{"id":"W7081566496","doi":"10.48550/arxiv.2509.09127","title":"Anti-Money Laundering Machine Learning Pipelines; A Technical Analysis on Identifying High-risk Bank Clients with Supervised Learning","year":2025,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Pipeline (software); Technical analysis; Feature (linguistics); Feature engineering; Supervised learning; Task (project management); Big data","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005175444,0.0009883991,0.0005866871,0.001847786,0.0005812927,0.001182839,0.001605333,0.0009538947,0.001723851],"category_scores_gemma":[0.01288419,0.000412012,0.0007325575,0.0009625384,0.0005986571,0.001873447,0.001879049,0.001680782,0.001525003],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009347965,"about_ca_system_score_gemma":0.001957452,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003598344,"about_ca_topic_score_gemma":0.005052533,"domain_scores_codex":[0.9977117,0.0008648463,0.0001331142,0.0005578023,0.0005483453,0.000184288],"domain_scores_gemma":[0.9928706,0.003426045,0.0006481216,0.001407474,0.001351444,0.000296242],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008113443,0.001192526,0.06453733,0.0003134763,0.0002839394,0.0003411952,0.0004740389,0.08290822,0.01977883,0.009086678,0.02987054,0.7904019],"study_design_scores_gemma":[0.00004221295,0.0002153383,0.008869044,0.00002119797,0.00003042436,0.0001157507,0.00008258039,0.963681,0.01443182,0.008435938,0.004045429,0.00002925339],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1795621,0.0006770606,0.7775902,0.002135375,0.0001245956,0.0006021965,0.002459213,0.03239303,0.00445628],"genre_scores_gemma":[0.6598133,0.0001474353,0.3308523,0.0004411086,0.00009899775,0.0003472668,0.005153692,0.0002795705,0.002866266],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005175444,"threshold_uncertainty_score":0.02737069,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03742345089504032,"score_gpt":0.194371840269054,"score_spread":0.1569483893740137,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}