{"id":"https://openalex.org/W3137868789","doi":"https://doi.org/10.1109/bigdata50022.2020.9377768","title":"C-SMOTE: Continuous Synthetic Minority Oversampling for Evolving Data Streams","display_name":"C-SMOTE: Continuous Synthetic Minority Oversampling for Evolving Data Streams","publication_year":2020,"publication_date":"2020-12-10","ids":{"openalex":"https://openalex.org/W3137868789","doi":"https://doi.org/10.1109/bigdata50022.2020.9377768","mag":"3137868789"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata50022.2020.9377768","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9377768","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/11311/1166189","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087779654","display_name":"Alessio Bernardo","orcid":"https://orcid.org/0000-0002-3492-0345"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Alessio Bernardo","raw_affiliation_strings":["DEIB-Politecnico di Milano,Milano,Italy","POLIMI - Politecnico di Milano [Milan] (Piazza Leonardo da Vinci, 32 20133 Milano - Italy)"],"affiliations":[{"raw_affiliation_string":"DEIB-Politecnico di Milano,Milano,Italy","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"POLIMI - Politecnico di Milano [Milan] (Piazza Leonardo da Vinci, 32 20133 Milano - Italy)","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071380196","display_name":"Heitor Murilo Gomes","orcid":"https://orcid.org/0000-0002-5276-637X"},"institutions":[{"id":"https://openalex.org/I52179390","display_name":"University of Waikato","ror":"https://ror.org/013fsnh78","country_code":"NZ","type":"education","lineage":["https://openalex.org/I52179390"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Heitor Murilo Gomes","raw_affiliation_strings":["University of Waikato,Hamilton,New Zealand","University of Waikato [Hamilton] (Hillcrest, Hamilton 3216 - New Zealand)"],"affiliations":[{"raw_affiliation_string":"University of Waikato,Hamilton,New Zealand","institution_ids":["https://openalex.org/I52179390"]},{"raw_affiliation_string":"University of Waikato [Hamilton] (Hillcrest, Hamilton 3216 - New Zealand)","institution_ids":["https://openalex.org/I52179390"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042593186","display_name":"Jacob Montiel","orcid":"https://orcid.org/0000-0003-2245-0718"},"institutions":[{"id":"https://openalex.org/I52179390","display_name":"University of Waikato","ror":"https://ror.org/013fsnh78","country_code":"NZ","type":"education","lineage":["https://openalex.org/I52179390"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Jacob Montiel","raw_affiliation_strings":["University of Waikato,Hamilton,New Zealand","University of Waikato [Hamilton] (Hillcrest, Hamilton 3216 - New Zealand)"],"affiliations":[{"raw_affiliation_string":"University of Waikato,Hamilton,New Zealand","institution_ids":["https://openalex.org/I52179390"]},{"raw_affiliation_string":"University of Waikato [Hamilton] (Hillcrest, Hamilton 3216 - New Zealand)","institution_ids":["https://openalex.org/I52179390"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087785022","display_name":"Bernhard Pfahringer","orcid":"https://orcid.org/0000-0002-3732-5787"},"institutions":[{"id":"https://openalex.org/I52179390","display_name":"University of Waikato","ror":"https://ror.org/013fsnh78","country_code":"NZ","type":"education","lineage":["https://openalex.org/I52179390"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Bernhard Pfahringer","raw_affiliation_strings":["University of Waikato,Hamilton,New Zealand","University of Waikato [Hamilton] (Hillcrest, Hamilton 3216 - New Zealand)"],"affiliations":[{"raw_affiliation_string":"University of Waikato,Hamilton,New Zealand","institution_ids":["https://openalex.org/I52179390"]},{"raw_affiliation_string":"University of Waikato [Hamilton] (Hillcrest, Hamilton 3216 - New Zealand)","institution_ids":["https://openalex.org/I52179390"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080970505","display_name":"Albert Bifet","orcid":"https://orcid.org/0000-0002-8339-7773"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I52179390","display_name":"University of Waikato","ror":"https://ror.org/013fsnh78","country_code":"NZ","type":"education","lineage":["https://openalex.org/I52179390"]}],"countries":["FR","NZ"],"is_corresponding":false,"raw_author_name":"Albert