{"id":"W4413995044","doi":"10.1108/jmlc-07-2024-0114","title":"Enhancing AML compliance: a machine learning approach to suspicious activity detection through routine activity theory","year":2025,"lang":"en","type":"article","venue":"Journal of Money Laundering Control","topic":"Cybercrime and Law Enforcement Studies","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Royal Roads University","funders":"","keywords":"Compliance (psychology); Money laundering; Business; Accounting; Psychology; Finance; Social psychology","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":[0.001089492,0.0002267705,0.0005216166,0.0001756045,0.0004630456,0.0001425591,0.0004600099,0.00006813787,0.000005172376],"category_scores_gemma":[0.0003282649,0.0001963248,0.0001961546,0.0003996379,0.00002936488,0.0006830152,0.0002033256,0.00061933,0.000004928272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002403392,"about_ca_system_score_gemma":0.00007225394,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001476186,"about_ca_topic_score_gemma":0.00005882341,"domain_scores_codex":[0.9983216,0.0002684723,0.0003966823,0.0002889818,0.0003533756,0.0003708989],"domain_scores_gemma":[0.9987443,0.000359736,0.0003478267,0.0002827626,0.0001754819,0.00008987964],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002948978,0.001317571,0.002196864,0.000536431,0.002326445,0.00007139194,0.01335936,0.09278832,0.591042,0.03860226,0.0002863691,0.254524],"study_design_scores_gemma":[0.01850906,0.002777469,0.06687462,0.001826333,0.0006774189,0.0003226556,0.001571799,0.4849745,0.401118,0.008594964,0.0106946,0.002058644],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1279842,0.0003236078,0.8676416,0.0003893573,0.0003733978,0.0002140143,0.000001106122,0.00007633469,0.002996455],"genre_scores_gemma":[0.9946264,0.00002306635,0.004490867,0.0003912441,0.00013968,0.00001401366,2.325135e-7,0.00001132553,0.0003031945],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8666422,"threshold_uncertainty_score":0.8005893,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02191298859147133,"score_gpt":0.2734292352624987,"score_spread":0.2515162466710274,"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."}}