{"id":"W2562377713","doi":"10.1109/uemcon.2016.7777919","title":"A new algorithm for money laundering detection based on structural similarity","year":2016,"lang":"en","type":"article","venue":"","topic":"Crime, Illicit Activities, and Governance","field":"Social Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Money laundering; Computer science; Task (project management); Process (computing); Cluster analysis; Set (abstract data type); Similarity (geometry); Data mining; Data set; Financial transaction; Reduction (mathematics); Algorithm; Finance; Business; Machine learning; Artificial intelligence; Database; Database transaction; Image (mathematics); Economics; Mathematics","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":[0.0001522431,0.00007841581,0.00008865369,0.00002682404,0.0003329653,0.00004880096,0.00009659011,0.00006954003,0.0002163002],"category_scores_gemma":[0.0001446697,0.00005583626,0.00006550663,0.0000730865,0.00005014378,0.0002243342,0.000008862566,0.00004258583,0.00000628809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001809137,"about_ca_system_score_gemma":0.0001164927,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009991398,"about_ca_topic_score_gemma":0.01449846,"domain_scores_codex":[0.9992461,0.00002999312,0.00008204702,0.0001768488,0.0002269961,0.0002379941],"domain_scores_gemma":[0.9994609,0.0002623329,0.00004823398,0.000101465,0.00003459352,0.00009247637],"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":[0.00003344321,0.000009294801,0.0001463258,0.000003319002,0.000006042904,4.254103e-7,0.001205003,0.00001072572,0.001226545,0.003015823,0.001480008,0.9928631],"study_design_scores_gemma":[0.00810029,0.001119846,0.02502725,0.0002068356,0.00008489584,0.000002365898,0.008958686,0.0847402,0.1925427,0.07130846,0.6058271,0.002081396],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04706311,0.00001485598,0.9366783,0.0018118,0.0007986817,0.0003325422,0.00002794644,0.0001773058,0.01309542],"genre_scores_gemma":[0.9841465,0.000007178476,0.006870424,0.0002981138,0.0005346222,0.00001055749,5.297308e-7,0.000008793315,0.008123222],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9907817,"threshold_uncertainty_score":0.9966012,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02745587934902836,"score_gpt":0.2978497972329219,"score_spread":0.2703939178838936,"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."}}