{"id":"https://openalex.org/W2023938061","doi":"https://doi.org/10.1109/ictai.2007.71","title":"Mining Data with Rare Events: A Case Study","display_name":"Mining Data with Rare Events: A Case Study","publication_year":2007,"publication_date":"2007-10-01","ids":{"openalex":"https://openalex.org/W2023938061","doi":"https://doi.org/10.1109/ictai.2007.71","mag":"2023938061"},"language":"en","primary_location":{"id":"doi:10.1109/ictai.2007.71","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictai.2007.71","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"19th IEEE International Conference on Tools with Artificial Intelligence(ICTAI 2007)","raw_type":"proceedings-article"},"type":"article","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":null,"display_name":"Chris Seiffert","orcid":null},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]},{"id":"https://openalex.org/I71437568","display_name":"Universidade de Pernambuco","ror":"https://ror.org/00gtcbp88","country_code":"BR","type":"education","lineage":["https://openalex.org/I71437568"]}],"countries":["BR","US"],"is_corresponding":true,"raw_author_name":"Chris Seiffert","raw_affiliation_strings":["Department of Computer Science and Engineering, Florida Atlantic University, Boca Raton, FL, USA","[Fed. Univ. of Pernambuco, Recife]"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Florida Atlantic University, Boca Raton, FL, USA","institution_ids":["https://openalex.org/I63772739"]},{"raw_affiliation_string":"[Fed. Univ. of Pernambuco, Recife]","institution_ids":["https://openalex.org/I71437568"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Taghi M. Khoshgoftaar","orcid":null},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]},{"id":"https://openalex.org/I71437568","display_name":"Universidade de Pernambuco","ror":"https://ror.org/00gtcbp88","country_code":"BR","type":"education","lineage":["https://openalex.org/I71437568"]}],"countries":["BR","US"],"is_corresponding":false,"raw_author_name":"Taghi M. Khoshgoftaar","raw_affiliation_strings":["Department of Computer Science and Engineering, Florida Atlantic University, Boca Raton, FL, USA","[Fed. Univ. of Pernambuco, Recife]"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Florida Atlantic University, Boca Raton, FL, USA","institution_ids":["https://openalex.org/I63772739"]},{"raw_affiliation_string":"[Fed. Univ. of Pernambuco, Recife]","institution_ids":["https://openalex.org/I71437568"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jason Van Hulse","orcid":null},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]},{"id":"https://openalex.org/I71437568","display_name":"Universidade de Pernambuco","ror":"https://ror.org/00gtcbp88","country_code":"BR","type":"education","lineage":["https://openalex.org/I71437568"]}],"countries":["BR","US"],"is_corresponding":false,"raw_author_name":"Jason Van Hulse","raw_affiliation_strings":["Department of Computer Science and Engineering, Florida Atlantic University, Boca Raton, FL, USA","University of pernambuco"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Florida Atlantic University, Boca Raton, FL, USA","institution_ids":["https://openalex.org/I63772739"]},{"raw_affiliation_string":"University of pernambuco","institution_ids":["https://openalex.org/I71437568"]}]},{"author_position":"last","author":{"id":null,"display_name":"Amri Napolitano","orcid":null},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]},{"id":"https://openalex.org/I71437568","display_name":"Universidade de Pernambuco","ror":"https://ror.org/00gtcbp88","country_code":"BR","type":"education","lineage":["https://openalex.org/I71437568"]}],"countries":["BR","US"],"is_corresponding":false,"raw_author_name":"Amri Napolitano","raw_affiliation_strings":["Department of Computer Science and Engineering, Florida Atlantic University, Boca Raton, FL, USA","University of pernambuco"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Florida Atlantic University, Boca Raton, FL, USA","institution_ids":["https://openalex.org/I63772739"]},{"raw_affiliation_string":"University of pernambuco","institution_ids":["https://openalex.org/I71437568"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63772739","https://openalex.org/I71437568"],"apc_list":null,"apc_paid":null,"fwci":2.4182,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.89840525,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"132","last_page":"139"},"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/T13429","display_name":"Electricity Theft Detection Techniques","score":0.9912999868392944,"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/T11653","display_name":"Financial Distress and Bankruptcy Prediction","score":0.9679999947547913,"subfield":{"id":"https://openalex.org/subfields/1402","display_name":"Accounting"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/rare-events","display_name":"Rare