Bifet","raw_affiliation_strings":["University of Waikato,New Zealand","INFRES - D\u00e9partement Informatique et R\u00e9seaux (46, rue Barrault \r\n75013 Paris - France)","DIG - Data, Intelligence and Graphs (T\u00e9l\u00e9com Paris 19 Place Marguerite Perey 91120 Palaiseau - France)"],"affiliations":[{"raw_affiliation_string":"University of Waikato,New Zealand","institution_ids":["https://openalex.org/I52179390"]},{"raw_affiliation_string":"INFRES - D\u00e9partement Informatique et R\u00e9seaux (46, rue Barrault \r\n75013 Paris - France)","institution_ids":[]},{"raw_affiliation_string":"DIG - Data, Intelligence and Graphs (T\u00e9l\u00e9com Paris 19 Place Marguerite Perey 91120 Palaiseau - France)","institution_ids":["https://openalex.org/I12356871"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015694017","display_name":"Emanuele Della Valle","orcid":"https://orcid.org/0000-0002-5176-5885"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Emanuele Della Valle","raw_affiliation_strings":["DEIB-Politecnico di Milano,Milano,Italy","POLIMI - Politecnico di Milano [Milan] (Piazza Leonardo da Vinci, 32 20133 Milano - Italy)"],"affiliations":[{"raw_affiliation_string":"DEIB-Politecnico di Milano,Milano,Italy","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"POLIMI - Politecnico di Milano [Milan] (Piazza Leonardo da Vinci, 32 20133 Milano - Italy)","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5087779654"],"corresponding_institution_ids":["https://openalex.org/I93860229"],"apc_list":null,"apc_paid":null,"fwci":3.0174,"has_fulltext":false,"cited_by_count":46,"citation_normalized_percentile":{"value":0.92996808,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"483","last_page":"492"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining 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/T12761","display_name":"Data Stream Mining 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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9925000071525574,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9684000015258789,"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/oversampling","display_name":"Oversampling","score":0.8388897180557251},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7963229417800903},{"id":"https://openalex.org/keywords/concept-drift","display_name":"Concept drift","score":0.7842769622802734},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7061452865600586},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.705220103263855},{"id":"https://openalex.org/keywords/data-stream","display_name":"Data stream","score":0.6998438835144043},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.6701574921607971},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5630961656570435},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5388185381889343},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5298808813095093},{"id":"https://openalex.org/keywords/pipeline-transport","display_name":"Pipeline transport","score":0.49904298782348633},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07186603546142578},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.06823959946632385},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.06706279516220093}],"concepts":[{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.8388897180557251},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7963229417800903},{"id":"https://openalex.org/C60777511","wikidata":"https://www.wikidata.org/wiki/Q3045002","display_name":"Concept drift","level":3,"score":0.7842769622802734},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7061452865600586},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.705220103263855},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.6998438835144043},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.6701574921607971},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5630961656570435},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5388185381889343},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5298808813095093},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.49904298782348633},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07186603546142578},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.06823959946632385},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.06706279516220093},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C87717796","wikidata":"https://www.wikidata.org/wiki/Q146326","display_name":"Environmental