{"id":"https://openalex.org/W2794292095","doi":"https://doi.org/10.1145/3170521.3170535","title":"Imbalanced big data classification","display_name":"Imbalanced big data classification","publication_year":2018,"publication_date":"2018-01-04","ids":{"openalex":"https://openalex.org/W2794292095","doi":"https://doi.org/10.1145/3170521.3170535","mag":"2794292095"},"language":"en","primary_location":{"id":"doi:10.1145/3170521.3170535","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3170521.3170535","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop Program of the 19th International Conference on Distributed Computing and Networking","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/A5019285283","display_name":"Avnish Rastogi","orcid":null},"institutions":[{"id":"https://openalex.org/I96211989","display_name":"HCL Technologies (India)","ror":"https://ror.org/02nbb5780","country_code":"IN","type":"company","lineage":["https://openalex.org/I96211989"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Avnish Kumar Rastogi","raw_affiliation_strings":["HCL Technologies, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HCL Technologies, India","institution_ids":["https://openalex.org/I96211989"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054436285","display_name":"Nitin Narang","orcid":"https://orcid.org/0000-0002-0860-8905"},"institutions":[{"id":"https://openalex.org/I96211989","display_name":"HCL Technologies (India)","ror":"https://ror.org/02nbb5780","country_code":"IN","type":"company","lineage":["https://openalex.org/I96211989"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Nitin Narang","raw_affiliation_strings":["HCL Technologies, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HCL Technologies, India","institution_ids":["https://openalex.org/I96211989"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046130737","display_name":"Zamir Ahmad Siddiqui","orcid":null},"institutions":[{"id":"https://openalex.org/I96211989","display_name":"HCL Technologies (India)","ror":"https://ror.org/02nbb5780","country_code":"IN","type":"company","lineage":["https://openalex.org/I96211989"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Zamir Ahmad Siddiqui","raw_affiliation_strings":["HCL Technologies, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"HCL Technologies, India","institution_ids":["https://openalex.org/I96211989"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I96211989"],"apc_list":null,"apc_paid":null,"fwci":0.8988,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.79225093,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9983000159263611,"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":0.9952999949455261,"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/computer-science","display_name":"Computer science","score":0.8039374947547913},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6436966061592102},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.5972044467926025},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5671658515930176},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4924491345882416},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.4771444499492645},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.47384053468704224},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4324015974998474}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8039374947547913},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6436966061592102},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5972044467926025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5671658515930176},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4924491345882416},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.4771444499492645},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.47384053468704224},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4324015974998474},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3170521.3170535","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3170521.3170535","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Workshop Program of the 19th International Conference on Distributed Computing and Networking","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.75,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1736726159","https://openalex.org/W1974079881","https://openalex.org/W1993220166","https://openalex.org/W2011376672","https://openalex.org/W2015452969","https://openalex.org/W2020498246","https://openalex.org/W2033104711","https://openalex.org/W2049003051","https://openalex.org/W2049280902","https://openalex.org/W2058732827","https://openalex.org/W2082344779","https://openalex.org/W2096451472","https://openalex.org/W2108399535","https://openalex.org/W2112053337","https://openalex.org/W2113124588","https://openalex.org/W2118269922","https://openalex.org/W2118978333","https://openalex.org/W2125671345","https://openalex.org/W2132791018","https://openalex.org/W2147717514","https://openalex.org/W2148143831","https://openalex.org/W2151415462","https://openalex.org/W2161449253","https://openalex.org/W2162006472","https://openalex.org/W2164330572","https://openalex.org/W2168573734","https://openalex.org/W2170037597","https://openalex.org/W2182722412","https://openalex.org/W2325552192","https://openalex.org/W2338318698","https://openalex.org/W2912724389","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2341492732","https://openalex.org/W3187193180","https://openalex.org/W106542691","https://openalex.org/W1699080303","https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W4388692845","https://openalex.org/W3202731209","https://openalex.org/W3211874991","https://openalex.org/W3191926225"],"abstract_inverted_index":{"In":[0,178],"the":[1,82,90,112,172],"domain":[2],"of":[3,7,49,56,71,78,114,122,150,191,211],"machine":[4],"learning,":[5],"quality":[6,216],"data":[8,115,125,194],"is":[9,19,33,128,155,171],"most":[10,55],"critical":[11],"component":[12],"for":[13,157,161,175,188],"building":[14],"good":[15],"models.":[16],"Predictive":[17],"analytics":[18],"an":[20],"AI":[21],"stream":[22],"used":[23,34],"to":[24,63,68,81,103,135,166,205],"predict":[25],"future":[26],"events":[27],"based":[28],"on":[29],"historical":[30],"learnings":[31],"and":[32,139,186],"in":[35,54,89,96,152],"diverse":[36],"fields":[37],"like":[38,86,105],"predicting":[39],"online":[40,92],"frauds,":[41],"oil":[42],"slicks,":[43],"intrusion":[44],"attacks,":[45],"credit":[46],"defaults,":[47],"prognosis":[48],"disease":[50],"cells":[51],"etc.":[52],"Unfortunately,":[53],"these":[57],"cases,":[58],"traditional":[59],"learning":[60,117],"models":[61],"fail":[62],"generate":[64,140],"required":[65],"results":[66,187],"due":[67,102],"imbalanced":[69,97],"nature":[70],"data.":[72],"Here":[73],"imbalance":[74],"denotes":[75],"small":[76,106],"number":[77],"instances":[79,88],"belonging":[80],"class":[83,124,193],"under":[84,169,195],"prediction":[85,95],"fraud":[87],"total":[91],"transactions.":[93],"The":[94],"classification":[98],"gets":[99],"further":[100],"limited":[101],"factors":[104],"disjuncts":[107],"which":[108,214],"get":[109],"accentuated":[110],"during":[111],"partitioning":[113],"when":[116],"at":[118],"scale.":[119],"Synthetic":[120],"generation":[121,190],"minority":[123,192],"(SMOTE":[126],"[1])":[127],"one":[129],"pioneering":[130],"approach":[131],"by":[132],"Chawla":[133],"[1]":[134],"offset":[136],"said":[137],"limitations":[138],"more":[141],"balanced":[142],"datasets.":[143,163],"Although":[144],"there":[145],"exists":[146],"a":[147,208],"standard":[148],"implementation":[149],"SMOTE":[151,165,213],"python,":[153],"it":[154],"unavailable":[156],"distributed":[158,167,209],"computing":[159],"environments":[160],"large":[162],"Bringing":[164],"environment":[168],"spark":[170,196],"key":[173],"motivation":[174],"our":[176,183],"research.":[177],"this":[179],"paper":[180],"we":[181],"present":[182],"algorithm,":[184],"observations":[185],"synthetic":[189],"using":[197],"Locality":[198],"Sensitivity":[199],"Hashing":[200],"[LSH].":[201],"We":[202],"were":[203],"able":[204],"successfully":[206],"demonstrate":[207],"version":[210],"Spark":[212],"generated":[215],"artificial":[217],"samples":[218],"preserving":[219],"spatial":[220],"distribution1.":[221]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}