{"id":"https://openalex.org/W4308333922","doi":"https://doi.org/10.3390/axioms11110607","title":"A Method for Analyzing the Performance Impact of Imbalanced Binary Data on Machine Learning Models","display_name":"A Method for Analyzing the Performance Impact of Imbalanced Binary Data on Machine Learning Models","publication_year":2022,"publication_date":"2022-11-01","ids":{"openalex":"https://openalex.org/W4308333922","doi":"https://doi.org/10.3390/axioms11110607"},"language":"en","primary_location":{"id":"doi:10.3390/axioms11110607","is_oa":true,"landing_page_url":"https://doi.org/10.3390/axioms11110607","pdf_url":"https://www.mdpi.com/2075-1680/11/11/607/pdf?version=1669033749","source":{"id":"https://openalex.org/S4210173132","display_name":"Axioms","issn_l":"2075-1680","issn":["2075-1680"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Axioms","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2075-1680/11/11/607/pdf?version=1669033749","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016980869","display_name":"Ming Zheng","orcid":"https://orcid.org/0000-0001-9001-0859"},"institutions":[{"id":"https://openalex.org/I4210145049","display_name":"Anhui Institute of Information Technology","ror":"https://ror.org/04mw2ty13","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210145049"]},{"id":"https://openalex.org/I4472751","display_name":"Anhui Normal University","ror":"https://ror.org/05fsfvw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I4472751"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ming Zheng","raw_affiliation_strings":["Anhui Provincial Key Laboratory of Network and Information Security, Wuhu 241002, China","School of Computer and Information, Anhui Normal University, Wuhu 241002, China"],"raw_orcid":"https://orcid.org/0000-0001-9001-0859","affiliations":[{"raw_affiliation_string":"Anhui Provincial Key Laboratory of Network and Information Security, Wuhu 241002, China","institution_ids":["https://openalex.org/I4210145049"]},{"raw_affiliation_string":"School of Computer and Information, Anhui Normal University, Wuhu 241002, China","institution_ids":["https://openalex.org/I4472751"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100455958","display_name":"Fei Wang","orcid":"https://orcid.org/0000-0003-3462-8472"},"institutions":[{"id":"https://openalex.org/I4472751","display_name":"Anhui Normal University","ror":"https://ror.org/05fsfvw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I4472751"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Wang","raw_affiliation_strings":["School of Computer and Information, Anhui Normal University, Wuhu 241002, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Information, Anhui Normal University, Wuhu 241002, China","institution_ids":["https://openalex.org/I4472751"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026617513","display_name":"Xiaowen Hu","orcid":"https://orcid.org/0000-0002-3727-6049"},"institutions":[{"id":"https://openalex.org/I4472751","display_name":"Anhui Normal University","ror":"https://ror.org/05fsfvw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I4472751"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaowen Hu","raw_affiliation_strings":["School of Computer and Information, Anhui Normal University, Wuhu 241002, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Information, Anhui Normal University, Wuhu 241002, China","institution_ids":["https://openalex.org/I4472751"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032636617","display_name":"Yuhao Miao","orcid":"https://orcid.org/0009-0009-3058-563X"},"institutions":[{"id":"https://openalex.org/I4472751","display_name":"Anhui Normal University","ror":"https://ror.org/05fsfvw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I4472751"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhao Miao","raw_affiliation_strings":["Affiliated Institution of Anhui Normal University, Wuhu 241002, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Affiliated Institution of Anhui Normal University, Wuhu 241002, China","institution_ids":["https://openalex.org/I4472751"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039969928","display_name":"Huo Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I4472751","display_name":"Anhui Normal University","ror":"https://ror.org/05fsfvw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I4472751"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huo Cao","raw_affiliation_strings":["School of Computer and Information, Anhui Normal University, Wuhu 241002, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Information, Anhui Normal University, Wuhu 241002, China","institution_ids":["https://openalex.org/I4472751"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085145640","display_name":"Mingjing Tang","orcid":"https://orcid.org/0000-0003-0435-8854"},"institutions":[{"id":"https://openalex.org/I120825670","display_name":"Yunnan