events","score":0.8661634922027588},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6899867653846741},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6737849712371826},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5338820815086365},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5295062065124512},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.49555933475494385},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4574325680732727},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4251961410045624},{"id":"https://openalex.org/keywords/data-sampling","display_name":"Data sampling","score":0.41209226846694946},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33303195238113403},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.28546494245529175},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13942071795463562}],"concepts":[{"id":"https://openalex.org/C2777317252","wikidata":"https://www.wikidata.org/wiki/Q18393516","display_name":"Rare events","level":2,"score":0.8661634922027588},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6899867653846741},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6737849712371826},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5338820815086365},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5295062065124512},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.49555933475494385},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4574325680732727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4251961410045624},{"id":"https://openalex.org/C2985946229","wikidata":"https://www.wikidata.org/wiki/Q49908","display_name":"Data sampling","level":2,"score":0.41209226846694946},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33303195238113403},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.28546494245529175},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13942071795463562},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictai.2007.71","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictai.2007.71","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"19th IEEE International Conference on Tools with Artificial Intelligence(ICTAI 2007)","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":36,"referenced_works":["https://openalex.org/W41129630","https://openalex.org/W65738273","https://openalex.org/W85350352","https://openalex.org/W167016754","https://openalex.org/W409166618","https://openalex.org/W1490573914","https://openalex.org/W1570448133","https://openalex.org/W1572615921","https://openalex.org/W1819386543","https://openalex.org/W1965895350","https://openalex.org/W1994892446","https://openalex.org/W2011376672","https://openalex.org/W2053606794","https://openalex.org/W2084812512","https://openalex.org/W2109288821","https://openalex.org/W2114968414","https://openalex.org/W2116419779","https://openalex.org/W2119168155","https://openalex.org/W2123977051","https://openalex.org/W2124776405","https://openalex.org/W2132791018","https://openalex.org/W2136903812","https://openalex.org/W2140060749","https://openalex.org/W2140187489","https://openalex.org/W2148143831","https://openalex.org/W2170325853","https://openalex.org/W2911964244","https://openalex.org/W3017201198","https://openalex.org/W4229772528","https://openalex.org/W4235072768","https://openalex.org/W6603460400","https://openalex.org/W6606837198","https://openalex.org/W6638261285","https://openalex.org/W6678797503","https://openalex.org/W6679745481","https://openalex.org/W6680202767"],"related_works":["https://openalex.org/W2368644753","https://openalex.org/W2367538773","https://openalex.org/W2075654366","https://openalex.org/W2023938061","https://openalex.org/W2096760809","https://openalex.org/W1999758163","https://openalex.org/W2092657059","https://openalex.org/W2064155031","https://openalex.org/W2135107501","https://openalex.org/W4211047554"],"abstract_inverted_index":{"The":[0],"performance":[1,74,88],"of":[2,28,41,57,66,97,114],"classification":[3,73],"models":[4],"can":[5,50],"be":[6],"negatively":[7],"impacted":[8],"if":[9,32],"the":[10,26,39,47,58,64,78,87,112],"data":[11,99,105],"on":[12,72],"which":[13],"they":[14],"are":[15,81],"trained":[16],"contains":[17],"very":[18,108],"rare":[19,115],"events.":[20,116],"While":[21],"recent":[22],"research":[23],"has":[24],"investigated":[25],"issue":[27],"class":[29,49,70,80],"imbalance,":[30],"few":[31],"any":[33],"studies":[34],"address":[35],"issues":[36],"related":[37],"to":[38,95],"handling":[40],"extreme":[42],"imbalance":[43],"(rare":[44],"events),":[45],"where":[46],"minority":[48,79],"account":[51],"for":[52],"as":[53,55],"little":[54],"0.1%":[56],"training":[59],"data.":[60],"This":[61],"work":[62],"investigates":[63],"effect":[65],"dataset":[67],"size":[68],"and":[69],"distribution":[71],"when":[75],"examples":[76,94],"from":[77],"rare.":[82],"In":[83],"addition,":[84],"we":[85],"compare":[86],"improvement":[89],"achieved":[90],"by":[91],"acquiring":[92],"additional":[93],"that":[96,104],"applying":[98],"sampling.":[100],"Our":[101],"results":[102],"demonstrate":[103],"sampling":[106],"is":[107],"effective":[109],"at":[110],"alleviating":[111],"problem":[113]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2016-06-24T00:00:00"}