{"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":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.001333575,0.0001465083,0.0002165193,0.0001445149,0.001481929,0.0004883456,0.0002561439,0.00007678136,0.0001367475],"category_scores_gemma":[0.00009422333,0.0001480742,0.00006215994,0.0003334475,0.00008714353,0.001081294,0.00006441162,0.0006014886,0.000001939339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002984196,"about_ca_system_score_gemma":0.0002822709,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002177076,"about_ca_topic_score_gemma":0.00447711,"domain_scores_codex":[0.9980151,0.0003953777,0.0002917584,0.0003347874,0.0006352343,0.0003277283],"domain_scores_gemma":[0.9991047,0.0001700548,0.0002051215,0.0001864101,0.0001019346,0.0002317293],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000633518,0.0006553728,0.06977507,0.0004263638,0.000500207,0.001643284,0.2066837,0.001544812,0.4001951,0.009221816,0.009159075,0.2995616],"study_design_scores_gemma":[0.003240581,0.0003629168,0.0686235,0.007232514,0.0006447622,0.002687476,0.1875191,0.01197774,0.1144968,0.01500899,0.584455,0.003750718],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.946336,0.00152127,0.03776389,0.002376093,0.001184353,0.0002150359,0.00005085891,0.0001614192,0.01039107],"genre_scores_gemma":[0.9910213,0.001354618,0.003357893,0.0001141348,0.0008416188,0.000001976313,0.00001494703,0.00002362757,0.003269935],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5752959,"threshold_uncertainty_score":0.999818,"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."}}