{"id":"https://openalex.org/W2963963837","doi":"https://doi.org/10.1049/iet-sen.2018.5193","title":"Systematic literature review of preprocessing techniques for imbalanced data","display_name":"Systematic literature review of preprocessing techniques for imbalanced data","publication_year":2019,"publication_date":"2019-07-22","ids":{"openalex":"https://openalex.org/W2963963837","doi":"https://doi.org/10.1049/iet-sen.2018.5193","mag":"2963963837"},"language":"en","primary_location":{"id":"doi:10.1049/iet-sen.2018.5193","doi":"https://doi.org/10.1049/iet-sen.2018.5193","is_oa":false,"landing_page_url":"https://doi.org/10.1049/iet-sen.2018.5193","pdf_url":null,"source":{"id":"https://openalex.org/S164201770","display_name":"IET Software","issn_l":"1751-8806","issn":["1751-8806","1751-8814"],"is_oa":false,"is_in_doaj":true,"is_core":true,"listed_in":["ccf-b","cwts-core","doaj","dongbi-c","jufo-1","norway-1","oarl","poland-70","russia-white-list-2"],"host_organization":"https://openalex.org/P4310311714","host_organization_name":"Institution of Engineering and Technology","host_organization_lineage":["https://openalex.org/P4310311714"],"host_organization_lineage_names":["Institution of Engineering and Technology"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IET Software","raw_type":"journal-article"},"volume":null,"type":"review","is_traditional":true,"indexed_in":["crossref","doaj"],"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/A5062747352","display_name":"Ebubeogu Amarachukwu Felix","orcid":"https://orcid.org/0000-0001-8389-4860","observed_orcids":["https://orcid.org/0000-0001-8389-4860"]},"institutions":[{"id":"https://openalex.org/I33849332","display_name":"University of Malaya","ror":"https://ror.org/00rzspn62","country_code":"MY","type":"education","lineage":["https://openalex.org/I33849332"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Ebubeogu Amarachukwu Felix","raw_affiliation_strings":["Faculty of Computer Science and Information Technology, University of Malaya, 50603 Kuala Lumpur, Malaysia"],"raw_orcid":"https://orcid.org/0000-0001-8389-4860","affiliations":[{"raw_affiliation_string":"Faculty of Computer Science and Information Technology, University of Malaya, 50603 Kuala Lumpur, Malaysia","institution_ids":["https://openalex.org/I33849332"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045011154","display_name":"Sai Peck Lee","orcid":"https://orcid.org/0000-0002-4551-430X","observed_orcids":["https://orcid.org/0000-0002-4551-430X"]},"institutions":[{"id":"https://openalex.org/I33849332","display_name":"University of Malaya","ror":"https://ror.org/00rzspn62","country_code":"MY","type":"education","lineage":["https://openalex.org/I33849332"]}],"countries":["MY"],"is_corresponding":true,"raw_author_name":"Sai Peck Lee","raw_affiliation_strings":["Faculty of Computer Science and Information Technology, University of Malaya, 50603 Kuala Lumpur, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science and Information Technology, University of Malaya, 50603 Kuala Lumpur, Malaysia","institution_ids":["https://openalex.org/I33849332"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5045011154"],"corresponding_institution_ids":["https://openalex.org/I33849332"],"apc_list":{"value":2210,"currency":"USD","value_usd":2210},"apc_paid":null,"fwci":0.3761,"has_fulltext":false,"cited_by_count":115,"citation_normalized_percentile":{"value":0.53633218,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":"13","issue":"6","first_page":"479","last_page":"496"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9922000169754028,"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":0.9922000169754028,"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":0.004399999976158142,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.0003000000142492354,"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/class-imbalance","display_name":"class imbalance","score":0.9869999885559082},{"id":"https://openalex.org/keywords/data-preprocessing","display_name":"data preprocessing","score":0.9900000095367432},{"id":"https://openalex.org/keywords/data-quality","display_name":"data quality","score":0.9369999766349792},{"id":"https://openalex.org/keywords/data-handling","display_name":"data