{"id":"W7117130785","doi":"10.3390/jrfm19010014","title":"Recent Progress on Financial Risk Detection in the Context of Transaction Fraud Based on Machine Learning Algorithms","year":2025,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Financial Distress and Bankruptcy Prediction","field":"Business, Management and Accounting","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Database transaction; Feature engineering; Financial transaction; Credit card fraud; Feature (linguistics); Financial services; Categorization; Preprocessor; Data pre-processing","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00108505,0.0001749284,0.0002781873,0.0006154455,0.0002745827,0.00008427546,0.0001612677,0.0000930679,0.000009844622],"category_scores_gemma":[0.0002255296,0.0001276535,0.0001289854,0.0006867874,0.00005575903,0.0002546347,0.00002284701,0.0005610464,0.000002626841],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005569781,"about_ca_system_score_gemma":0.00002120968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002089809,"about_ca_topic_score_gemma":0.0003607344,"domain_scores_codex":[0.9986578,0.00007471056,0.0005295649,0.0001879177,0.0003705901,0.0001794526],"domain_scores_gemma":[0.9990181,0.00006917304,0.0006535296,0.0001184812,0.0001319893,0.000008780392],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00132064,0.0003936636,0.01998299,0.0001241308,0.000009801802,0.00002069202,0.00009334176,0.00146883,0.000003849216,0.002510078,0.000237446,0.9738345],"study_design_scores_gemma":[0.003670856,0.0005296253,0.7610457,0.0005935304,0.0002779631,0.000001128387,0.0004338438,0.02168094,0.000130302,0.002224967,0.2092144,0.0001967597],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9164308,0.001333034,0.07496506,0.0009503257,0.002512817,0.0009739218,0.00003025221,0.00004054173,0.002763248],"genre_scores_gemma":[0.9966691,0.002423624,0.00007662338,0.0004113969,0.0003717192,0.00001798908,0.000005355061,0.000008678726,0.00001552195],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9736378,"threshold_uncertainty_score":0.520556,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005985650318026749,"score_gpt":0.2064015438947776,"score_spread":0.2004158935767508,"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."}}