engineering","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/bigdata50022.2020.9377768","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9377768","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04468435v1","is_oa":false,"landing_page_url":"https://hal.science/hal-04468435","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2020 IEEE International Conference on Big Data (IEEE BigData 2020), Atlanta, GA, USA, December 10-13, 2020, Dec 2020, Atlanta, United States. pp.483--492, ⟨10.1109/BIGDATA50022.2020.9377768⟩","raw_type":"Conference papers"},{"id":"pmh:oai:re.public.polimi.it:11311/1166189","is_oa":true,"landing_page_url":"https://hdl.handle.net/11311/1166189","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:re.public.polimi.it:11311/1166189","is_oa":true,"landing_page_url":"https://hdl.handle.net/11311/1166189","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W139044672","https://openalex.org/W164124199","https://openalex.org/W1525647652","https://openalex.org/W1529840045","https://openalex.org/W1988812547","https://openalex.org/W2012663856","https://openalex.org/W2026316367","https://openalex.org/W2084689094","https://openalex.org/W2088654600","https://openalex.org/W2093919988","https://openalex.org/W2107327607","https://openalex.org/W2118978333","https://openalex.org/W2130486630","https://openalex.org/W2135335717","https://openalex.org/W2143991132","https://openalex.org/W2148143831","https://openalex.org/W2520599539","https://openalex.org/W2626498001","https://openalex.org/W2756359217","https://openalex.org/W2913146537","https://openalex.org/W2978488090","https://openalex.org/W2984308182","https://openalex.org/W3003253354","https://openalex.org/W3120740533","https://openalex.org/W4288594627","https://openalex.org/W6605683200","https://openalex.org/W6680192438","https://openalex.org/W6758221360","https://openalex.org/W6768413947","https://openalex.org/W6769806525"],"related_works":["https://openalex.org/W4307392573","https://openalex.org/W2802243998","https://openalex.org/W2736127210","https://openalex.org/W2329342202","https://openalex.org/W2574092225","https://openalex.org/W4200217704","https://openalex.org/W2161835057","https://openalex.org/W1521014365","https://openalex.org/W3208495060","https://openalex.org/W2740428142"],"abstract_inverted_index":{"Streaming":[0],"Machine":[1],"Learning":[2],"(SML)":[3],"studies":[4],"single-pass":[5],"learning":[6,36],"algorithms":[7],"that":[8,42,125,150],"update":[9],"their":[10],"models":[11,126,132],"one":[12,76],"data":[13,26,68,119,136],"item":[14],"at":[15,78],"a":[16,38,79,89],"time":[17],"given":[18],"an":[19,64],"unbounded":[20],"and":[21,50],"often":[22],"non-stationary":[23],"flow":[24],"of":[25,30,40,46,62,67,72,118],"(a.k.a.,":[27],"in":[28,69],"presence":[29,71],"concept":[31,51,73,145],"drift).":[32],"Online":[33],"class":[34,48],"imbalance":[35,49],"is":[37,100],"branch":[39],"SML":[41,96],"combines":[43],"the":[44,58,70,103,140,158],"challenges":[45],"both":[47],"drift.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56,148],"investigate":[57],"binary":[59],"classification":[60,97],"problem":[61],"rebalancing":[63,91],"imbalanced":[65,135],"stream":[66,137,154],"drift,":[74],"accessing":[75],"sample":[77],"time.":[80],"We":[81,110,121],"propose":[82],"Continuous":[83],"Synthetic":[84],"Minority":[85],"Oversampling":[86],"Technique":[87],"(C-SMOTE),":[88],"novel":[90],"meta-strategy":[92],"to":[93,142],"pipeline":[94],"with":[95,128,144],"algorithms.":[98],"C-SMOTE":[99,112,129],"inspired":[101],"by":[102],"popular":[104],"SMOTE":[105],"algorithm":[106],"but":[107],"operates":[108],"continuously.":[109],"benchmark":[111],"pipelines":[113,130],"on":[114,134],"ten":[115],"different":[116],"groups":[117],"streams.":[120],"bring":[122],"empirical":[123],"evidence":[124],"learnt":[127],"outperform":[131,152],"trained":[133],"without":[138],"losing":[139],"ability":[141],"deal":[143],"drifts.":[146],"Moreover,":[147],"show":[149],"they":[151],"other":[153],"balancing":[155],"techniques":[156],"from":[157],"literature.":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5}],"updated_date":"2026-03-17T09:09:15.849793","created_date":"2025-10-10T00:00:00"}