{"id":"W4410728601","doi":"10.1007/s41060-025-00799-8","title":"A data-driven approach for predicting crime occurrence using machine learning models","year":2025,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Crime Patterns and Interventions","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence","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":[0.002903221,0.00006234704,0.0001218218,0.0003179208,0.0004871565,0.000455816,0.002616234,0.0000246188,0.00001625473],"category_scores_gemma":[0.001298008,0.00005508192,0.00003761023,0.0003316448,0.0003913524,0.003258864,0.0007925255,0.0001626505,1.999495e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009012336,"about_ca_system_score_gemma":0.0006469128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004197486,"about_ca_topic_score_gemma":0.0001125207,"domain_scores_codex":[0.9984983,0.00003793562,0.0003502526,0.0002489559,0.0006985058,0.000166055],"domain_scores_gemma":[0.9982739,0.000111247,0.000278743,0.0002327826,0.001025728,0.0000775763],"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":[0.0004727865,0.002913767,0.3160058,0.0004083999,0.002828607,0.00008194404,0.0170816,0.1416015,0.006759717,0.2008257,0.04182116,0.269199],"study_design_scores_gemma":[0.0001966973,0.00002171739,0.0001428115,0.0001028821,0.00007024498,0.000008386055,0.001757178,0.98682,0.00001416979,0.000540175,0.01026997,0.00005580455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04132342,0.0005160219,0.9500831,0.001405795,0.0008882392,0.0001470894,0.002042722,0.00001450108,0.003579054],"genre_scores_gemma":[0.9728684,0.0003036898,0.02618156,0.0001174217,0.0002624271,4.615467e-7,0.0001427345,0.000002659018,0.000120667],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.931545,"threshold_uncertainty_score":0.4861657,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3388764596217803,"score_gpt":0.4783996502889309,"score_spread":0.1395231906671506,"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."}}