{"id":"https://openalex.org/W4415420689","doi":"https://doi.org/10.1186/s40537-025-01248-w","title":"Scalable unsupervised labeling with SHAP feature selection for fraud detection in imbalanced data","display_name":"Scalable unsupervised labeling with SHAP feature selection for fraud detection in imbalanced data","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4415420689","doi":"https://doi.org/10.1186/s40537-025-01248-w"},"language":"en","primary_location":{"id":"doi:10.1186/s40537-025-01248-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-025-01248-w","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-025-01248-w","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-025-01248-w","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011476239","display_name":"Mary Anne Walauskis","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"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mary Anne Walauskis","raw_affiliation_strings":["College of Engineering & Computer Science, Florida Atlantic University, 777 Glades Road, Boca Raton, FL, 33431, USA"],"affiliations":[{"raw_affiliation_string":"College of Engineering & Computer Science, Florida Atlantic University, 777 Glades Road, Boca Raton, FL, 33431, USA","institution_ids":["https://openalex.org/I63772739"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089170562","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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taghi M. Khoshgoftaar","raw_affiliation_strings":["College of Engineering & Computer Science, Florida Atlantic University, 777 Glades Road, Boca Raton, FL, 33431, USA"],"affiliations":[{"raw_affiliation_string":"College of Engineering & Computer Science, Florida Atlantic University, 777 Glades Road, Boca Raton, FL, 33431, USA","institution_ids":["https://openalex.org/I63772739"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5011476239"],"corresponding_institution_ids":["https://openalex.org/I63772739"],"apc_list":{"value":1060,"currency":"GBP","value_usd":1300},"apc_paid":{"value":1060,"currency":"GBP","value_usd":1300},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16152927,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":"1","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":0.9998999834060669,"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":0.9998000264167786,"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":0.9970999956130981,"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/jaccard-index","display_name":"Jaccard index","score":0.7767999768257141},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.6158000230789185},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5522000193595886},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.5401999950408936},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5393999814987183},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5378000140190125},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42660000920295715}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8610000014305115},{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.7767999768257141},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.671999990940094},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6158000230789185},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5522000193595886},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5401999950408936},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5393999814987183},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5378000140190125},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5299000144004822},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42660000920295715},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.36649999022483826},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36570000648498535},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.2567000091075897}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s40537-025-01248-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-025-01248-w","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-025-01248-w","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:c4c38d7aa60245ffa46a2c09072b1be5","is_oa":true,"landing_page_url":"https://doaj.org/article/c4c38d7aa60245ffa46a2c09072b1be5","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Big Data, Vol 12, Iss 1, Pp 1-26 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s40537-025-01248-w","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-025-01248-w","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-025-01248-w","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310801","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387"},{"id":"https://openalex.org/F4320317380","display_name":"Universidad del Atl\u00e1ntico","ror":"https://ror.org/05mm1w714"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415420689.pdf","grobid_xml":"https://content.openalex.org/works/W4415420689.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W2051627038","https://openalex.org/W2103018059","https://openalex.org/W2114060717","https://openalex.org/W2296719434","https://openalex.org/W2338318698","https://openalex.org/W2340896621","https://openalex.org/W2564754306","https://openalex.org/W2565047864","https://openalex.org/W2596052762","https://openalex.org/W2683833049","https://openalex.org/W2943758177","https://openalex.org/W2945876440","https://openalex.org/W2989219518","https://openalex.org/W2990138404","https://openalex.org/W2999309192","https://openalex.org/W3033548640","https://openalex.org/W3037381232","https://openalex.org/W3037682562","https://openalex.org/W3108391844","https://openalex.org/W3108807663","https://openalex.org/W3128837268","https://openalex.org/W3186605977","https://openalex.org/W3206152519","https://openalex.org/W4282946014","https://openalex.org/W4283160212","https://openalex.org/W4283791631","https://openalex.org/W4289236186","https://openalex.org/W4306317276","https://openalex.org/W4311543603","https://openalex.org/W4366308790","https://openalex.org/W4380685430","https://openalex.org/W4387157425","https://openalex.org/W4388115374","https://openalex.org/W4388229648","https://openalex.org/W4391935956","https://openalex.org/W4393930981","https://openalex.org/W4402642396","https://openalex.org/W4402966057","https://openalex.org/W4404492403","https://openalex.org/W4406799292","https://openalex.org/W4406895100","https://openalex.org/W4408339736"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"There":[1],"is":[2,12,130],"a":[3,29,91,171],"growing":[4],"need":[5],"for":[6,141,174],"labeled":[7],"data,":[8],"yet":[9],"manual":[10],"annotation":[11],"costly,":[13],"error-prone,":[14],"and":[15,59,69,103,117,155,165],"often":[16],"infeasible":[17],"in":[18],"privacy-sensitive,":[19],"highly":[20],"imbalanced":[21,179],"domains":[22],"such":[23],"as":[24],"fraud":[25],"detection.":[26],"We":[27,48,106],"introduce":[28],"fully":[30],"unsupervised":[31,35,45,50,76,93],"framework":[32],"that":[33],"combines":[34],"SHapley":[36],"Additive":[37],"exPlanations":[38],"(SHAP)":[39],"feature":[40,67,153],"selection":[41],"with":[42,74,150],"our":[43,75,86,121,168],"novel":[44,87],"labeling":[46,77],"method.":[47],"apply":[49,90],"SHAP":[51],"to":[52,64,98,132],"the":[53,72,82,100,125,134,147,151],"Kaggle":[54],"Credit":[55],"Card":[56],"Fraud":[57],"Detection":[58],"Medicare":[60],"Part":[61],"D":[62],"datasets":[63,73,102],"produce":[65],"high-impact":[66],"subsets,":[68],"then":[70],"label":[71,159],"approach.":[78],"To":[79],"effectively":[80],"evaluate":[81],"labels":[83,123,137],"generated":[84,122],"by":[85,119],"methodology,":[88],"we":[89],"baseline":[92],"learner,":[94],"Isolation":[95],"Forest":[96],"(IF),":[97],"both":[99],"original":[101],"their":[104],"subsets.":[105],"calculate":[107],"Matthew\u2019s":[108],"Correlation":[109],"Coefficient":[110],"(MCC),":[111],"Jaccard":[112],"Index":[113],"(JI),":[114],"Precision,":[115],"Recall,":[116],"F1-score":[118],"comparing":[120],"against":[124],"ground":[126,135],"truth":[127,136],"labels.":[128],"It":[129],"important":[131],"note,":[133],"were":[138],"used":[139],"solely":[140],"evaluation.":[142],"Our":[143],"empirical":[144],"results":[145,148],"surpass":[146],"obtained":[149],"full":[152],"dataset":[154],"baseline.":[156],"By":[157],"improving":[158],"quality":[160],"while":[161],"reducing":[162],"computational":[163],"complexity":[164],"preserving":[166],"privacy,":[167],"approach":[169],"offers":[170],"practical":[172],"solution":[173],"learning":[175],"from":[176],"unlabeled,":[177],"severely":[178],"data.":[180]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-24T00:00:00"}