{"id":"https://openalex.org/W1965895350","doi":"https://doi.org/10.1145/1007730.1007734","title":"Mining with rarity","display_name":"Mining with rarity","publication_year":2004,"publication_date":"2004-06-01","ids":{"openalex":"https://openalex.org/W1965895350","doi":"https://doi.org/10.1145/1007730.1007734","mag":"1965895350"},"language":"en","primary_location":{"id":"doi:10.1145/1007730.1007734","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1007730.1007734","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGKDD Explorations Newsletter","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/A5073269476","display_name":"Gary M. Weiss","orcid":"https://orcid.org/0000-0001-5009-7101"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gary M. Weiss","raw_affiliation_strings":["AT&T Laboratories, Piscataway, NJ"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&T Laboratories, Piscataway, NJ","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5073269476"],"corresponding_institution_ids":["https://openalex.org/I1283103587"],"apc_list":null,"apc_paid":null,"fwci":51.4333,"has_fulltext":false,"cited_by_count":1387,"citation_normalized_percentile":{"value":0.9986152,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"6","issue":"1","first_page":"7","last_page":"19"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9994000196456909,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9994000196456909,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9991000294685364,"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.988099992275238,"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":0.767162561416626},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5962942242622375},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5554556846618652},{"id":"https://openalex.org/keywords/rare-events","display_name":"Rare events","score":0.4663471579551697},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3409436345100403},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.10517260432243347},{"id":"https://openalex.org/keywords/archaeology","display_name":"Archaeology","score":0.07753831148147583}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.767162561416626},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5962942242622375},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5554556846618652},{"id":"https://openalex.org/C2777317252","wikidata":"https://www.wikidata.org/wiki/Q18393516","display_name":"Rare events","level":2,"score":0.4663471579551697},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3409436345100403},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.10517260432243347},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.07753831148147583},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1007730.1007734","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1007730.1007734","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGKDD Explorations Newsletter","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W85350352","https://openalex.org/W117266877","https://openalex.org/W141301003","https://openalex.org/W142793689","https://openalex.org/W145450961","https://openalex.org/W146100937","https://openalex.org/W167016754","https://openalex.org/W1487629352","https://openalex.org/W1503432700","https://openalex.org/W1504694836","https://openalex.org/W1509515766","https://openalex.org/W1525877877","https://openalex.org/W1528025004","https://openalex.org/W1535842702","https://openalex.org/W1540371141","https://openalex.org/W1563938718","https://openalex.org/W1570188672","https://openalex.org/W1580049798","https://openalex.org/W1588282782","https://openalex.org/W1594031697","https://openalex.org/W1595468493","https://openalex.org/W1605695115","https://openalex.org/W1606760692","https://openalex.org/W1639032689","https://openalex.org/W1670263352","https://openalex.org/W1917795079","https://openalex.org/W1935940263","https://openalex.org/W1941659294","https://openalex.org/W1964061843","https://openalex.org/W1977245551","https://openalex.org/W1986383870","https://openalex.org/W1991597981","https://openalex.org/W1993989674","https://openalex.org/W2000106226","https://openalex.org/W2023299139","https://openalex.org/W2096123080","https://openalex.org/W2096942889","https://openalex.org/W2114968414","https://openalex.org/W2119157339","https://openalex.org/W2125055259","https://openalex.org/W2125815042","https://openalex.org/W2136865157","https://openalex.org/W2136903812","https://openalex.org/W2143534004","https://openalex.org/W2145227912","https://openalex.org/W2147834490","https://openalex.org/W2148143831","https://openalex.org/W2152150600","https://openalex.org/W2152325113","https://openalex.org/W2155653793","https://openalex.org/W2166559705","https://openalex.org/W2170335877","https://openalex.org/W2914782308","https://openalex.org/W2914859268","https://openalex.org/W2914933231","https://openalex.org/W2997149703","https://openalex.org/W2999549716","https://openalex.org/W3085162807","https://openalex.org/W4231022671","https://openalex.org/W4285719527","https://openalex.org/W4365800092","https://openalex.org/W4376490867"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655","https://openalex.org/W2359140296"],"abstract_inverted_index":{"Rare":[0],"objects":[1],"are":[2,31,41,71,76,115,122],"often":[3],"of":[4,22,38,69,97,120],"great":[5,8],"interest":[6],"and":[7,34,53,112,131],"value.":[9],"Until":[10],"recently,":[11],"however,":[12],"rarity":[13,70,101,121],"has":[14],"not":[15],"received":[16],"much":[17],"attention":[18],"in":[19,57,73,102],"the":[20,35,48,98,134],"context":[21],"data":[23,58,103,129],"mining.":[24,59,104],"Now,":[25],"as":[26,75],"increasingly":[27],"complex":[28],"real-world":[29],"problems":[30,61,127],"addressed,":[32],"rarity,":[33],"related":[36],"problem":[37],"imbalanced":[39],"data,":[40],"taking":[42],"center":[43],"stage.":[44],"This":[45,105],"article":[46,92,106],"discusses":[47],"role":[49],"that":[50,62,90,109],"rare":[51,54,110,113],"classes":[52,111],"cases":[55,114],"play":[56],"The":[60],"can":[63],"result":[64],"from":[65,86,133],"these":[66,80],"two":[67],"forms":[68,119],"described":[72],"detail,":[74],"methods":[77],"for":[78],"addressing":[79],"problems.":[81],"These":[82],"descriptions":[83],"utilize":[84],"examples":[85],"existing":[87],"research.":[88],"So":[89],"this":[91],"provides":[93],"a":[94],"good":[95],"survey":[96],"literature":[99],"on":[100],"also":[107],"demonstrates":[108],"very":[116],"similar":[117,126],"phenomena---both":[118],"shown":[123],"to":[124],"cause":[125],"during":[128],"mining":[130],"benefit":[132],"same":[135],"remediation":[136],"methods.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":17},{"year":2025,"cited_by_count":38},{"year":2024,"cited_by_count":42},{"year":2023,"cited_by_count":52},{"year":2022,"cited_by_count":60},{"year":2021,"cited_by_count":73},{"year":2020,"cited_by_count":87},{"year":2019,"cited_by_count":96},{"year":2018,"cited_by_count":74},{"year":2017,"cited_by_count":67},{"year":2016,"cited_by_count":68},{"year":2015,"cited_by_count":77},{"year":2014,"cited_by_count":85},{"year":2013,"cited_by_count":69},{"year":2012,"cited_by_count":98}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2016-06-24T00:00:00"}