{"id":"https://openalex.org/W2145955964","doi":"https://doi.org/10.1145/1233321.1233325","title":"Maximizing classifier utility when training data is costly","display_name":"Maximizing classifier utility when training data is costly","publication_year":2006,"publication_date":"2006-12-01","ids":{"openalex":"https://openalex.org/W2145955964","doi":"https://doi.org/10.1145/1233321.1233325","mag":"2145955964"},"language":"en","primary_location":{"id":"doi:10.1145/1233321.1233325","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1233321.1233325","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGKDD Explorations Newsletter","raw_type":"journal-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":"https://openalex.org/A5073269476","display_name":"Gary M. Weiss","orcid":"https://orcid.org/0000-0001-5009-7101"},"institutions":[{"id":"https://openalex.org/I164389053","display_name":"Fordham University","ror":"https://ror.org/03qnxaf80","country_code":"US","type":"education","lineage":["https://openalex.org/I164389053"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gary M. Weiss","raw_affiliation_strings":["Fordham University, Bronx, NY","Fordham University (Bronx, NY)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fordham University, Bronx, NY","institution_ids":["https://openalex.org/I164389053"]},{"raw_affiliation_string":"Fordham University (Bronx, NY)","institution_ids":["https://openalex.org/I164389053"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101883911","display_name":"Ye Tian","orcid":"https://orcid.org/0000-0002-6846-5141"},"institutions":[{"id":"https://openalex.org/I164389053","display_name":"Fordham University","ror":"https://ror.org/03qnxaf80","country_code":"US","type":"education","lineage":["https://openalex.org/I164389053"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ye Tian","raw_affiliation_strings":["Fordham University, Bronx, NY","Fordham University (Bronx, NY)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fordham University, Bronx, NY","institution_ids":["https://openalex.org/I164389053"]},{"raw_affiliation_string":"Fordham University (Bronx, NY)","institution_ids":["https://openalex.org/I164389053"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I164389053"],"apc_list":null,"apc_paid":null,"fwci":4.16,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.93919126,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"8","issue":"2","first_page":"31","last_page":"38"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","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/T12072","display_name":"Machine Learning and Algorithms","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/T12535","display_name":"Machine Learning and Data Classification","score":0.9976999759674072,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9945999979972839,"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":0.8511978387832642},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.8105450868606567},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6890741586685181},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.664971113204956},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.607952356338501},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.45199114084243774}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8511978387832642},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.8105450868606567},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6890741586685181},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.664971113204956},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.607952356338501},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45199114084243774}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1233321.1233325","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1233321.1233325","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGKDD Explorations Newsletter","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.119.4357","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.119.4357","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ic.uff.br/~bianca/ubdm-camera-ready/weiss-ubdm06.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.63.976","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.63.976","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://storm.cis.fordham.edu/~gweiss/papers/ubdm06.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.71.7358","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.71.7358","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://storm.cis.fordham.edu/~gweiss/papers/sigkdd06.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1504694836","https://openalex.org/W1562418542","https://openalex.org/W1819386543","https://openalex.org/W1994326354","https://openalex.org/W2026829590","https://openalex.org/W2084812512","https://openalex.org/W2108955812","https://openalex.org/W2114968414","https://openalex.org/W2124920454","https://openalex.org/W2125055259","https://openalex.org/W2148831205","https://openalex.org/W2151023586","https://openalex.org/W2167793421","https://openalex.org/W2997149703","https://openalex.org/W4252378842"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347","https://openalex.org/W4210805261"],"abstract_inverted_index":{"Classification":[0],"is":[1],"a":[2,64,102],"well-studied":[3],"problem":[4],"in":[5,24,78],"machine":[6],"learning":[7],"and":[8,106],"data":[9,80,92,104],"mining.":[10],"Classifier":[11],"performance":[12,109],"was":[13],"originally":[14],"gauged":[15],"almost":[16],"exclusively":[17],"using":[18],"predictive":[19],"accuracy.":[20],"However,":[21],"as":[22],"work":[23,47],"the":[25,37,40,50,60,71,75,79,85,88,96,108,117,120,131],"field":[26],"progressed,":[27],"more":[28],"sophisticated":[29],"measures":[30],"of":[31,39,52,63,73,87,90,110,119],"classifier":[32],"utility":[33,62],"that":[34,126],"better":[35],"represented":[36],"value":[38],"induced":[41],"knowledge":[42],"were":[43],"introduced.":[44],"Nonetheless,":[45],"most":[46],"still":[48],"ignored":[49],"cost":[51,89,118],"acquiring":[53,74],"training":[54,76,91,98,121],"examples,":[55],"even":[56],"though":[57],"this":[58,67],"affects":[59],"overall":[61,132],"classifier.":[65],"In":[66],"paper":[68],"we":[69,83],"consider":[70],"costs":[72],"examples":[77],"mining":[81],"process;":[82],"analyze":[84,107],"impact":[86],"on":[93],"learning,":[94],"identify":[95],"optimal":[97],"set":[99],"size":[100],"for":[101],"given":[103,116],"set,":[105],"several":[111],"progressive":[112],"sampling":[113],"schemes,":[114],"which,":[115],"data,":[122],"will":[123],"generate":[124],"classifiers":[125],"come":[127],"close":[128],"to":[129],"maximizing":[130],"utility.":[133]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}