{"id":"W4395683488","doi":"10.3390/jrfm17050181","title":"Machine Learning to Enhance the Detection of Terrorist Financing and Suspicious Transactions in Migrant Remittances","year":2024,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Universiteit van die Vrystaat","keywords":"Remittance; False positive paradox; Terrorism; Anomaly detection; Outlier; Finance; Poverty; Financial transaction; Computer science; Business; Computer security; Database; Artificial intelligence; Economics; Database transaction; Economic growth; Political science; Law","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":[0.0003950785,0.00005754494,0.000101623,0.0001775766,0.0001252393,0.00004784619,0.0001186783,0.00002088108,7.222827e-7],"category_scores_gemma":[0.00001284642,0.00004140523,0.00003801735,0.0004132776,0.00002194043,0.0001258503,0.0000259837,0.0002001682,3.214685e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000209976,"about_ca_system_score_gemma":0.000009523034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001325731,"about_ca_topic_score_gemma":0.0002566446,"domain_scores_codex":[0.9994446,0.00002580836,0.0002462337,0.0001142359,0.0000936492,0.00007548399],"domain_scores_gemma":[0.9997393,0.00004231881,0.00009690227,0.0000763414,0.0000225275,0.00002258061],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00000966818,0.00001215435,0.000130349,0.00002584611,0.000003507821,0.000007817355,0.001313027,0.0004129537,0.0003470907,0.001089568,0.000005544603,0.9966425],"study_design_scores_gemma":[0.0007406513,0.002037688,0.1210123,0.00133004,0.0002005423,0.0003034525,0.001817579,0.1534479,0.02570836,0.02587331,0.666882,0.0006461346],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.108329,0.00250886,0.8885923,0.0003214277,0.0001007628,0.00009724531,9.476797e-7,0.00001488613,0.00003454493],"genre_scores_gemma":[0.9894624,0.003504937,0.006903558,0.00002227577,0.00002501696,0.00001019905,3.085459e-8,0.00000278026,0.00006877185],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9959964,"threshold_uncertainty_score":0.1688456,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.003952923672452689,"score_gpt":0.2276437952725357,"score_spread":0.223690871600083,"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."}}