Normal University","ror":"https://ror.org/00sc9n023","country_code":"CN","type":"education","lineage":["https://openalex.org/I120825670"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mingjing Tang","raw_affiliation_strings":["Engineering Research Center of Sustainable Development and Utilization of Biomass Energy, Ministry of Education, Yunnan Normal University, Kunming 650500, China","School of Life Science, Yunnan Normal University, Kunming 650500, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Research Center of Sustainable Development and Utilization of Biomass Energy, Ministry of Education, Yunnan Normal University, Kunming 650500, China","institution_ids":["https://openalex.org/I120825670"]},{"raw_affiliation_string":"School of Life Science, Yunnan Normal University, Kunming 650500, China","institution_ids":["https://openalex.org/I120825670"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5016980869","https://openalex.org/A5085145640"],"corresponding_institution_ids":["https://openalex.org/I120825670","https://openalex.org/I4210145049","https://openalex.org/I4472751"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":4.7165,"has_fulltext":true,"cited_by_count":38,"citation_normalized_percentile":{"value":0.95485091,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"11","issue":"11","first_page":"607","last_page":"607"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9810000061988831,"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/T13429","display_name":"Electricity Theft Detection Techniques","score":0.9794999957084656,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.8591800928115845},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.818081259727478},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7626010775566101},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.7373772859573364},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.671955943107605},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.5429049134254456},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5062798261642456},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.5010232925415039},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.48780444264411926},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37945497035980225},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.264840304851532},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1915903091430664},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09652042388916016}],"concepts":[{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.8591800928115845},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.818081259727478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7626010775566101},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.7373772859573364},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.671955943107605},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.5429049134254456},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5062798261642456},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.5010232925415039},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.48780444264411926},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37945497035980225},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.264840304851532},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1915903091430664},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09652042388916016},{"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/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/axioms11110607","is_oa":true,"landing_page_url":"https://doi.org/10.3390/axioms11110607","pdf_url":"https://www.mdpi.com/2075-1680/11/11/607/pdf?version=1669033749","source":{"id":"https://openalex.org/S4210173132","display_name":"Axioms","issn_l":"2075-1680","issn":["2075-1680"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Axioms","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:929d09e3eb5c4d58bb5eab3179d0ce27","is_oa":true,"landing_page_url":"https://doaj.org/article/929d09e3eb5c4d58bb5eab3179d0ce27","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":"Axioms, Vol 11, Iss 11, p 607 (2022)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2075-1680/11/11/607/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/axioms11110607","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"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":"Axioms; Volume 11; Issue 11; Pages: 607","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/axioms11110607","is_oa":true,"landing_page_url":"https://doi.org/10.3390/axioms11110607","pdf_url":"https://www.mdpi.com/2075-1680/11/11/607/pdf?version=1669033749","source":{"id":"https://openalex.org/S4210173132","display_name":"Axioms","issn_l":"2075-1680","issn":["2075-1680"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Axioms","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320328006","display_name":"Anhui Normal University","ror":"https://ror.org/05fsfvw79"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4308333922.pdf","grobid_xml":"https://content.openalex.org/works/W4308333922.