handling","score":0.34200000762939453},{"id":"https://openalex.org/keywords/imbalanced-data-classification","display_name":"imbalanced classification","score":0.42899999022483826}],"concepts":[{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.8360322713851929},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.7706050872802734},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7534539103507996},{"id":"https://openalex.org/C189708586","wikidata":"https://www.wikidata.org/wiki/Q1504425","display_name":"Systematic review","level":3,"score":0.6982825994491577},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48590153455734253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47987523674964905},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47244101762771606},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.4597565829753876},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.45623302459716797},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.43831533193588257},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.39490652084350586},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1619587540626526},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.08294841647148132},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.056168973445892334},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1049/iet-sen.2018.5193","doi":"https://doi.org/10.1049/iet-sen.2018.5193","is_oa":false,"landing_page_url":"https://doi.org/10.1049/iet-sen.2018.5193","pdf_url":null,"source":{"id":"https://openalex.org/S164201770","display_name":"IET Software","issn_l":"1751-8806","issn":["1751-8806","1751-8814"],"is_oa":false,"is_in_doaj":true,"is_core":true,"listed_in":["ccf-b","cwts-core","doaj","dongbi-c","jufo-1","norway-1","oarl","poland-70","russia-white-list-2"],"host_organization":"https://openalex.org/P4310311714","host_organization_name":"Institution of Engineering and Technology","host_organization_lineage":["https://openalex.org/P4310311714"],"host_organization_lineage_names":["Institution of Engineering and Technology"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IET Software","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[{"display_name":"Systematic Review","id":"https://openalex.org/study-designs/systematic-review"}],"awards":[{"id":"https://openalex.org/G7088438930","display_name":null,"funder_award_id":"(UM.C/625/1/HIR/MOHE/FCSIT/13","funder_id":"https://openalex.org/F4320322604","funder_display_name":"Universiti Malaya"},{"id":"https://openalex.org/G8294176360","display_name":null,"funder_award_id":"(FRGS) (FP001-2016)","funder_id":"https://openalex.org/F4320322604","funder_display_name":"Universiti Malaya"}],"funders":[{"id":"https://openalex.org/F4320322604","display_name":"Universiti Malaya","ror":"https://ror.org/00rzspn62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":206,"referenced_works":["https://openalex.org/W28412257","https://openalex.org/W79589210","https://openalex.org/W176026448","https://openalex.org/W571200655","https://openalex.org/W587473303","https://openalex.org/W769353746","https://openalex.org/W1570437003","https://openalex.org/W1585743408","https://openalex.org/W1623006543","https://openalex.org/W1624080771","https://openalex.org/W1656679015","https://openalex.org/W1678889691","https://openalex.org/W1736641051","https://openalex.org/W1766594731","https://openalex.org/W1822128848","https://openalex.org/W1822381047","https://openalex.org/W1864224110","https://openalex.org/W1877500380","https://openalex.org/W1905687056","https://openalex.org/W1909497710","https://openalex.org/W1917465580","https://openalex.org/W1940140457","https://openalex.org/W1941659294","https://openalex.org/W1966748751","https://openalex.org/W1966787785","https://openalex.org/W1968985250","https://openalex.org/W1972657718","https://openalex.org/W1974330405","https://openalex.org/W1974879849","https://openalex.org/W1975664724","https://openalex.org/W1977615839","https://openalex.org/W1982848337","https://openalex.org/W1983085975","https://openalex.org/W1984323748","https://openalex.org/W1987416998","https://openalex.org/W1987633617","https://openalex.org/W1991695226","https