{"id":"W4409149437","doi":"10.1016/j.jfds.2025.100163","title":"Finding a needle in a haystack: A machine learning framework for anomaly detection in payment systems","year":2025,"lang":"en","type":"article","venue":"The Journal of Finance and Data Science","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Bank of Canada","funders":"","keywords":"Haystack; Payment; Anomaly detection; Computer science; Anomaly (physics); Artificial intelligence; Machine learning; World Wide Web","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002492359,0.0000537117,0.0001086388,0.0002668941,0.0002467911,0.0001327879,0.001125595,0.00002523036,2.286977e-7],"category_scores_gemma":[0.0001714771,0.00003777384,0.00001237967,0.001323655,0.00008095672,0.0008562633,0.000290572,0.0002183949,1.97376e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005717695,"about_ca_system_score_gemma":0.0001140469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001232959,"about_ca_topic_score_gemma":0.00004517254,"domain_scores_codex":[0.9992542,0.00003254895,0.0002675755,0.000168741,0.0001286358,0.0001483164],"domain_scores_gemma":[0.9992164,0.0001698866,0.000197151,0.0003457085,0.00005283636,0.00001803157],"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":[0.0001918013,0.0002492755,0.01499169,0.0001265192,0.00001437714,0.00001320703,0.003383981,0.01106784,0.032132,0.3500116,0.0002212134,0.5875965],"study_design_scores_gemma":[0.0004022751,0.0002768325,0.02154668,0.000446501,0.000007685107,0.00008621395,0.0004219815,0.9487179,0.005766322,0.01397458,0.008222888,0.0001301469],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1244816,0.0006635582,0.8740028,0.0005637752,0.00008850645,0.0001535463,0.000002819627,0.000008160154,0.0000352675],"genre_scores_gemma":[0.979989,0.000473197,0.01942345,0.00005555919,0.00001392131,0.00001060332,1.720512e-7,0.000001342642,0.00003276457],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.93765,"threshold_uncertainty_score":0.2091654,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02964399627286791,"score_gpt":0.3219928109928626,"score_spread":0.2923488147199947,"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."}}