{"id":"https://openalex.org/W7224879869","doi":"https://doi.org/10.5281/zenodo.23787388","title":"Correcting a Classifier When Class Frequencies Change: Prior Adjustment by EM and by Confusion-Matrix Inversion on Three UCI Data Sets, and When the Correction Does Not Help","display_name":"Correcting a Classifier When Class Frequencies Change: Prior Adjustment by EM and by Confusion-Matrix Inversion on Three UCI Data Sets, and When the Correction Does Not Help","publication_year":2026,"publication_date":"2026-10-30","ids":{"openalex":"https://openalex.org/W7224879869","doi":"https://doi.org/10.5281/zenodo.23787388"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23787388","doi":"https://doi.org/10.5281/zenodo.23787388","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23787388","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.23787388","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5159002730","display_name":"Manoj Kumar Aguru","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405266258","display_name":"Chaitanya","ror":"https://ror.org/01m1bpg27","country_code":"IN","type":"education","lineage":["https://openalex.org/I4405266258"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Aguru, Manoj Kumar","raw_affiliation_strings":["Former Officer, Chaitanya Godavari Grameena Bank (CGGB)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Former Officer, Chaitanya Godavari Grameena Bank (CGGB)","institution_ids":["https://openalex.org/I4405266258"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5159002730"],"corresponding_institution_ids":["https://openalex.org/I4405266258"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":0.739300012588501,"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":0.739300012588501,"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":0.10480000078678131,"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":0.0729999989271164,"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/label-shift","display_name":"label shift","score":0.890999972820282},{"id":"https://openalex.org/keywords/probability-calibration","display_name":"probability calibration","score":0.7549999952316284},{"id":"https://openalex.org/keywords/expectation-maximization-algorithm","display_name":"expectation-maximization algorithm","score":0.6230000257492065},{"id":"https://openalex.org/keywords/prevalence-estimation","display_name":"prevalence estimation","score":0.531000018119812},{"id":"https://openalex.org/keywords/cross-entropy-loss","display_name":"cross-entropy loss","score":0.7570000290870667}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6079000234603882},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6068000197410583},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.52920001745224},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5027999877929688},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4399000108242035},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4090000092983246},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.37689998745918274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3476000130176544},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.3098999857902527},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.29499998688697815},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2833999991416931},{"id":"https://openalex.org/C19619285","wikidata":"https://www.wikidata.org/wiki/Q196372","display_name":"Observational error","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.25209999084472656}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23787388","doi":"https://doi.org/10.5281/zenodo.23787388","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23787388","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.5281/zenodo.23787389","doi":"https://doi.org/10.5281/zenodo.23787389","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23787389","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.5281/zenodo.23787388","doi":"https://doi.org/10.5281/zenodo.23787388","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23787388","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2141253686","https://openalex.org/W3023812961","https://openalex.org/W7223710431","https://openalex.org/W2982365439","https://openalex.org/W1506338521","https://openalex.org/W3117521168","https://openalex.org/W7213477062","https://openalex.org/W4417094375","https://openalex.org/W7007811266","https://openalex.org/W4409983080"],"abstract_inverted_index":{"A":[0],"classifier":[1,158],"trained":[2],"where":[3,14,156],"40%":[4],"of":[5,53,185],"cases":[6],"are":[7,205],"positive":[8],"will":[9],"give":[10],"poorly":[11],"calibrated":[12],"probabilities":[13,204],"10%":[15],"are.":[16],"If":[17],"only":[18],"the":[19,32,38,50,71,74,101,124,129,132,143,153,157,162,186,197,202],"class":[20],"frequencies":[21],"change":[22],"(label":[23],"shift),":[24],"Bayes'":[25],"rule":[26],"gives":[27],"an":[28],"exact":[29],"correction":[30,68,72,109,193],"once":[31],"new":[33],"frequency":[34,39],"is":[35,159,164,175,199],"known,":[36],"and":[37,56,58,69,85,118,127,139,169,201],"can":[40],"be":[41],"estimated":[42,133],"from":[43,93,113,135,147],"unlabelled":[44],"data.":[45],"I":[46],"compare":[47],"two":[48],"estimators,":[49],"EM":[51],"method":[52],"Saerens,":[54],"Latinne":[55],"Decaestecker":[57],"black-box":[59],"shift":[60,198],"estimation":[61],"(BBSE)":[62],"by":[63],"confusion-matrix":[64],"inversion,":[65],"with":[66,70,123],"no":[67],"at":[73,170],"true":[75,125],"frequency,":[76,126],"using":[77],"logistic":[78],"regression":[79],"on":[80,190],"three":[81],"UCI":[82],"data":[83],"sets":[84,87],"test":[86],"resampled":[88],"to":[89,95,115,137,149,167],"seven":[90],"target":[91,172],"prevalences":[92,173],"0.1":[94],"0.9":[96],"(50":[97],"replicates":[98],"each).":[99],"On":[100,141,152],"MAGIC":[102],"gamma":[103],"telescope":[104],"data,":[105,155],"averaged":[106],"over":[107],"targets,":[108],"cuts":[110,128],"log":[111,144,188],"loss":[112,145,189],"0.5204":[114],"0.3704":[116],"(EM)":[117],"0.3702":[119],"(BBSE),":[120],"against":[121],"0.3697":[122],"error":[130],"in":[131],"prevalence":[134],"0.1795":[136],"0.0100":[138],"0.0092.":[140],"spambase":[142],"falls":[146],"0.2505":[148],"about":[150],"0.195.":[151],"banknote":[154],"nearly":[160],"perfect,":[161],"gain":[163],"small":[165],"(0.0570":[166],"0.0466\u20130.0485)":[168],"high":[171],"accuracy":[174],"slightly":[176],"lower":[177],"after":[178],"correction.":[179],"Both":[180],"estimators":[181],"come":[182],"within":[183],"0.0018":[184],"oracle":[187],"average.":[191],"The":[192],"helps":[194],"most":[195],"when":[196],"large":[200],"classifier's":[203],"uncertain.":[206]},"counts_by_year":[],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2026-10-31T00:00:00"}