://openalex.org/W1992345889","https://openalex.org/W1993220166","https://openalex.org/W1994719586","https://openalex.org/W2001622722","https://openalex.org/W2001629770","https://openalex.org/W2001652071","https://openalex.org/W2003638356","https://openalex.org/W2004138036","https://openalex.org/W2006020859","https://openalex.org/W2006210519","https://openalex.org/W2006488700","https://openalex.org/W2008596407","https://openalex.org/W2015452969","https://openalex.org/W2015681982","https://openalex.org/W2015776218","https://openalex.org/W2021688474","https://openalex.org/W2022348393","https://openalex.org/W2022922462","https://openalex.org/W2023847169","https://openalex.org/W2025700486","https://openalex.org/W2025773596","https://openalex.org/W2025914996","https://openalex.org/W2026158579","https://openalex.org/W2026458067","https://openalex.org/W2028462432","https://openalex.org/W2032308366","https://openalex.org/W2032764504","https://openalex.org/W2033184625","https://openalex.org/W2036055923","https://openalex.org/W2041125834","https://openalex.org/W2042086215","https://openalex.org/W2046173508","https://openalex.org/W2053141315","https://openalex.org/W2053724458","https://openalex.org/W2054521721","https://openalex.org/W2054563706","https://openalex.org/W2054701320","https://openalex.org/W2055271333","https://openalex.org/W2055949897","https://openalex.org/W2056020020","https://openalex.org/W2056797234","https://openalex.org/W2064330644","https://openalex.org/W2072615238","https://openalex.org/W2076272581","https://openalex.org/W2076923495","https://openalex.org/W2083221797","https://openalex.org/W2083660761","https://openalex.org/W2084789715","https://openalex.org/W2091007025","https://openalex.org/W2093717447","https://openalex.org/W2094764356","https://openalex.org/W2094764962","https://openalex.org/W2094947835","https://openalex.org/W2095526364","https://openalex.org/W2099454382","https://openalex.org/W2099919734","https://openalex.org/W2101227285","https://openalex.org/W2102468096","https://openalex.org/W2105180131","https://openalex.org/W2105300539","https://openalex.org/W2106652842","https://openalex.org/W2106956101","https://openalex.org/W2107138773","https://openalex.org/W2107323945","https://openalex.org/W2109826612","https://openalex.org/W2110431240","https://openalex.org/W2113160553","https://openalex.org/W2113451446","https://openalex.org/W2113890143","https://openalex.org/W2114968414","https://openalex.org/W2115114820","https://openalex.org/W2115713980","https://openalex.org/W2116984840","https://openalex.org/W2117190680","https://openalex.org/W2118283821","https://openalex.org/W2118978333","https://openalex.org/W2119168155","https://openalex.org/W2119498311","https://openalex.org/W2123475055","https://openalex.org/W2126626812","https://openalex.org/W2130465103","https://openalex.org/W2133160781","https://openalex.org/W2138900513","https://openalex.org/W2140898374","https://openalex.org/W2141843719","https://openalex.org/W2146651503","https://openalex.org/W2151666086","https://openalex.org/W2155555718","https://openalex.org/W2160671582","https://openalex.org/W2160988203","https://openalex.org/W2162210260","https://openalex.org/W2163902533","https://openalex.org/W2164330572","https://openalex.org/W2169171327","https://openalex.org/W2172165257","https://openalex.org/W2179438935","https://openalex.org/W2184886772","https://openalex.org/W2189368561","https://openalex.org/W2192239100","https://openalex.org/W2194079679","https://openalex.org/W2207642946","https://openalex.org/W2218021565","https://openalex.org/W2226725405","https://openalex.org/W2249025844","https://openalex.org/W2276400542","https://openalex.org/W2279597087","https://openalex.org/W2286585054","https://openalex.org/W2287189768","https://openalex.org/W2291039747","https://openalex.org/W2296620627","https://openalex.org/W2301233168","https://openalex.org/W2305347498","https://openalex.org/W2320349359","https://openalex.org/W2324868376","https://openalex.org/W2327900220","https://openalex.org/W2333362108","https://openalex.org/W2395429379","https://openalex.org/W2395492705","https://openalex.org/W2404607184","https://openalex.org/W2412267538","https://openalex.org/W2413640221","https