{"id":"https://openalex.org/W4364361380","doi":"https://doi.org/10.1186/s40537-023-00724-5","title":"Evaluating classifier performance with highly imbalanced Big Data","display_name":"Evaluating classifier performance with highly imbalanced Big Data","publication_year":2023,"publication_date":"2023-04-11","ids":{"openalex":"https://openalex.org/W4364361380","doi":"https://doi.org/10.1186/s40537-023-00724-5"},"language":"en","primary_location":{"id":"doi:10.1186/s40537-023-00724-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-023-00724-5","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-023-00724-5","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"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":"Journal of Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-023-00724-5","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047489766","display_name":"John Hancock","orcid":null},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"John T. Hancock","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, USA","institution_ids":["https://openalex.org/I63772739"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089170562","display_name":"Taghi M. Khoshgoftaar","orcid":null},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taghi M. Khoshgoftaar","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, USA","institution_ids":["https://openalex.org/I63772739"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018875253","display_name":"Justin Johnson","orcid":"https://orcid.org/0000-0003-3511-0624"},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Justin M. Johnson","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, USA","institution_ids":["https://openalex.org/I63772739"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5047489766"],"corresponding_institution_ids":["https://openalex.org/I63772739"],"apc_list":{"value":2290,"currency":"USD","value_usd":2290},"apc_paid":{"value":2290,"currency":"USD","value_usd":2290},"fwci":13.1625,"has_fulltext":true,"cited_by_count":102,"citation_normalized_percentile":{"value":0.99202368,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"10","issue":"1","first_page":null,"last_page":null},"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/T13429","display_name":"Electricity Theft Detection Techniques","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9882000088691711,"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/computer-science","display_name":"Computer science","score":0.7882592678070068},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.6336268186569214},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5968177914619446},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5844680666923523},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5589317679405212},{"id":"https://openalex.org/keywords/undersampling","display_name":"Undersampling","score":0.5552915930747986},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5343407988548279},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.5327109694480896},{"id":"https://openalex.org/keywords/receiver-operating-characteristic","display_name":"Receiver operating characteristic","score":0.5244408249855042},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5065690279006958},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4687640368938446},{"id":"https://openalex.org/keywords/f1-score","display_name":"F1 score","score":0.4254816770553589},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34561866521835327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7882592678070068},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.6336268186569214},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5968177914619446},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5844680666923523},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5589317679405212},{"id":"https://openalex.org/C136536468","wikidata":"https://www.wikidata.org/wiki/Q1225894","display_name":"Undersampling","level":2,"score":0.5552915930747986},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5343407988548279},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.5327109694480896},{"id":"https://openalex.org/C58471807","wikidata":"https://www.wikidata.org/wiki/Q327120","display_name":"Receiver operating characteristic","level":2,"score":0.5244408249855042},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5065690279006958},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4687640368938446},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.4254816770553589},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34561866521835327},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s40537-023-00724-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-023-00724-5","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-023-00724-5","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"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":"Journal of Big