{"id":"W3203707054","doi":"10.1177/03611981211044462","title":"Modeling Freight Vehicle Type Choice using Machine Learning and Discrete Choice Methods","year":2021,"lang":"en","type":"article","venue":"Transportation Research Record Journal of the Transportation Research Board","topic":"Urban and Freight Transport Logistics","field":"Engineering","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Multinomial logistic regression; Discrete choice; Truck; Trailer; Random forest; Variable (mathematics); Mixed logit; Computer science; Variables; Econometrics; Operations research; Logistic regression; Transport engineering; Mathematics; Engineering; Artificial intelligence; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.005326975,0.0007639599,0.001016186,0.001703378,0.0004422832,0.001152885,0.001341678,0.001299064,0.002985945],"category_scores_gemma":[0.009034057,0.0005996421,0.001381395,0.001505134,0.0005736519,0.001244839,0.0005394187,0.001319833,0.0003356306],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001512242,"about_ca_system_score_gemma":0.001181665,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02232946,"about_ca_topic_score_gemma":0.01715381,"domain_scores_codex":[0.9972378,0.00200972,0.00008803361,0.0002421385,0.0002011784,0.0002211409],"domain_scores_gemma":[0.987531,0.01131117,0.0005404995,0.0001413186,0.0003292715,0.0001467689],"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":[0.0001255058,0.0002679641,0.009294823,0.00004210228,0.00009498968,0.00005167323,0.00005626096,0.9680798,0.0001439192,0.004554201,0.0003325789,0.01695614],"study_design_scores_gemma":[0.000006256586,0.00001372176,0.0004700033,0.000002660766,0.000003327005,0.000003051989,0.000007723678,0.9981188,0.0000267816,0.001290416,0.00005387297,0.000003447464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4468923,0.0004739255,0.5485433,0.0005974172,0.00008226234,0.0003100478,0.0007491079,0.0003067438,0.002044831],"genre_scores_gemma":[0.8728356,0.0002695817,0.1233281,0.00009011367,0.00005896962,0.000452758,0.0005805243,0.00001994638,0.002364432],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02232946,"threshold_uncertainty_score":0.04439896,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1599798507920372,"score_gpt":0.4074086065065915,"score_spread":0.2474287557145543,"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."}}