://openalex.org/W2461041754","https://openalex.org/W2470052106","https://openalex.org/W2471353105","https://openalex.org/W2490420619","https://openalex.org/W2508179673","https://openalex.org/W2508189139","https://openalex.org/W2510885373","https://openalex.org/W2516328000","https://openalex.org/W2524620548","https://openalex.org/W2526177130","https://openalex.org/W2528103328","https://openalex.org/W2531607313","https://openalex.org/W2539427701","https://openalex.org/W2547202110","https://openalex.org/W2547498384","https://openalex.org/W2555550222","https://openalex.org/W2560730652","https://openalex.org/W2562319768","https://openalex.org/W2570224090","https://openalex.org/W2585284977","https://openalex.org/W2586138702","https://openalex.org/W2588292072","https://openalex.org/W2624900765","https://openalex.org/W2666681845","https://openalex.org/W2727549497","https://openalex.org/W2731935965","https://openalex.org/W2737334527","https://openalex.org/W2740749606","https://openalex.org/W2761745500","https://openalex.org/W2766521509","https://openalex.org/W2771362265","https://openalex.org/W2787079225","https://openalex.org/W2792399616","https://openalex.org/W2792895843","https://openalex.org/W2800769566","https://openalex.org/W2801692414","https://openalex.org/W2904027392","https://openalex.org/W2909172538","https://openalex.org/W2911964244","https://openalex.org/W2912934387","https://openalex.org/W2963162454","https://openalex.org/W2963548617","https://openalex.org/W4237670065","https://openalex.org/W4238859253","https://openalex.org/W4241879543","https://openalex.org/W4243379839","https://openalex.org/W4250685065","https://openalex.org/W4293582904"],"related_works":["https://openalex.org/W4308627565","https://openalex.org/W7212716984","https://openalex.org/W2971644666","https://openalex.org/W7217034046","https://openalex.org/W4406625903","https://openalex.org/W4415590652","https://openalex.org/W4390916242","https://openalex.org/W6886067055","https://openalex.org/W7152446191","https://openalex.org/W1994026396"],"abstract_inverted_index":{"Data":[0],"preprocessing":[1,14,60,184],"remains":[2],"an":[3],"important":[4],"step":[5],"in":[6,29,38,50,193],"machine":[7,51,194],"learning":[8,52,195],"studies.":[9,196],"This":[10,172],"is":[11],"because":[12],"proper":[13],"of":[15,36,57,70,105,142,189],"imbalanced":[16,58,76],"data":[17,40,59,77,95,115,183,191],"can":[18],"enable":[19],"researchers":[20],"to":[21,33,88,94,100,109,128,135,185],"reduce":[22],"defects":[23,37],"as":[24,26,163],"much":[25],"possible,":[27],"which,":[28],"turn,":[30],"may":[31],"lead":[32],"the":[34,43,82,85,90,106,143,154,187,190],"elimination":[35],"existing":[39,86,144],"sets.":[41],"Despite":[42],"remarkable":[44],"achievements":[45],"that":[46],"have":[47],"been":[48,165],"accomplished":[49],"studies,":[53],"systematic":[54,71,120,168,178],"literature":[55,72,87,121,169,179],"reviews":[56],"techniques":[61,107],"are":[62,66],"lacking.":[63],"Consequently,":[64],"there":[65],"a":[67,102,119,125],"limited":[68],"number":[69],"review":[73,122,170,180],"studies":[74,145,157,181],"on":[75,182],"preprocessing.":[78,116],"In":[79],"this":[80],"study,":[81,173],"authors":[83],"assess":[84],"identify":[89],"key":[91],"issues":[92,112],"related":[93],"quality":[96,150,188],"and":[97,99],"handling":[98],"provide":[101],"convenient":[103],"collection":[104],"used":[108],"address":[110],"these":[111],"when":[113],"performing":[114],"They":[117],"applied":[118,192],"method":[123],"involving":[124],"manual":[126],"search":[127],"select":[129],"articles":[130],"published":[131],"from":[132],"January":[133],"2010":[134],"September":[136],"2018":[137],"for":[138,176],"review.":[139],"The":[140],"qualities":[141],"were":[146,161],"assessed":[147],"using":[148],"certain":[149],"assessment":[151],"criteria.":[152],"Of":[153],"118":[155],"relevant":[156],"found,":[158],"only":[159],"2%":[160],"identified":[162],"having":[164],"conducted":[166],"following":[167],"guidelines.":[171],"therefore,":[174],"calls":[175],"more":[177],"improve":[186]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":30},{"year":2024,"cited_by_count":33},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2019-07-30T00:00:00"}