454825401306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6274521946907043},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5769850015640259},{"id":"https://openalex.org/C120894424","wikidata":"https://www.wikidata.org/wiki/Q1322871","display_name":"Exploratory data analysis","level":2,"score":0.5544431209564209},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5459080338478088},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.543249249458313},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.52657151222229},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.47969648241996765},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.45316898822784424},{"id":"https://openalex.org/C193524817","wikidata":"https://www.wikidata.org/wiki/Q386780","display_name":"Association rule learning","level":2,"score":0.44161564111709595},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4356330335140228},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.42882031202316284},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39388328790664673},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35894009470939636},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3513597548007965},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19131454825401306},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10618-020-00703-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10618-020-00703-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10618-020-00703-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"}],"best_oa_location":{"id":"doi:10.1007/s10618-020-00703-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10618-020-00703-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10618-020-00703-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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320929","display_name":"Universiteit Leiden","ror":"https://ror.org/027bh9e22"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3087280012.pdf","grobid_xml":"https://content.openalex.org/works/W3087280012.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W109368050","https://openalex.org/W135524293","https://openalex.org/W160160746","https://openalex.org/W1481002266","https://openalex.org/W1484732323","https://openalex.org/W1546338409","https://openalex.org/W1565746575","https://openalex.org/W1569158104","https://openalex.org/W1585743408","https://openalex.org/W1594541780","https://openalex.org/W1678889691","https://openalex.org/W1689258902","https://openalex.org/W1937923414","https://openalex.org/W1972978214","https://openalex.org/W1976183135","https://openalex.org/W1985343487","https://openalex.org/W2000131178","https://openalex.org/W2011101028","https://openalex.org/W2031570842","https://openalex.org/W2037965136","https://openalex.org/W2038104911","https://openalex.org/W2055400097","https://openalex.org/W2064853889","https://openalex.org/W2090479884","https://openalex.org/W2103459555","https://openalex.org/W2104017387","https://openalex.org/W2106571168","https://openalex.org/W2107617008","https://openalex.org/W2113340410","https://openalex.org/W2123730855","https://openalex.org/W2124828389","https://openalex.org/W2132452100","https://openalex.org/W2136076205","https://openalex.org/W2137095888","https://openalex.org/W2149474501","https://openalex.org/W2158698691","https://openalex.org/W2238902321","https://openalex.org/W2338621248","https://openalex.org/W2400926481","https://openalex.org/W2481861024","https://openalex.org/W2566871804","https://openalex.org/W2586011290","https://openalex.org/W2626914210","https://openalex.org/W2911798963","https://openalex.org/W2914584367","https://openalex.org/W2950901155","https://openalex.org/W3118013975","https://openalex.org/W3120740533","https://openalex.org/W4212848460","https://openalex.org/W4236791902","https://openalex.org/W4238499898","https://openalex.org/W4252403066"],"related_works":["https://openalex.org/W4380150146","https://openalex.org/W3024870410","https://openalex.org/W2410652950","https://openalex.org/W4283773154","https://openalex.org/W3139174110","https://openalex.org/W4289597203","https://openalex.org/W2085630472","https://openalex.org/W1977098485","https://openalex.org/W4285201053","https://openalex.org/W4256612600"],"abstract_inverted_index":{"Abstract":[0],"Subgroup":[1],"discovery":[2,197],"(SD)":[3],"is":[4,33,78,146,152,221],"an":[5,113],"exploratory":[6],"pattern":[7],"mining":[8],"paradigm":[9],"that":[10,86],"comes":[11],"into":[12],"its":[13],"own":[14],"when":[15],"dealing":[16,100],"with":[17,38,101,234],"large":[18],"real-world":[19],"data,":[20],"which":[21,54],"typically":[22],"involves":[23],"many":[24],"attributes,":[25,40],"of":[26,29,74,106,116,120,163,172,179,193,210],"a":[27,71,83,117,191,231],"mixture":[28],"data":[30],"types.":[31],"Essential":[32],"the":[34,44,50,65,75,107,142,155,161,164,168,173,208,211,213],"ability":[35],"to":[36,95,131,224],"deal":[37],"numeric":[39,102,121,226],"whether":[41],"they":[42],"concern":[43],"target":[45],"(a":[46],"regression":[47,149],"setting)":[48],"or":[49],"description":[51],"attributes":[52],"(by":[53],"subgroups":[55],"are":[56,128,137,157,183,204],"identified).":[57],"Various":[58],"specific":[59],"algorithms":[60],"have":[61],"been":[62],"proposed":[63],"in":[64,90,93,109,123,207,230],"literature":[66],"for":[67,99,140],"both":[68,141],"cases,":[69],"but":[70],"systematic":[72],"review":[73],"available":[76],"options":[77],"missing.":[79],"This":[80],"paper":[81,111],"presents":[82],"generic":[84],"framework":[85],"can":[87,217],"be":[88,218],"instantiated":[89],"various":[91,205],"ways":[92],"order":[94],"create":[96],"different":[97],"strategies":[98,122,127,156,182],"data.":[103],"The":[104],"bulk":[105],"work":[108],"this":[110],"describes":[112],"experimental":[114],"comparison":[115],"considerable":[118],"range":[119],"SD,":[124],"where":[125],"these":[126],"organised":[129],"according":[130],"four":[132],"central":[133],"dimensions.":[134],"These":[135],"experiments":[136],"furthermore":[138],"repeated":[139],"classification":[143],"task":[144,150],"(target":[145,151],"nominal)":[147],"and":[148,154,167,170,190],"numeric),":[153],"compared":[158],"based":[159],"on":[160],"quality":[162,169],"top":[165],"subgroup,":[166],"redundancy":[171],"top-":[174],"k":[175],"result":[176],"set.":[177],"Results":[178],"three":[180],"search":[181],"compared:":[184],"traditional":[185],"beam":[186],"search,":[187,189],"complete":[188],"variant":[192],"diverse":[194],"subgroup":[195,200],"set":[196],"called":[198],"cover-based":[199],"selection.":[201],"Although":[202],"there":[203],"subtleties":[206],"outcome":[209],"experiments,":[212],"following":[214],"general":[215],"conclusions":[216],"drawn:":[219],"it":[220],"often":[222],"best":[223],"determine":[225],"thresholds":[227,241],"dynamically":[228],"(locally),":[229],"fine-grained":[232],"manner,":[233],"binary":[235],"splits,":[236],"while":[237],"considering":[238],"multiple":[239],"candidate":[240],"per":[242],"attribute.":[243]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}