{"id":"https://openalex.org/W4406416396","doi":"https://doi.org/10.1109/ic3i61595.2024.10829313","title":"Assessing the Impact of Data Imbalance on the Predictive Performance of Machine Learning Models","display_name":"Assessing the Impact of Data Imbalance on the Predictive Performance of Machine Learning Models","publication_year":2024,"publication_date":"2024-09-18","ids":{"openalex":"https://openalex.org/W4406416396","doi":"https://doi.org/10.1109/ic3i61595.2024.10829313"},"language":"en","primary_location":{"id":"doi:10.1109/ic3i61595.2024.10829313","doi":"https://doi.org/10.1109/ic3i61595.2024.10829313","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ic3i61595.2024.10829313","pdf_url":null,"source":{"id":"https://openalex.org/S7407087434","display_name":"International Conference on Contemporary Computing and Informatics (IC3I)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 7th International Conference on Contemporary Computing and Informatics (IC3I)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","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/A5107513120","display_name":"Murali Mohana Krishna Dandu","orcid":"https://orcid.org/0009-0008-5251-2661","observed_orcids":["https://orcid.org/0009-0008-5251-2661"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Murali Mohana Krishna Dandu","raw_affiliation_strings":["Independent Researcher Satyanarayana Puram,Vijayawada,Andhra Pradesh,India,520011"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher Satyanarayana Puram,Vijayawada,Andhra Pradesh,India,520011","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020106300","display_name":"Jaishree Jain","orcid":"https://orcid.org/0000-0003-0173-7664","observed_orcids":["https://orcid.org/0000-0003-0173-7664"]},"institutions":[{"id":"https://openalex.org/I4405257060","display_name":"Ajay Kumar Garg Engineering College","ror":"https://ror.org/04vddbq17","country_code":"IN","type":"education","lineage":["https://openalex.org/I4405257060"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jaishree Jain","raw_affiliation_strings":["Ajay Kumar Garg Engineering College,Department of Computer Science and Engineering,Ghaziabad,U.P,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ajay Kumar Garg Engineering College,Department of Computer Science and Engineering,Ghaziabad,U.P,India","institution_ids":["https://openalex.org/I4405257060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107474907","display_name":"Santhosh Vijayabaskar","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Santhosh Vijayabaskar","raw_affiliation_strings":["Independent Researcher,Chennai,Tamil Nadu,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher,Chennai,Tamil Nadu,India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113355040","display_name":"Punit Goel","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405258392","display_name":"Maharaja Agrasen Himalayan Garhwal University","ror":"https://ror.org/00k0pfp21","country_code":"IN","type":"education","lineage":["https://openalex.org/I4405258392"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Punit Goel","raw_affiliation_strings":["Maharaja Agrasen Himalayan Garhwal University,Uttarakhand,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Maharaja Agrasen Himalayan Garhwal University,Uttarakhand,India","institution_ids":["https://openalex.org/I4405258392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114425329","display_name":"Ashwini Shivarudra","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ashwini Shivarudra","raw_affiliation_strings":["Independent Researcher Satyanarayana Puram Chikkalasandra, Hanumagiri Nagar,Bengaluru,India,560061"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher Satyanarayana Puram Chikkalasandra, Hanumagiri Nagar,Bengaluru,India,560061","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Sachin Bhatt","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sachin Bhatt","raw_affiliation_strings":["Independent Researcher Annapurna Mandir Rd,Indore,Madhya Pradesh,India,452009"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher Annapurna Mandir Rd,Indore,Madhya Pradesh,India,452009","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9513,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.77919683,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1062","last_page":"1068"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":1.0,"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":1.0,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.0,"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/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.8289999961853027},{"id":"https://openalex.org/keywords/hybrid-sampling","display_name":"hybrid sampling","score":0.8209999799728394},{"id":"https://openalex.org/keywords/smote","display_name":"SMOTE","score":0.8970000147819519},{"id":"https://openalex.org/keywords/particle-swarm-optimization","display_name":"particle swarm optimization","score":0.8040000200271606},{"id":"https://openalex.org/keywords/minority-class-bias","display_name":"minority class bias","score":0.5519999861717224},{"id":"https://openalex.org/keywords/xgboost","display_name":"XGBoost","score":0.8370000123977661},{"id":"https://openalex.org/keywords/random-forest","display_name":"random