{"id":"https://openalex.org/W3080332509","doi":"https://doi.org/10.1145/3414274.3414278","title":"Imbalanced Classification Problem Using Data-driven and Random Forest Method","display_name":"Imbalanced Classification Problem Using Data-driven and Random Forest Method","publication_year":2020,"publication_date":"2020-07-24","ids":{"openalex":"https://openalex.org/W3080332509","doi":"https://doi.org/10.1145/3414274.3414278","mag":"3080332509"},"language":"en","primary_location":{"id":"doi:10.1145/3414274.3414278","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3414274.3414278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Data Science and Information Technology","raw_type":"proceedings-article"},"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/A5100612128","display_name":"Wan Wang","orcid":"https://orcid.org/0000-0002-0476-3334"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wan Wang","raw_affiliation_strings":["Intelligent Transportation and Logistics Systems Lab, Tsinghua-Berkeley Shenzhen Institute, ShenZhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Transportation and Logistics Systems Lab, Tsinghua-Berkeley Shenzhen Institute, ShenZhen, China","institution_ids":["https://openalex.org/I4210114105"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061328883","display_name":"Xinglu Liu","orcid":"https://orcid.org/0000-0001-6011-3179"},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinglu Liu","raw_affiliation_strings":["Intelligent Transportation and Logistics Systems Lab, Tsinghua-Berkeley Shenzhen Institute, ShenZhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Transportation and Logistics Systems Lab, Tsinghua-Berkeley Shenzhen Institute, ShenZhen, China","institution_ids":["https://openalex.org/I4210114105"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108743840","display_name":"Wai Kin Victor Chan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114105","display_name":"Tsinghua\u2013Berkeley Shenzhen Institute","ror":"https://ror.org/02hhwwz98","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210114105","https://openalex.org/I95457486","https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wai Kin Victor Chan","raw_affiliation_strings":["Intelligent Transportation and Logistics Systems Lab, Tsinghua-Berkeley Shenzhen Institute, ShenZhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Transportation and Logistics Systems Lab, Tsinghua-Berkeley Shenzhen Institute, ShenZhen, China","institution_ids":["https://openalex.org/I4210114105"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210114105"],"apc_list":null,"apc_paid":null,"fwci":0.115,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.35828318,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9890999794006348,"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/T14319","display_name":"Currency Recognition and Detection","score":0.9884999990463257,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/random-forest","display_name":"Random forest","score":0.7829130291938782},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6751731634140015},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45263728499412537},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36094847321510315},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3317892551422119},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32649263739585876}],"concepts":[{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.7829130291938782},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6751731634140015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45263728499412537},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36094847321510315},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3317892551422119},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32649263739585876}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3414274.3414278","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3414274.3414278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd International Conference on Data Science and Information Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2012035409","https://openalex.org/W2084812512","https://openalex.org/W2104471998","https://openalex.org/W2261059368","https://openalex.org/W2756359217","https://openalex.org/W2781900029","https://openalex.org/W2785818537","https://openalex.org/W2801749227","https://openalex.org/W2896787456","https://openalex.org/W2909785775","https://openalex.org/W2936311765","https://openalex.org/W2973651390","https://openalex.org/W6671611538"],"related_works":["https://openalex.org/W3116896278","https://openalex.org/W4225360065","https://openalex.org/W2275058042","https://openalex.org/W4283016678","https://openalex.org/W4282839226","https://openalex.org/W2240965754","https://openalex.org/W3018959556","https://openalex.org/W2911455822","https://openalex.org/W3174196512","https://openalex.org/W3126015411"],"abstract_inverted_index":{"Classification":[0],"problem":[1,13,186],"is":[2,108,125,131,145],"a":[3,38,63,67,128,189,220,241],"major":[4],"concern":[5],"in":[6,55,66,81,111,120,227,234,246],"numerous":[7],"domains,":[8],"for":[9],"instance,":[10],"customer":[11],"retaining":[12],"on":[14,138,151],"electronic":[15],"devices,":[16],"rare":[17],"disease":[18],"diagnosis,":[19],"bank":[20],"fraud":[21],"identification":[22],"etc.":[23],"Accurate":[24],"and":[25,35,48,74,175,187,204,223,244],"efficient":[26],"classification":[27,102,185],"approaches":[28],"can":[29,197,239],"reduce":[30],"operation":[31],"cost":[32],"of":[33,40,69,84,100,115,201],"companies":[34],"thus":[36],"save":[37],"mass":[39],"artificial":[41],"work":[42],"significantly.":[43],"Identifying":[44],"the":[45,82,87,101,139,143,165,199,202,206,247],"potential":[46],"targets":[47],"then":[49],"put":[50],"promotion":[51],"strategy":[52],"to":[53,57,92,97,133,192],"customers":[54],"order":[56],"achieve":[58],"considerable":[59],"improvement":[60],"has":[61],"become":[62],"critical":[64],"objective":[65],"range":[68],"institutions.":[70],"Nevertheless,":[71],"missing":[72],"values":[73,170],"some":[75],"statistical":[76],"errors":[77],"are":[78,231],"always":[79],"involved":[80],"majority":[83],"datasets.":[85,141,154],"Besides,":[86],"available":[88],"datasets":[89],"usually":[90],"tend":[91],"be":[93],"imbalanced,":[94],"which":[95,196,230,238],"leads":[96],"weak":[98],"performance":[99],"model.":[103],"Though":[104],"random":[105,158,216],"forest":[106,159,217],"method":[107,130,163,191],"widely":[109],"adopted":[110],"prediction":[112,144,166],"problem,":[113],"few":[114],"them":[116],"introduce":[117],"data-driven":[118,129,162,190,221],"technique":[119],"this":[121],"problem.":[122],"In":[123],"th":[124],"work,":[126],"firstly,":[127],"applied":[132],"generate":[134,193],"new":[135,194],"features":[136,203],"based":[137],"imbalanced":[140,225],"Then,":[142],"executed":[146],"by":[147],"Random":[148],"Forest(RF)":[149],"algorithm":[150],"three":[152],"open-sourced":[153],"Results":[155],"reveal":[156],"that":[157],"combined":[160],"with":[161,219],"improved":[164],"accuracy.":[167],"The":[168],"AUC":[169],"also":[171],"perform":[172],"well":[173],"stable":[174],"even":[176],"increased.":[177],"Our":[178],"main":[179],"contributions":[180],"are:":[181],"We":[182,214],"consider":[183,224],"two-class":[184],"employ":[188],"features,":[195],"raise":[198],"correlation":[200],"increase":[205],"accuracy":[207],"without":[208],"losing":[209],"original":[210],"information":[211],"meanwhile.":[212],"2.":[213],"use":[215],"coupled":[218],"method,":[222],"condition":[226],"our":[228],"test":[229],"more":[232],"reasonable":[233],"real":[235],"world":[236],"applications,":[237],"provide":[240],"general":[242],"idea":[243],"direction":[245],"industry.":[248]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}