{"id":"W1984758736","doi":"10.3141/1807-12","title":"Nested Logit Models and Artificial Neural Networks for Predicting Household Automobile Choices: Comparison of Performance","year":2002,"lang":"en","type":"article","venue":"Transportation Research Record Journal of the Transportation Research Board","topic":"Transportation Planning and Optimization","field":"Social Sciences","cited_by":73,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; McMaster University","funders":"","keywords":"Artificial neural network; Categorical variable; Computer science; Nested logit; Artificial intelligence; Discrete choice; Machine learning; Perceptron; Logit; Logistic regression; Multilayer perceptron; Econometrics; Mathematics","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":[0.009675255,0.001780534,0.001686789,0.002098083,0.0003715129,0.001412393,0.001220371,0.001574579,0.002083984],"category_scores_gemma":[0.02096794,0.0006362522,0.001053662,0.001857956,0.0005336524,0.002768441,0.001511912,0.00122158,0.0006154883],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001683037,"about_ca_system_score_gemma":0.001534358,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02651753,"about_ca_topic_score_gemma":0.02199128,"domain_scores_codex":[0.996947,0.001945138,0.0001752592,0.0003159895,0.000440548,0.0001760468],"domain_scores_gemma":[0.9859051,0.01138466,0.0005754746,0.0005022261,0.001222823,0.0004098538],"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":[0.003488815,0.001022181,0.02590628,0.0004214519,0.0006620152,0.00009934676,0.0002179124,0.8425391,0.0005325163,0.004942938,0.002117411,0.1180499],"study_design_scores_gemma":[0.00002954452,0.000146389,0.002599421,0.00002138956,0.00003729527,0.000010814,0.00003908764,0.9950512,0.0002187385,0.001681698,0.0001451512,0.00001922409],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8428968,0.01170989,0.1307064,0.001926735,0.000559446,0.0002600155,0.001722509,0.001122426,0.009095608],"genre_scores_gemma":[0.9667451,0.002342511,0.02704776,0.00007947753,0.00009594595,0.0001357822,0.0008862116,0.00004034564,0.002626746],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02651753,"threshold_uncertainty_score":0.05272633,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2421675420582257,"score_gpt":0.4078085481676971,"score_spread":0.1656410061094715,"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."}}