{"id":"W4399893068","doi":"10.20944/preprints202406.1251.v1","title":"Predicting Crime Categories in Montreal: A Comparative Analysis of Machine Learning Algorithms","year":2024,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Crime Patterns and Interventions","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec en Outaouais","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Algorithm","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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":[0.004781038,0.001435408,0.0008768936,0.005858214,0.0006755846,0.001711712,0.001126845,0.0008300751,0.001052615],"category_scores_gemma":[0.01107324,0.0002521658,0.001222353,0.00480397,0.00047727,0.001011068,0.0007561903,0.0008895879,0.0004120344],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004710388,"about_ca_system_score_gemma":0.00329902,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.4702973,"about_ca_topic_score_gemma":0.4251005,"domain_scores_codex":[0.9976783,0.0006844016,0.000154946,0.0004051579,0.0007878157,0.0002893663],"domain_scores_gemma":[0.9945322,0.002950302,0.0003211954,0.0003711471,0.001590956,0.0002341547],"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":[0.001154947,0.0005262144,0.3595238,0.0006776631,0.001660107,0.0003125067,0.0004557247,0.3005179,0.001362021,0.003112253,0.02596975,0.3047271],"study_design_scores_gemma":[0.00005546798,0.0004059233,0.2268383,0.0001583234,0.0004277101,0.00008362502,0.0007589808,0.7583348,0.001874774,0.001201408,0.009764908,0.00009583669],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9317488,0.01278436,0.02840696,0.002126231,0.0003421751,0.0002969411,0.008578287,0.002143607,0.01357259],"genre_scores_gemma":[0.9586823,0.002560642,0.02399896,0.0001857546,0.00008587853,0.00008566601,0.0121264,0.0001367747,0.002137637],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5297027,"threshold_uncertainty_score":0.9351197,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1870221987397313,"score_gpt":0.4414866150432157,"score_spread":0.2544644163034844,"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."}}