{"id":"W4362676646","doi":"10.1016/j.trip.2023.100814","title":"A study on road accident prediction and contributing factors using explainable machine learning models: analysis and performance","year":2023,"lang":"en","type":"article","venue":"Transportation Research Interdisciplinary Perspectives","topic":"Traffic and Road Safety","field":"Engineering","cited_by":176,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Road accident; Random forest; Computer science; Machine learning; AdaBoost; Boosting (machine learning); Categorical variable; Gradient boosting; Artificial intelligence; Road traffic accident; Predictive modelling; Classifier (UML); Transport engineering; Road traffic; Engineering","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":[0.0007440504,0.0001743033,0.0002453234,0.0008804375,0.0008057464,0.00006626928,0.0000805926,0.0000596873,0.00001471358],"category_scores_gemma":[0.00001457411,0.0001563607,0.00005939527,0.00118796,0.00008783875,0.0004254529,0.00004602349,0.000489568,0.000002440197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001525168,"about_ca_system_score_gemma":0.00001308848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001161184,"about_ca_topic_score_gemma":0.0002648504,"domain_scores_codex":[0.9984521,0.0001080347,0.0002568665,0.0003800771,0.0003929967,0.0004098834],"domain_scores_gemma":[0.9995033,0.0001228201,0.00002953445,0.0001219515,0.0001141711,0.0001082079],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000127888,0.00005877838,0.475782,0.00003359898,0.0003219328,0.00001987086,0.09150302,0.4314408,0.00007395222,0.00005279899,0.000003114487,0.0005821806],"study_design_scores_gemma":[0.0002427621,0.000288072,0.5034382,0.0000240322,0.00005257741,4.583602e-7,0.1230151,0.3728119,0.00002815615,0.00002597829,7.915301e-7,0.00007201172],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9966297,0.0002259581,0.002068989,0.00004327489,0.00004019973,0.0003950876,0.00004087835,0.0003755057,0.000180433],"genre_scores_gemma":[0.999403,0.0003256105,0.00003246459,3.940584e-7,0.00002784569,0.0000362926,0.00007674436,0.00002711231,0.00007054542],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05862894,"threshold_uncertainty_score":0.6376203,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08359841811684365,"score_gpt":0.354591971049676,"score_spread":0.2709935529328323,"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."}}