{"id":"https://openalex.org/W4313555233","doi":"https://doi.org/10.1007/s10994-022-06296-4","title":"A theoretical distribution analysis of synthetic minority oversampling technique (SMOTE) for imbalanced learning","display_name":"A theoretical distribution analysis of synthetic minority oversampling technique (SMOTE) for imbalanced learning","publication_year":2023,"publication_date":"2023-01-05","ids":{"openalex":"https://openalex.org/W4313555233","doi":"https://doi.org/10.1007/s10994-022-06296-4"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-022-06296-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-022-06296-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-022-06296-4.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"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":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-022-06296-4.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013349040","display_name":"Dina Elreedy","orcid":"https://orcid.org/0000-0001-5664-2457"},"institutions":[{"id":"https://openalex.org/I145487455","display_name":"Cairo University","ror":"https://ror.org/03q21mh05","country_code":"EG","type":"education","lineage":["https://openalex.org/I145487455"]}],"countries":["EG"],"is_corresponding":true,"raw_author_name":"Dina Elreedy","raw_affiliation_strings":["Computer Engineering Department, Cairo University, Giza, 12613, Egypt"],"raw_orcid":"https://orcid.org/0000-0001-5664-2457","affiliations":[{"raw_affiliation_string":"Computer Engineering Department, Cairo University, Giza, 12613, Egypt","institution_ids":["https://openalex.org/I145487455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013978386","display_name":"Amir F. Atiya","orcid":"https://orcid.org/0000-0001-8766-5600"},"institutions":[{"id":"https://openalex.org/I145487455","display_name":"Cairo University","ror":"https://ror.org/03q21mh05","country_code":"EG","type":"education","lineage":["https://openalex.org/I145487455"]}],"countries":["EG"],"is_corresponding":false,"raw_author_name":"Amir F. Atiya","raw_affiliation_strings":["Computer Engineering Department, Cairo University, Giza, 12613, Egypt"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Engineering Department, Cairo University, Giza, 12613, Egypt","institution_ids":["https://openalex.org/I145487455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051609871","display_name":"Firuz Kamalov","orcid":"https://orcid.org/0000-0003-3946-0920"},"institutions":[{"id":"https://openalex.org/I186129607","display_name":"Canadian University of Dubai","ror":"https://ror.org/029zgsn59","country_code":"AE","type":"education","lineage":["https://openalex.org/I186129607"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Firuz Kamalov","raw_affiliation_strings":["Department of Electrical Engineering, Canadian University Dubai, Dubai, 117781, UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Canadian University Dubai, Dubai, 117781, UAE","institution_ids":["https://openalex.org/I186129607"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5013349040"],"corresponding_institution_ids":["https://openalex.org/I145487455"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":53.466,"has_fulltext":true,"cited_by_count":332,"citation_normalized_percentile":{"value":0.99916727,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"113","issue":"7","first_page":"4903","last_page":"4923"},"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/T13429","display_name":"Electricity Theft Detection Techniques","score":0.9768000245094299,"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/T14400","display_name":"Medical Coding and Health Information","score":0.9675999879837036,"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/oversampling","display_name":"Oversampling","score":0.9152204394340515},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6546463966369629},{"id":"https://openalex.org/keywords/interpolation","display_name":"Interpolation (computer graphics)","score":0.5892342329025269},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5292040109634399},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.5104562044143677},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4980783462524414},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4363037347793579},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4326295852661133},{"id":"https://openalex.org/keywords/conditional-probability-distribution","display_name":"Conditional probability distribution","score":0.4135053753852844},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38786014914512634},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33247804641723633},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.25680702924728394}],"concepts":[{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.9152204394340515},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6546463966369629},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.5892342329025269},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5292040109634399},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.5104562044143677},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4980783462524414},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4363037347793579},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4326295852661133},{"id":"https://openalex.org/C43555835","wikidata":"https://www.wikidata.org/wiki/Q2300258","display_name":"Conditional probability distribution","level":2,"score":0.4135053753852844},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38786014914512634},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33247804641723633},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.25680702924728394},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10994-022-06296-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-022-06296-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-022-06296-4.