{"id":"https://openalex.org/W7225625550","doi":"https://doi.org/10.48550/arxiv.2611.08706","title":"Dual-Stream LLM-Guided Reward Design for Reject-Inference-Aware Reinforcement Learning in E-Commerce Payment Fraud Detection","display_name":"Dual-Stream LLM-Guided Reward Design for Reject-Inference-Aware Reinforcement Learning in E-Commerce Payment Fraud Detection","publication_year":2026,"publication_date":"2026-11-05","ids":{"openalex":"https://openalex.org/W7225625550","doi":"https://doi.org/10.48550/arxiv.2611.08706"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2611.08706","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.08706","pdf_url":"https://arxiv.org/pdf/2611.08706","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2611.08706","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121064549","display_name":"Bo Qu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qu, Bo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161359335","display_name":"Zhurong Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhurong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115002544","display_name":"Frank Zahradnik","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zahradnik, Frank","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5160210946","display_name":"Ming Ouyang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ouyang, Ming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.8916000127792358,"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":0.8916000127792358,"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":0.04430000111460686,"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/T11644","display_name":"Spam and Phishing Detection","score":0.018300000578165054,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/payment-fraud-detection","display_name":"payment fraud detection","score":0.8519999980926514},{"id":"https://openalex.org/keywords/e-commerce-transactions","display_name":"e-commerce transactions","score":0.550000011920929}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7275999784469604},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6902999877929688},{"id":"https://openalex.org/C145097563","wikidata":"https://www.wikidata.org/wiki/Q1148747","display_name":"Payment","level":2,"score":0.6495000123977661},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5360000133514404},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.49570000171661377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.451200008392334},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.41370001435279846},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38920000195503235},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","level":2,"score":0.25929999351501465}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2611.08706","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.08706","pdf_url":"https://arxiv.org/pdf/2611.08706","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2611.08706","doi":"https://doi.org/10.48550/arxiv.2611.08706","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.08706","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"pmh:oai:arXiv.org:2611.08706","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.08706","pdf_url":"https://arxiv.org/pdf/2611.08706","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225625550.pdf","grobid_xml":"https://content.openalex.org/works/W7225625550.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W3177813494","https://openalex.org/W4311991106","https://openalex.org/W4403564379","https://openalex.org/W7148543823"],"related_works":["https://openalex.org/W4412886917","https://openalex.org/W4417358068","https://openalex.org/W7164028987","https://openalex.org/W7123270585","https://openalex.org/W7214147774","https://openalex.org/W6884991343","https://openalex.org/W7225645306","https://openalex.org/W4200633590","https://openalex.org/W4410304638","https://openalex.org/W7134931017"],"abstract_inverted_index":{"Production":[0],"fraud-detection":[1],"models":[2,22],"learn":[3],"from":[4],"a":[5,13,25,49,66,110,142],"censored":[6],"slice":[7],"of":[8,36,48,112,165,191],"their":[9],"own":[10],"traffic:":[11],"transactions":[12,85],"legacy":[14,95],"system":[15],"blocked":[16],"never":[17],"receive":[18],"fraud":[19],"labels,":[20],"so":[21],"train":[23],"on":[24,181],"biased,":[26],"approved-only":[27],"distribution.":[28],"We":[29],"extend":[30],"LLM-guided":[31],"reward":[32,47,133],"design,":[33],"the":[34,46,60,72,88,94,99,116,132,147,151,175],"framework":[35],"Qu":[37,192],"et":[38,193],"al.":[39,194],"(2025)":[40,195],"in":[41],"which":[42,105,121],"an":[43],"LLM":[44,64,117],"evolves":[45],"two-step":[50],"REINFORCE":[51],"fraud-blocking":[52],"policy,":[53],"to":[54,77,122,189],"attack":[55],"this":[56],"reject-inference":[57],"problem":[58],"inside":[59],"reward.":[61],"A":[62],"single":[63],"designs":[65],"dual-stream":[67,148],"reward:":[68],"stream":[69,80],"1":[70],"applies":[71],"standard":[73],"dollar-weighted":[74,166],"precision":[75,167],"objective":[76],"labeled":[78],"transactions;":[79],"2":[81],"scores":[82,96],"legacy-blocked,":[83],"unlabeled":[84],"by":[86,125,159,178],"contrasting":[87],"newest":[89],"gradient-boosted":[90],"risk":[91],"signal":[92],"against":[93],"that":[97,136,190],"drove":[98],"original":[100],"block.":[101],"Rather":[102],"than":[103],"prescribe":[104],"signals":[106],"matter,":[107],"we":[108],"expose":[109],"superset":[111],"evidence":[113],"and":[114,162,171,174,196],"let":[115],"decide":[118],"for":[119],"itself":[120],"use,":[123],"guided":[124],"evaluation":[126],"feedback":[127],"alone;":[128],"because":[129],"it":[130],"writes":[131],"as":[134],"code,":[135],"choice":[137],"is":[138,186],"directly":[139],"auditable.":[140],"On":[141],"held-out":[143],"four-month":[144],"out-of-time":[145],"test,":[146],"agent":[149,154],"beats":[150],"prior":[152],"labeled-only":[153],"at":[155,168],"every":[156],"target":[157],"recall,":[158,173],"+4.7,":[160],"+2.4":[161],"+3.0":[163],"points":[164,180],"80%,":[169],"85%":[170],"90%":[172],"production":[176],"baseline":[177],"+6.8":[179],"average.":[182],"The":[183],"resulting":[184],"policy":[185],"architecturally":[187],"identical":[188],"adds":[197],"no":[198],"inference":[199],"cost.":[200]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-10T00:00:00"}