{"id":"https://openalex.org/W7225326544","doi":"https://doi.org/10.21203/rs.3.rs-11618494/v1","title":"Prototype Learning with Concept Bottleneck Models for Interpretable Insurance Fraud Detection","display_name":"Prototype Learning with Concept Bottleneck Models for Interpretable Insurance Fraud Detection","publication_year":2026,"publication_date":"2026-11-05","ids":{"openalex":"https://openalex.org/W7225326544","doi":"https://doi.org/10.21203/rs.3.rs-11618494/v1"},"language":"en","primary_location":{"id":"doi:10.21203/rs.3.rs-11618494/v1","doi":"https://doi.org/10.21203/rs.3.rs-11618494/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11618494/v1","pdf_url":"https://www.researchsquare.com/article/rs-11618494/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.researchsquare.com/article/rs-11618494/latest.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5157870851","display_name":"Qinzheng Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I146563203","display_name":"University of International Business and Economics","ror":"https://ror.org/05khqpb71","country_code":"CN","type":"education","lineage":["https://openalex.org/I146563203"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qinzheng Wang","raw_affiliation_strings":["University of International Business and Economics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of International Business and Economics","institution_ids":["https://openalex.org/I146563203"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5157870851"],"corresponding_institution_ids":["https://openalex.org/I146563203"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":1.0,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":1.0,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":9.999999747378752e-05,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.0,"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/insurance-fraud-detection","display_name":"insurance fraud detection","score":0.9879999756813049},{"id":"https://openalex.org/keywords/prototype-learning","display_name":"prototype learning","score":0.8939999938011169},{"id":"https://openalex.org/keywords/concept-bottleneck-models","display_name":"concept bottleneck models","score":0.9959999918937683},{"id":"https://openalex.org/keywords/model-interpretability","display_name":"model interpretability","score":0.7549999952316284},{"id":"https://openalex.org/keywords/health-insurance-claims","display_name":"health insurance claims","score":0.7559999823570251},{"id":"https://openalex.org/keywords/regulatory-transparency","display_name":"regulatory transparency","score":0.5910000205039978}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9096999764442444},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.847100019454956},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6114000082015991},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5877000093460083},{"id":"https://openalex.org/C167729594","wikidata":"https://www.wikidata.org/wiki/Q17736","display_name":"Axiom","level":2,"score":0.5342000126838684},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5232999920845032},{"id":"https://openalex.org/C60008888","wikidata":"https://www.wikidata.org/wiki/Q6031013","display_name":"Information bottleneck method","level":3,"score":0.5203999876976013},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.49889999628067017},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.4625000059604645},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.3847000002861023},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35760000348091125},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21203/rs.3.rs-11618494/v1","doi":"https://doi.org/10.21203/rs.3.rs-11618494/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11618494/v1","pdf_url":"https://www.researchsquare.com/article/rs-11618494/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.21203/rs.3.rs-11618494/v1","doi":"https://doi.org/10.21203/rs.3.rs-11618494/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11618494/v1","pdf_url":"https://www.researchsquare.com/article/rs-11618494/latest.pdf","source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225326544.pdf","grobid_xml":"https://content.openalex.org/works/W7225326544.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7164154301","https://openalex.org/W7159977408","https://openalex.org/W2915336450","https://openalex.org/W7038641210","https://openalex.org/W2949038902","https://openalex.org/W3093009993","https://openalex.org/W3125559414","https://openalex.org/W7160837018","https://openalex.org/W7129332452","https://openalex.org/W7116080540"],"abstract_inverted_index":{"Abstract":[0],"Post-hoc":[1],"explanation":[2],"methods":[3],"(SHAP,":[4],"LIME,":[5],"GNNExplainer)":[6],"are":[7,21],"effective":[8],"at":[9,166,173],"describing":[10],"already-trained":[11],"models,":[12],"but":[13],"their":[14],"faithfulness":[15,41],"cannot":[16],"be":[17],"guaranteed,":[18],"and":[19,56,79,141,169,190],"they":[20],"sensitive":[22],"to":[23,125],"input":[24],"perturbations.":[25],"Intrinsically":[26],"interpretable":[27,48,97,164,200],"models":[28,59,193],"embed":[29],"interpretability":[30,67],"into":[31,106],"the":[32,36,40,62,85,89,99,104,118,145,184],"model":[33,148],"architecture":[34],"from":[35],"outset,":[37],"fundamentally":[38],"avoiding":[39],"problem.":[42],"This":[43],"paper":[44],"proposes":[45],"an":[46,199],"intrinsically":[47],"insurance-fraud":[49],"attribution":[50],"framework":[51],"built":[52],"on":[53],"prototype":[54,70,77,120,188],"learning":[55,189],"concept":[57,86,101,146,191],"bottleneck":[58,102,147,192],"(CBM).":[60],"At":[61,88],"theory":[63],"level,":[64,91],"we":[65,92],"establish":[66],"axioms":[68],"for":[69,76,84,194],"learning,":[71],"derive":[72],"a":[73,81,94,126,138,150,176],"convergence":[74],"rate":[75],"estimation,":[78],"prove":[80],"performance-decomposition":[82],"bound":[83],"bottleneck.":[87],"method":[90],"design":[93],"\"concept--prototype\"":[95],"two-layer":[96],"architecture:":[98],"bottom":[100],"decomposes":[103],"prediction":[105],"human-understandable":[107],"high-level":[108],"concepts":[109,165],"(e.g.,":[110],"time":[111],"anomaly,":[112,114],"amount":[113],"relation":[115],"anomaly),":[116],"while":[117,161],"top":[119],"layer":[121],"maps":[122],"each":[123],"case":[124],"fraud-type":[127],"prototype,":[128],"providing":[129],"example-level":[130],"explanations.":[131],"On":[132],"simulated":[133],"health-insurance":[134],"claim":[135],"data":[136],"with":[137],"realistically":[139],"weak":[140],"noisy":[142],"fraud":[143,171,196],"signal,":[144],"attains":[149],"test":[151],"AUC":[152],"of":[153,158,187],"0.806,":[154],"within":[155],"1-2":[156],"points":[157],"black-box":[159],"baselines,":[160],"predicting":[162],"seven":[163],"0.801":[167],"accuracy":[168],"attributing":[170],"types":[172],"36.4%":[174],"versus":[175],"25%":[177],"random":[178],"baseline.":[179],"The":[180],"core":[181],"contribution":[182],"is":[183],"first":[185],"combination":[186],"insurance":[195],"detection,":[197],"offering":[198],"alternative":[201],"that":[202],"satisfies":[203],"regulatory":[204],"transparency":[205],"requirements.":[206]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-11-06T00:00:00"}