{"id":"https://openalex.org/W4409363617","doi":"https://doi.org/10.1609/aaai.v39i19.34240","title":"Improving Model Probability Calibration by Integration of Large Data Sources with Biased Labels","display_name":"Improving Model Probability Calibration by Integration of Large Data Sources with Biased Labels","publication_year":2025,"publication_date":"2025-04-11","ids":{"openalex":"https://openalex.org/W4409363617","doi":"https://doi.org/10.1609/aaai.v39i19.34240"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v39i19.34240","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i19.34240","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/34240/36395","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/34240/36395","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029573357","display_name":"Renat Sergazinov","orcid":"https://orcid.org/0000-0001-5905-3674"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE","US"],"is_corresponding":true,"raw_author_name":"Renat Sergazinov","raw_affiliation_strings":["Texas A&M University\nAmazon"],"affiliations":[{"raw_affiliation_string":"Texas A&M University\nAmazon","institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107889400","display_name":"Richard Chen","orcid":"https://orcid.org/0000-0002-7740-0251"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Richard Chen","raw_affiliation_strings":["Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059393102","display_name":"Ji Cheng","orcid":"https://orcid.org/0000-0003-1610-2557"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Cheng Ji","raw_affiliation_strings":["Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023757993","display_name":"Jing Cynthia Wu","orcid":"https://orcid.org/0000-0003-4239-1233"},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jing Wu","raw_affiliation_strings":["Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034220067","display_name":"Daniel Cociorva","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Cociorva","raw_affiliation_strings":["Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025303186","display_name":"H. Brunzell","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hakan Brunzell","raw_affiliation_strings":["Amazon"],"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5029573357"],"corresponding_institution_ids":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17737003,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"39","issue":"19","first_page":"20338","last_page":"20345"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.5485000014305115,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.5485000014305115,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T12120","display_name":"Air Quality Monitoring and Forecasting","score":0.47839999198913574,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.699762761592865},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.45576012134552},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.4364653527736664},{"id":"https://openalex.org/keywords/probability-model","display_name":"Probability model","score":0.42828595638275146},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.4265735149383545},{"id":"https://openalex.org/keywords/environmental-science","display_name":"Environmental science","score":0.33256757259368896},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.30255407094955444}],"concepts":[{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.699762761592865},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45576012134552},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4364653527736664},{"id":"https://openalex.org/C2984179964","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Probability model","level":2,"score":0.42828595638275146},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.4265735149383545},{"id":"https://openalex.org/C39432304","wikidata":"https://www.wikidata.org/wiki/Q188847","display_name":"Environmental science","level":0,"score":0.33256757259368896},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30255407094955444}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v39i19.34240","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i19.34240","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/34240/36395","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v39i19.34240","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v39i19.34240","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/34240/36395","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409363617.pdf","grobid_xml":"https://content.openalex.org/works/W4409363617.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1922851888","https://openalex.org/W2114770238","https://openalex.org/W2406961220","https://openalex.org/W2365607528","https://openalex.org/W2046724649","https://openalex.org/W2555586164","https://openalex.org/W2030747924","https://openalex.org/W1499374895","https://openalex.org/W2365102679","https://openalex.org/W2043347519"],"abstract_inverted_index":{"Probability":[0],"calibration":[1,83],"transforms":[2],"raw":[3],"output":[4],"of":[5,82],"a":[6,24,80],"classification":[7],"model":[8,15,117],"into":[9],"empirically":[10],"interpretable":[11],"probability.":[12],"When":[13],"the":[14,75,87,96,109,115,122],"is":[16,48],"purposed":[17],"to":[18,36,70],"detect":[19],"rare":[20],"event":[21],"and":[22,94,120],"only":[23],"small":[25],"expensive":[26],"data":[27,46,53,77],"source":[28,47],"has":[29],"clean":[30],"labels,":[31],"it":[32,127],"becomes":[33],"extraordinarily":[34],"challenging":[35],"obtain":[37],"accurate":[38],"probability":[39],"calibration.":[40],"Utilizing":[41],"an":[42,65],"additional":[43],"large":[44,76],"cheap":[45],"very":[49],"helpful,":[50],"however,":[51],"such":[52],"sources":[54],"oftentimes":[55],"suffer":[56],"from":[57,74,108],"biased":[58],"labels.":[59],"To":[60],"this":[61],"end,":[62],"we":[63,90],"introduce":[64],"approximate":[66,110],"expectation-maximization":[67],"(EM)":[68],"algorithm":[69,99],"extract":[71],"useful":[72],"information":[73],"sources.":[78],"For":[79],"family":[81],"methods":[84],"based":[85],"on":[86,121],"logistic":[88],"likelihood,":[89],"derive":[91],"closed-form":[92],"updates":[93],"call":[95],"resulting":[97],"iterative":[98],"CalEM.":[100],"We":[101,113],"show":[102],"that":[103],"CalEM":[104],"inherits":[105],"convergence":[106],"guarantees":[107],"EM":[111],"algorithm.":[112],"test":[114],"proposed":[116],"in":[118],"simulation":[119],"real":[123],"marketing":[124],"datasets,":[125],"where":[126],"shows":[128],"significant":[129],"performance":[130],"increases.":[131]},"counts_by_year":[],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}