{"id":"W4401522263","doi":"10.1080/23270012.2024.2377168","title":"Handling highly imbalanced data for classifying fatality of auto collisions using machine learning techniques","year":2024,"lang":"en","type":"article","venue":"Journal of Management Analytics","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph; Toronto Metropolitan University","funders":"","keywords":"Machine learning; Computer science; Artificial intelligence; Risk analysis (engineering); Data mining; Medicine","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":[0.002169744,0.0001573977,0.0003554191,0.0006048384,0.0001320606,0.0003189941,0.001929004,0.00006421229,0.000003877311],"category_scores_gemma":[0.0001915901,0.0001372998,0.000133442,0.0007774124,0.00005170323,0.001249123,0.0008318648,0.0002849544,8.143509e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001552407,"about_ca_system_score_gemma":0.00009646601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007109853,"about_ca_topic_score_gemma":0.000001630757,"domain_scores_codex":[0.9980083,0.00006593639,0.0008859651,0.0003326211,0.0004887424,0.0002184293],"domain_scores_gemma":[0.9978564,0.0002159399,0.0006748139,0.0009105497,0.0002792806,0.00006299149],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002450291,0.0009656135,0.005899534,0.006103319,0.003852649,0.0005119792,0.001206925,0.008872193,0.1239242,0.5355315,0.02463197,0.2882551],"study_design_scores_gemma":[0.0001857219,0.0001028862,0.0001458519,0.0005608661,0.000189979,0.00001772298,0.00005143878,0.9192517,0.01474377,0.00210905,0.06248531,0.0001556552],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007105991,0.0005934963,0.9969203,0.0008100796,0.0002510105,0.0002455799,0.00006966694,0.000191697,0.0002075738],"genre_scores_gemma":[0.2012928,0.0005766393,0.7976859,0.00007698117,0.0001072137,0.000003706122,0.00005032765,0.00001980731,0.0001866329],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9103795,"threshold_uncertainty_score":0.5598925,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09543007381265481,"score_gpt":0.3582703427381831,"score_spread":0.2628402689255284,"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."}}