{"id":"https://openalex.org/W2904542630","doi":"https://doi.org/10.1609/aaai.v33i01.33014039","title":"Precision-Recall versus Accuracy and the Role of Large Data Sets","display_name":"Precision-Recall versus Accuracy and the Role of Large Data Sets","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2904542630","doi":"https://doi.org/10.1609/aaai.v33i01.33014039","mag":"2904542630"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33014039","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33014039","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/5193/5059","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/5193/5059","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064954992","display_name":"Brendan Juba","orcid":"https://orcid.org/0000-0001-6542-833X"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Brendan Juba","raw_affiliation_strings":["Washington University in St. Louis"],"affiliations":[{"raw_affiliation_string":"Washington University in St. Louis","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111386493","display_name":"Hai Son Le","orcid":"https://orcid.org/0009-0003-2240-0451"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hai S. Le","raw_affiliation_strings":["Washington University in St. Louis"],"affiliations":[{"raw_affiliation_string":"Washington University in St. Louis","institution_ids":["https://openalex.org/I204465549"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5064954992"],"corresponding_institution_ids":["https://openalex.org/I204465549"],"apc_list":null,"apc_paid":null,"fwci":14.6308,"has_fulltext":true,"cited_by_count":305,"citation_normalized_percentile":{"value":0.9893635,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"33","issue":"01","first_page":"4039","last_page":"4048"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T11653","display_name":"Financial Distress and Bankruptcy Prediction","score":0.9905999898910522,"subfield":{"id":"https://openalex.org/subfields/1402","display_name":"Accounting"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9900000095367432,"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/precision-and-recall","display_name":"Precision and recall","score":0.6367270946502686},{"id":"https://openalex.org/keywords/corollary","display_name":"Corollary","score":0.594917893409729},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.579382061958313},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.579003632068634},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.5761824250221252},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5619832873344421},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5452098250389099},{"id":"https://openalex.org/keywords/vc-dimension","display_name":"VC dimension","score":0.4768356382846832},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3697739243507385},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3460495173931122},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3108850121498108},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13066378235816956},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.12684369087219238}],"concepts":[{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.6367270946502686},{"id":"https://openalex.org/C2780012671","wikidata":"https://www.wikidata.org/wiki/Q1343870","display_name":"Corollary","level":2,"score":0.594917893409729},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.579382061958313},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.579003632068634},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.5761824250221252},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5619832873344421},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5452098250389099},{"id":"https://openalex.org/C119322782","wikidata":"https://www.wikidata.org/wiki/Q2662236","display_name":"VC dimension","level":2,"score":0.4768356382846832},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3697739243507385},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3460495173931122},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3108850121498108},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13066378235816956},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.12684369087219238},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v33i01.33014039","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33014039","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/5193/5059","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33014039","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33014039","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/5193/5059","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3205609911","display_name":null,"funder_award_id":"CCF-1718380","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8973285213","display_name":"AF: Small: Integrated Knowledge Discovery and Analysis Using Sum-of-Squares Proofs","funder_award_id":"1718380","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2904542630.pdf","grobid_xml":"https://content.openalex.org/works/W2904542630.