Data","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b3663037dfe34ae08c3c8d4d6090fa4e","is_oa":true,"landing_page_url":"https://doaj.org/article/b3663037dfe34ae08c3c8d4d6090fa4e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Big Data, Vol 10, Iss 1, Pp 1-31 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s40537-023-00724-5","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-023-00724-5","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-023-00724-5","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"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":"Journal of Big Data","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310801","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387"},{"id":"https://openalex.org/F4320317380","display_name":"Universidad del Atl\u00e1ntico","ror":"https://ror.org/05mm1w714"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4364361380.pdf","grobid_xml":"https://content.openalex.org/works/W4364361380.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1546047689","https://openalex.org/W1966716734","https://openalex.org/W1995945562","https://openalex.org/W2056132907","https://openalex.org/W2106393550","https://openalex.org/W2118978333","https://openalex.org/W2295598076","https://openalex.org/W2303147257","https://openalex.org/W2318802957","https://openalex.org/W2542459869","https://openalex.org/W2564754306","https://openalex.org/W2887451702","https://openalex.org/W2903701969","https://openalex.org/W2911964244","https://openalex.org/W2962200422","https://openalex.org/W2962807382","https://openalex.org/W2990580840","https://openalex.org/W3005928523","https://openalex.org/W3020873385","https://openalex.org/W3035999516","https://openalex.org/W3094843711","https://openalex.org/W3094948551","https://openalex.org/W3163087324","https://openalex.org/W3165582150","https://openalex.org/W3205119553","https://openalex.org/W4212883601","https://openalex.org/W4235730433","https://openalex.org/W4246413330","https://openalex.org/W4247993926","https://openalex.org/W6614148910","https://openalex.org/W6675354045"],"related_works":["https://openalex.org/W2109073422","https://openalex.org/W2887783772","https://openalex.org/W2101754595","https://openalex.org/W4249381695","https://openalex.org/W2534887053","https://openalex.org/W2026172757","https://openalex.org/W2080076470","https://openalex.org/W4293261997","https://openalex.org/W2074765259","https://openalex.org/W4205391357"],"abstract_inverted_index":{"Abstract":[0],"Using":[1],"the":[2,61,68,91,101,108,132,135,144,165,169,195,210,227],"wrong":[3],"metrics":[4,26,53],"to":[5,70,121,199,217],"gauge":[6],"classification":[7,58,159,175],"of":[8,25,63,95,103,112,172,179,229],"highly":[9,88,191,234],"imbalanced":[10,192,235],"Big":[11,56,193,236],"Data":[12,57],"may":[13],"hide":[14,34],"important":[15],"information":[16,201],"in":[17,40,82,107,177],"experimental":[18],"results.":[19],"However,":[20,174],"we":[21,44,66],"find":[22],"that":[23,46,152,164,209],"analysis":[24],"for":[27,190,225],"performance":[28,52,102,170,228],"evaluation":[29],"and":[30,141,205],"what":[31],"they":[32],"can":[33],"or":[35],"reveal":[36,163],"is":[37,119,216,220],"rarely":[38],"covered":[39],"related":[41],"works.":[42],"Therefore,":[43],"address":[45],"gap":[47],"by":[48],"analyzing":[49],"multiple":[50],"popular":[51],"on":[54],"three":[55,72],"tasks.":[59],"To":[60],"best":[62],"our":[64],"knowledge,":[65],"are":[67,86,93,128],"first":[69],"utilize":[71],"new":[73],"Medicare":[74,113],"insurance":[75],"claims":[76],"datasets":[77,85,92],"which":[78],"became":[79],"publicly":[80],"available":[81],"2021.":[83],"These":[84],"all":[87],"imbalanced.":[89],"Furthermore,":[90],"comprised":[94],"completely":[96],"different":[97],"data.":[98],"We":[99,150,187],"evaluate":[100],"five":[104,123],"ensemble":[105],"learners":[106],"Machine":[109],"Learning":[110],"task":[111],"fraud":[114],"detection.":[115],"Random":[116],"Undersampling":[117],"(RUS)":[118],"applied":[120],"induce":[122],"class":[124],"ratios.":[125],"The":[126],"classifiers":[127,230],"evaluated":[129],"with":[130,233],"both":[131],"Area":[133,142],"Under":[134,143],"Receiver":[136],"Operating":[137],"Characteristic":[138],"Curve":[139,147],"(AUC),":[140],"Precision":[145],"Recall":[146],"(AUPRC)":[148],"metrics.":[149],"show":[151,181,188,218],"AUPRC":[153,180,211,219],"provides":[154],"a":[155,184,221],"better":[156],"insight":[157],"into":[158],"performance.":[160],"Our":[161,214],"findings":[162],"AUC":[166,196],"metric":[167,197,212,224],"hides":[168],"impact":[171],"RUS.":[173],"results":[176],"terms":[178],"RUS":[182],"has":[183],"detrimental":[185],"effect.":[186],"that,":[189],"Data,":[194],"fails":[198],"capture":[200],"about":[202],"precision":[203],"scores":[204],"false":[206],"positive":[207],"counts":[208],"reveals.":[213],"contribution":[215],"more":[222],"effective":[223],"evaluating":[226],"when":[231],"working":[232],"Data.":[237]},"counts_by_year":[{"year":2026,"cited_by_count":29},{"year":2025,"cited_by_count":39},{"year":2024,"cited_by_count":23},{"year":2023,"cited_by_count":11}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}