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W2087824068","https://openalex.org/W2097521902","https://openalex.org/W2101234009","https://openalex.org/W2106479238","https://openalex.org/W2148143831","https://openalex.org/W2589805776","https://openalex.org/W2598548966","https://openalex.org/W2913306795","https://openalex.org/W2915691082","https://openalex.org/W2918408501","https://openalex.org/W2943045886","https://openalex.org/W2944544772","https://openalex.org/W2948000013","https://openalex.org/W2953675148","https://openalex.org/W2962981269","https://openalex.org/W2963566126","https://openalex.org/W2966679659","https://openalex.org/W2979389376","https://openalex.org/W2979824173","https://openalex.org/W2981905647","https://openalex.org/W2985783697","https://openalex.org/W2989219518","https://openalex.org/W2997531808","https://openalex.org/W3010795489","https://openalex.org/W3039142166","https://openalex.org/W3045882059","https://openalex.org/W3097863389","https://openalex.org/W3185843640","https://openalex.org/W3195631217","https://openalex.org/W3207518904","https://openalex.org/W4221029256","https://openalex.org/W4226182453","https://openalex.org/W4283073771","https://openalex.org/W4285248321","https://openalex.org/W6675354045"],"related_works":["https://openalex.org/W2766503024","https://openalex.org/W2781247653","https://openalex.org/W4206637278","https://openalex.org/W4386005305","https://openalex.org/W4386214543","https://openalex.org/W3082051559","https://openalex.org/W1969988626","https://openalex.org/W1682621979","https://openalex.org/W2141301039","https://openalex.org/W2999368888"],"abstract_inverted_index":{"Machine":[0],"learning":[1,20,40,53,65,128,146,156,170,283],"models":[2,54,66,147,157,171],"may":[3],"not":[4,205],"be":[5,270],"able":[6],"to":[7,83,95,121,207,272],"effectively":[8],"learn":[9],"and":[10,21,55,117,134,190,199,204,222,242,266],"predict":[11],"from":[12],"imbalanced":[13,35,68,76,86,161,181,208,239,259,278],"data":[14,22,37,77,240,260,280],"in":[15,51,93,237],"the":[16,31,46,60,72,75,85,101,110,123,139,165,174,179,184,212,215,256,274],"fields":[17],"of":[18,34,63,107,126,136,144,151,168,176,187,277],"machine":[19,39,52,64,127,145,155,169,282],"mining.":[23],"This":[24],"study":[25],"proposed":[26,73],"a":[27],"method":[28,143,234],"for":[29],"analyzing":[30],"performance":[32,50,61,125,140,167,275],"impact":[33,276],"binary":[36,69,279],"on":[38,67,132,158,178,264,281],"models.":[41,129,284],"It":[42],"systematically":[43],"analyzes":[44],"1.":[45],"relationship":[47],"between":[48],"varying":[49,90],"imbalance":[56],"rate":[57],"(IR);":[58],"2.":[59],"stability":[62,141],"data.":[70,182,209],"In":[71,210,255],"method,":[74],"augmentation":[78,261],"algorithms":[79],"are":[80,119,192,201],"first":[81],"designed":[82],"obtain":[84,96,249],"dataset":[87],"with":[88,173],"gradually":[89],"IR.":[91],"Then,":[92],"order":[94],"more":[97],"objective":[98],"classification":[99,124,166,185,218],"results,":[100],"evaluation":[102,142],"metric":[103],"AFG,":[104],"arithmetic":[105],"mean":[106],"area":[108],"under":[109],"receiver":[111],"operating":[112],"characteristic":[113],"curve":[114],"(AUC),":[115],"F-measure":[116],"G-mean":[118],"used":[120,154,236,271],"evaluate":[122],"Finally,":[130],"based":[131,263],"AFG":[133],"coefficient":[135],"variation":[137],"(CV),":[138],"is":[148,235],"proposed.":[149],"Experiments":[150],"eight":[152],"widely":[153],"48":[159],"different":[160],"datasets":[162],"demonstrate":[163],"that":[164],"decreases":[172],"increase":[175],"IR":[177],"same":[180],"Meanwhile,":[183],"performances":[186],"LR,":[188],"DT":[189],"SVC":[191],"unstable,":[193],"while":[194],"GNB,":[195],"BNB,":[196],"KNN,":[197],"RF":[198],"GBDT":[200],"relatively":[202],"stable":[203,217],"susceptible":[206],"particular,":[211],"BNB":[213],"has":[214],"most":[216],"performance.":[219],"The":[220,232],"Friedman":[221],"Nemenyi":[223],"post":[224],"hoc":[225],"statistical":[226],"tests":[227],"also":[228],"confirmed":[229],"this":[230],"result.":[231],"SMOTE":[233],"oversampling-based":[238],"augmentation,":[241],"determining":[243],"whether":[244],"other":[245],"oversampling":[246],"methods":[247],"can":[248],"consistent":[250],"results":[251],"needs":[252],"further":[253],"research.":[254],"future,":[257],"an":[258],"algorithm":[262],"undersampling":[265],"hybrid":[267],"sampling":[268],"should":[269],"analyze":[273]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":11}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2022-11-11T00:00:00"}