{"id":"W3209120126","doi":"10.17975/sfj-2021-006","title":"Using real-world transaction data to identify money laundering: Leveraging traditional regression and machine learning techniques","year":2021,"lang":"en","type":"article","venue":"STEM Fellowship Journal","topic":"Crime, Illicit Activities, and Governance","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Ontario; University of Toronto","funders":"","keywords":"Multinomial logistic regression; Logistic regression; Lasso (programming language); Machine learning; Computer science; Artificial intelligence; Random forest; Outcome (game theory); Transaction data; Database transaction; Binary classification; Money laundering; Predictive modelling; Regression; Econometrics; Support vector machine; Statistics; Business; Finance; Economics; Mathematics; Database","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004718859,0.001632317,0.0009405464,0.00534961,0.0005119484,0.001937803,0.00135877,0.001273033,0.000828016],"category_scores_gemma":[0.01604847,0.0003669216,0.0008270312,0.003649446,0.0005339842,0.001992595,0.001172628,0.001793982,0.001197784],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009938149,"about_ca_system_score_gemma":0.001254128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02998979,"about_ca_topic_score_gemma":0.04068851,"domain_scores_codex":[0.9975809,0.001020088,0.0002004813,0.0005339682,0.0004831147,0.0001814398],"domain_scores_gemma":[0.9892047,0.005988199,0.001622921,0.001073148,0.001801252,0.000309704],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005466678,0.001460327,0.4737262,0.0005419487,0.0007033788,0.0008785964,0.0004985376,0.2323886,0.002818626,0.002178518,0.01945248,0.2648061],"study_design_scores_gemma":[0.0000256683,0.0001381826,0.05876365,0.0001059665,0.00006319959,0.0001791695,0.0004348639,0.9312617,0.001716026,0.002543886,0.004706899,0.00006086314],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8581063,0.003488688,0.1164422,0.003392408,0.0002882154,0.0002980195,0.009593499,0.003233162,0.005157505],"genre_scores_gemma":[0.9193597,0.0006721289,0.06512748,0.0002671579,0.000184242,0.0001160217,0.01212749,0.0001199219,0.002025912],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02998979,"threshold_uncertainty_score":0.05963045,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3162495610043552,"score_gpt":0.4021594169687887,"score_spread":0.08590985596443351,"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."}}