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W478671","https://openalex.org/W1499397922","https://openalex.org/W1521626219","https://openalex.org/W1542886316","https://openalex.org/W1551909886","https://openalex.org/W1564947197","https://openalex.org/W1591252468","https://openalex.org/W1861993554","https://openalex.org/W1941659294","https://openalex.org/W1965895350","https://openalex.org/W1976526581","https://openalex.org/W1993220166","https://openalex.org/W1994592916","https://openalex.org/W2029538739","https://openalex.org/W2045313701","https://openalex.org/W2056614917","https://openalex.org/W2067214947","https://openalex.org/W2101234009","https://openalex.org/W2104167780","https://openalex.org/W2107295961","https://openalex.org/W2109664771","https://openalex.org/W2114968414","https://openalex.org/W2117244863","https://openalex.org/W2118978333","https://openalex.org/W2120100126","https://openalex.org/W2125055259","https://openalex.org/W2148143831","https://openalex.org/W2154952480","https://openalex.org/W2438298867","https://openalex.org/W2508465722","https://openalex.org/W2521200999","https://openalex.org/W2964179321","https://openalex.org/W3155649056","https://openalex.org/W4238284510","https://openalex.org/W4293399083","https://openalex.org/W4293467142","https://openalex.org/W4293713156","https://openalex.org/W6600014930","https://openalex.org/W6625667212","https://openalex.org/W6629782617","https://openalex.org/W6631239350","https://openalex.org/W6640479084","https://openalex.org/W6675354045","https://openalex.org/W6675732969","https://openalex.org/W6676373471","https://openalex.org/W6677770173","https://openalex.org/W6677954473","https://openalex.org/W6724911422","https://openalex.org/W6758539934"],"related_works":["https://openalex.org/W2376029318","https://openalex.org/W2388301251","https://openalex.org/W3013941779","https://openalex.org/W1998659141","https://openalex.org/W3195376785","https://openalex.org/W2358294942","https://openalex.org/W4367460280","https://openalex.org/W4328049145","https://openalex.org/W2900966163","https://openalex.org/W2904542630"],"abstract_inverted_index":{"Practitioners":[0],"of":[1,13,23,52,61,68,74,81,87,111,116,132,146,157,167,175],"data":[2,17],"mining":[3],"and":[4,91,118,149,179],"machine":[5,53],"learning":[6,54,70],"have":[7,36],"long":[8],"observed":[9],"that":[10,27,122,137,171],"the":[11,21,48,59,72,79,92,95,109,130,139,144,147,158,162],"imbalance":[12,60,97],"classes":[14,62],"in":[15,114],"a":[16,82,85,120,153,172,185],"set":[18],"negatively":[19],"impacts":[20],"quality":[22],"classifiers":[24],"trained":[25],"on":[26,58],"data.":[28,134],"Numerous":[29],"techniques":[30],"for":[31],"coping":[32],"with":[33],"such":[34],"imbalances":[35],"been":[37],"proposed,":[38],"but":[39],"nearly":[40],"all":[41],"lack":[42],"any":[43],"theoretical":[44,50],"grounding.":[45],"By":[46],"contrast,":[47],"standard":[49],"analysis":[51],"admits":[55],"no":[56],"dependence":[57],"at":[63],"all.":[64],"The":[65],"basic":[66],"theorems":[67],"statistical":[69],"establish":[71],"number":[73,174],"examples":[75,176],"needed":[76],"to":[77,129,181],"estimate":[78],"accuracy":[80,159],"classifier":[83,112],"as":[84,126],"function":[86],"its":[88],"complexity":[89],"(VC-dimension)":[90],"confidence":[93],"desired;":[94],"class":[96,163,183],"does":[98],"not":[99],"enter":[100],"these":[101],"formulas":[102],"anywhere.":[103],"In":[104],"this":[105,168],"work,":[106],"we":[107,187],"consider":[108],"measures":[110],"performance":[113],"terms":[115],"precision":[117,140,148],"recall,":[119],"measure":[121],"is":[123,141,151,170,177],"widely":[124],"suggested":[125],"more":[127],"appropriate":[128],"classification":[131],"imbalanced":[133],"We":[135],"observe":[136],"whenever":[138],"moderately":[142],"large,":[143],"worse":[145],"recall":[150],"within":[152],"small":[154],"constant":[155],"factor":[156],"weighted":[160],"by":[161],"imbalance.":[164],"A":[165],"corollary":[166],"observation":[169],"larger":[173],"necessary":[178],"sufficient":[180],"address":[182],"imbalance,":[184],"finding":[186],"also":[188],"illustrate":[189],"empirically.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":12},{"year":2025,"cited_by_count":62},{"year":2024,"cited_by_count":66},{"year":2023,"cited_by_count":55},{"year":2022,"cited_by_count":66},{"year":2021,"cited_by_count":28},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-11T08:14:18.477133","created_date":"2025-10-10T00:00:00"}