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"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":"Machine Learning","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10994-022-06296-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-022-06296-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-022-06296-4.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"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":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321148","display_name":"Cairo University","ror":"https://ror.org/03q21mh05"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4313555233.pdf"},"referenced_works_count":64,"referenced_works":["https://openalex.org/W157007071","https://openalex.org/W1496056137","https://openalex.org/W1941659294","https://openalex.org/W1967127231","https://openalex.org/W1974079881","https://openalex.org/W1986515506","https://openalex.org/W1993220166","https://openalex.org/W2003233718","https://openalex.org/W2006350740","https://openalex.org/W2006848945","https://openalex.org/W2008056655","https://openalex.org/W2014268383","https://openalex.org/W2033184625","https://openalex.org/W2067514259","https://openalex.org/W2072893848","https://openalex.org/W2081697244","https://openalex.org/W2092998534","https://openalex.org/W2104933073","https://openalex.org/W2114968414","https://openalex.org/W2118020555","https://openalex.org/W2119734256","https://openalex.org/W2132791018","https://openalex.org/W2136132422","https://openalex.org/W2139618930","https://openalex.org/W2139986471","https://openalex.org/W2148143831","https://openalex.org/W2150559772","https://openalex.org/W2151415462","https://openalex.org/W2168508521","https://openalex.org/W2301363727","https://openalex.org/W2507469091","https://openalex.org/W2508098092","https://openalex.org/W2562319768","https://openalex.org/W2604756720","https://openalex.org/W2767106145","https://openalex.org/W2786532017","https://openalex.org/W2794590714","https://openalex.org/W2800788706","https://openalex.org/W2899147610","https://openalex.org/W2908465383","https://openalex.org/W2963613787","https://openalex.org/W2971749073","https://openalex.org/W2989219518","https://openalex.org/W3005919462","https://openalex.org/W3017963672","https://openalex.org/W3042350893","https://openalex.org/W3090431724","https://openalex.org/W3100774601","https://openalex.org/W3101880446","https://openalex.org/W3120655457","https://openalex.org/W3129693849","https://openalex.org/W3154490392","https://openalex.org/W3157699413","https://openalex.org/W3167186267","https://openalex.org/W3168743454","https://openalex.org/W3173818966","https://openalex.org/W3203004730","https://openalex.org/W3210983949","https://openalex.org/W3216081012","https://openalex.org/W4205619992","https://openalex.org/W4210263531","https://openalex.org/W4214503032","https://openalex.org/W4250685065","https://openalex.org/W4285114433"],"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/W2300921526"],"abstract_inverted_index":{"Abstract":[0],"Class":[1],"imbalance":[2,33],"occurs":[3],"when":[4],"the":[5,19,27,43,48,61,91,100,113,118,122,127,134,142,152,155,159,170],"class":[6,13,21,32,46,49,83,103],"distribution":[7,120],"is":[8,14,35,47,59,133,177],"not":[9,96],"equal.":[10],"Namely,":[11],"one":[12],"under-represented":[15,44],"(minority":[16],"class),":[17],"and":[18,85,190],"other":[20],"has":[22],"significantly":[23],"more":[24],"samples":[25,84,157,172],"in":[26,37,164],"data":[28,75],"(majority":[29],"class).":[30],"The":[31,52,69,174],"problem":[34],"prevalent":[36],"many":[38],"real":[39],"world":[40],"applications.":[41],"Generally,":[42],"minority":[45,54,82,102],"of":[50,112,121,129,154,185],"interest.":[51],"synthetic":[53,74],"over-sampling":[55],"technique":[56],"(SMOTE)":[57],"method":[58,64,71,115],"considered":[60],"most":[62],"prominent":[63],"for":[65,141],"handling":[66],"unbalanced":[67],"data.":[68],"SMOTE":[70,92,114,123,143],"generates":[72],"new":[73],"patterns":[76,94],"by":[77,116,179],"performing":[78],"linear":[79],"interpolation":[80],"between":[81],"their":[86],"K":[87],"nearest":[88],"neighbors.":[89],"However,":[90],"generated":[93,124,156,171],"do":[95],"necessarily":[97],"conform":[98],"to":[99,150,166],"original":[101],"distribution.":[104,146],"This":[105,147],"paper":[106],"develops":[107],"a":[108,138,183],"novel":[109],"theoretical":[110],"analysis":[111],"deriving":[117,137],"probability":[119,145],"samples.":[125],"To":[126],"best":[128],"our":[130],"knowledge,":[131],"this":[132],"first":[135],"work":[136],"mathematical":[139],"formulation":[140],"patterns\u2019":[144],"allows":[148],"us":[149],"compare":[151],"density":[153],"with":[158],"true":[160],"underlying":[161],"class-conditional":[162],"density,":[163],"order":[165],"assess":[167],"how":[168],"representative":[169],"are.":[173],"derived":[175],"formula":[176],"verified":[178],"computing":[180],"it":[181],"on":[182],"number":[184],"densities":[186,188],"versus":[187],"computed":[189],"estimated":[191],"empirically.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":61},{"year":2025,"cited_by_count":160},{"year":2024,"cited_by_count":94},{"year":2023,"cited_by_count":17}],"updated_date":"2026-06-29T08:53:18.405633","created_date":"2025-10-10T00:00:00"}