{"id":"W4390964285","doi":"10.2139/ssrn.4683557","title":"Geographically Weighted Machine Learning for Modeling Spatial Heterogeneity in Traffic Crash Frequency and Determinants in US","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Traffic and Road Safety","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Crash; Intersection (aeronautics); Spatial heterogeneity; Geography; Econometrics; Random forest; Spatial variability; Spatial ecology; Socioeconomic status; Computer science; Statistics; Cartography; Mathematics; Machine learning; Demography; Ecology; Population","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004444438,0.0006718545,0.0009636304,0.001984925,0.000523267,0.001147348,0.001600069,0.001389185,0.002214233],"category_scores_gemma":[0.01634308,0.0005808649,0.001392182,0.002514178,0.0008209309,0.001479733,0.001560799,0.001647811,0.0003686202],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009128089,"about_ca_system_score_gemma":0.0008891548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.06095072,"about_ca_topic_score_gemma":0.03806638,"domain_scores_codex":[0.9984946,0.0008506212,0.00006709446,0.0003499099,0.00005948254,0.00017814],"domain_scores_gemma":[0.9884948,0.00889158,0.001118607,0.000700831,0.0004557673,0.0003383696],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002893894,0.0002748604,0.428183,0.00004685922,0.0009624636,0.0002159538,0.0002113073,0.5386022,0.000221812,0.006579488,0.002031432,0.02238124],"study_design_scores_gemma":[0.00001634154,0.0000433102,0.03282877,0.00001374084,0.00008476758,0.00004000335,0.0002399192,0.9560345,0.00008549444,0.01027235,0.0003249572,0.00001573443],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9533423,0.00056651,0.04378436,0.0006688752,0.00004110123,0.00002777587,0.0009479316,0.0001127763,0.0005083946],"genre_scores_gemma":[0.9955626,0.0001134118,0.002983036,0.00003520597,0.00002388188,0.00002195985,0.0006174697,0.00001254764,0.0006299049],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06095072,"threshold_uncertainty_score":0.1211919,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007343225787542249,"score_gpt":0.226826419927925,"score_spread":0.2194831941403828,"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."}}