forest","score":0.7850000262260437},{"id":"https://openalex.org/keywords/medical-data-classification","display_name":"medical data classification","score":0.5569999814033508}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6956700682640076},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5475344657897949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45432084798812866}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ic3i61595.2024.10829313","doi":"https://doi.org/10.1109/ic3i61595.2024.10829313","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ic3i61595.2024.10829313","pdf_url":null,"source":{"id":"https://openalex.org/S7407087434","display_name":"International Conference on Contemporary Computing and Informatics (IC3I)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 7th International Conference on Contemporary Computing and Informatics (IC3I)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7390999794006348,"display_name":"Reduced inequalities"},{"id":"https://metadata.un.org/sdg/3","score":0.5683000087738037,"display_name":"Good health and well-being"}],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2338318698","https://openalex.org/W2562319768","https://openalex.org/W2762644836","https://openalex.org/W2800788706","https://openalex.org/W2897093100","https://openalex.org/W3008199583","https://openalex.org/W3099185017","https://openalex.org/W3135028703","https://openalex.org/W3137097829","https://openalex.org/W3170219029","https://openalex.org/W4205399886","https://openalex.org/W4220884761","https://openalex.org/W4229005186","https://openalex.org/W4245830938","https://openalex.org/W4285269727","https://openalex.org/W4285815530","https://openalex.org/W4312628598","https://openalex.org/W4313199266","https://openalex.org/W4313555233","https://openalex.org/W4361215133","https://openalex.org/W4378417908","https://openalex.org/W4382468148","https://openalex.org/W4384257687","https://openalex.org/W4385080377","https://openalex.org/W7038814599"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"Examining":[0],"how":[1],"data":[2,38,128,137,237,248],"imbalance":[3],"affects":[4],"machine":[5,230],"learning":[6,34,231],"model":[7,155,189],"prediction":[8],"accuracy":[9,193,199,207],"is":[10,19,160],"the":[11,17,51,84,91,125,171,197,225,240],"focus":[12],"of":[13,53,65,127,156,165,194],"this":[14,96,132],"study.":[15],"Here,":[16],"emphasis":[18,46],"squarely":[20],"on":[21,47,90],"a":[22,44,62,81,101,153,220],"comprehensive":[23],"architecture":[24],"that":[25,79,106],"integrates":[26],"many":[27],"classifiers":[28],"with":[29,43,118,143,184,229,235],"hybrid":[30,103,154,187],"sampling":[31,104],"methodologies.":[32],"Machine":[33],"has":[35],"significantly":[36],"transformed":[37],"analysis":[39],"in":[40,77,206,212],"several":[41],"domains,":[42],"special":[45],"healthcare,":[48],"by":[49,61,176,210],"improving":[50],"precision":[52],"diagnoses":[54],"and":[55,87,112,152,158,215,227,238],"decision-making":[56],"processes.":[57],"Imbalanced":[58],"datasets,":[59],"characterized":[60],"large":[63],"underrepresentation":[64],"one":[66],"class":[67],"relative":[68],"to":[69,134,186,190,201,223,246],"another,":[70],"offer":[71],"considerable":[72],"issues.":[73],"This":[74,121],"often":[75],"results":[76],"models":[78],"exhibit":[80],"bias":[82],"towards":[83],"majority":[85],"classes":[86],"perform":[88],"poorly":[89],"minority":[92],"classes.":[93],"To":[94],"address":[95],"issue,":[97],"our":[98,177],"study":[99,218],"utilizes":[100],"unique":[102],"technique":[105],"combines":[107],"GASMOTE":[108],"(Genetic":[109],"Algorithm-based":[110],"SMOTE)":[111,117],"SMOTE-PSO":[113],"(Particle":[114],"Swarm":[115],"Optimization-enhanced":[116],"ENN":[119],"under-sampling.":[120],"approach":[122],"successfully":[123],"addresses":[124],"problem":[126],"imbalance.":[129,249],"We":[130],"use":[131],"framework":[133],"analyze":[135],"health":[136],"obtained":[138],"from":[139],"Kaggle,":[140],"combining":[141],"it":[142],"XGBoost,":[144],"Logistic":[145],"Regression,":[146],"Random":[147],"Forest,":[148],"Support":[149],"Vector":[150],"Machine,":[151],"RF":[157],"XGBoost":[159],"not":[161],"uncommon.":[162],"A":[163],"combination":[164],"these":[166],"preprocessing":[167,181],"procedures":[168],"substantially":[169],"improves":[170],"model\u2019s":[172,198],"performance,":[173],"as":[174],"shown":[175],"study\u2019s":[178],"findings.":[179],"No":[180],"was":[182],"necessary":[183],"regard":[185],"RF+XGBoost":[188],"achieve":[191],"an":[192],"0.97.":[195],"Nevertheless,":[196],"improved":[200],"0.99":[202],"after":[203],"preprocessing.":[204],"Gains":[205],"were":[208],"accompanied":[209],"enhancements":[211],"recall,":[213],"precision,":[214],"F1-score.":[216],"The":[217],"provides":[219],"standard":[221],"structure":[222],"enhance":[224],"robustness":[226],"reliability":[228],"algorithms":[232],"during":[233],"circumstances":[234],"uneven":[236],"highlights":[239],"pressing":[241],"requirement":[242],"for":[243],"particular":[244],"techniques":[245],"combat":[247]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-06T10:28:23.643775","created_date":"2025-10-10T00:00:00"}