{"id":"W4321105142","doi":"10.1080/13504851.2023.2176435","title":"Predicting money laundering sanctions using machine learning algorithms and artificial neural networks","year":2023,"lang":"en","type":"article","venue":"Applied Economics Letters","topic":"Crime, Illicit Activities, and Governance","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Royal Roads University","funders":"","keywords":"Sanctions; Money laundering; Artificial neural network; Transparency (behavior); Machine learning; Artificial intelligence; Support vector machine; Logistic regression; Algorithm; Computer science; Financial crisis; Economics; Finance; Law; Computer security; Political science; Macroeconomics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003498811,0.0001245708,0.0001648346,0.00007423309,0.001072864,0.0001877538,0.0001002582,0.00007233075,0.00001360762],"category_scores_gemma":[0.0000239877,0.0001607247,0.00004324305,0.0001647299,0.0001675617,0.0002187668,0.00007240616,0.0002691654,0.000006957345],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001447101,"about_ca_system_score_gemma":0.00002111647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004366245,"about_ca_topic_score_gemma":0.002558289,"domain_scores_codex":[0.9989784,0.0000309056,0.0002006788,0.0002887736,0.0000726881,0.0004285281],"domain_scores_gemma":[0.99951,0.0001716334,0.0001322405,0.00009263959,0.000006124072,0.00008729583],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002939689,0.00001560751,0.02000635,0.00001214866,0.00006812008,0.000005077258,0.01690632,0.9264822,0.003535079,0.006936126,0.0002474645,0.02575613],"study_design_scores_gemma":[0.0002014059,0.000007724527,0.002796837,0.00000718412,0.00002340042,0.000002537786,0.007216861,0.9851896,0.0001387996,0.0004111063,0.003703248,0.0003012568],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9942744,0.00003700804,0.002773082,0.0008980974,0.0006023055,0.0001474671,0.00000673261,0.0002070644,0.001053841],"genre_scores_gemma":[0.9979256,0.0001621448,0.0002429199,0.0005458252,0.001008989,0.00001351772,0.00001103796,0.0000277691,0.00006215007],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05870746,"threshold_uncertainty_score":0.8251709,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03480438124735694,"score_gpt":0.2534119171452875,"score_spread":0.2186075358979306,"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."}}