{"id":"W4416887687","doi":"10.1016/j.trip.2025.101754","title":"Understanding travel behavior and mode choice prediction for university commuters: insights from discrete choice models and machine learning","year":2025,"lang":"en","type":"article","venue":"Transportation Research Interdisciplinary Perspectives","topic":"Urban Transport and Accessibility","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mode choice; Multinomial logistic regression; Discrete choice; Mode (computer interface); Travel behavior; Choice set; Choice modelling; Public transport; Mixed logit","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"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":[0.002811002,0.0005246406,0.0005178163,0.001334761,0.000314248,0.001408492,0.0008592616,0.0007386506,0.002133204],"category_scores_gemma":[0.01245834,0.0002661313,0.001003089,0.001608623,0.0005268506,0.001709101,0.0006925275,0.001250722,0.0002886868],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001574486,"about_ca_system_score_gemma":0.001416902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.038008,"about_ca_topic_score_gemma":0.03320402,"domain_scores_codex":[0.9990423,0.0005905194,0.000039456,0.0001616632,0.00009194826,0.00007408549],"domain_scores_gemma":[0.9880599,0.01016117,0.0007359143,0.0003395629,0.0004239363,0.0002795609],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000215184,0.0009506565,0.5557756,0.0003176463,0.0002759138,0.0001668325,0.001640679,0.3058444,0.0006365799,0.03833311,0.002316079,0.09352728],"study_design_scores_gemma":[0.00001066693,0.00008620249,0.05047194,0.0000606516,0.00003492451,0.00003105033,0.0007674671,0.9250605,0.0001977015,0.02187873,0.001372774,0.00002738106],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8310145,0.0007735242,0.1600003,0.002317203,0.00003481823,0.000101428,0.001180315,0.0001214513,0.004456566],"genre_scores_gemma":[0.9761294,0.0003789664,0.02196553,0.00008814842,0.0000190614,0.00007837519,0.0005426523,0.00001031021,0.000787533],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.038008,"threshold_uncertainty_score":0.07557356,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1577888419600679,"score_gpt":0.4173125163805816,"score_spread":0.2595236744205137,"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."}}