{"id":"W2136483635","doi":"10.1002/atr.1306","title":"A new logit‐artificial neural network ensemble for mode choice modeling: a case study for border transport","year":2015,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Transportation Planning and Optimization","field":"Social Sciences","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Multinomial logistic regression; Mode choice; Artificial neural network; Mode (computer interface); Computer science; Metropolitan area; Logit; Logistic regression; Discrete choice; Artificial intelligence; Ensemble learning; Econometrics; Machine learning; Operations research; Public transport; Transport engineering; Engineering; Mathematics; Geography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001734853,0.0005151397,0.0005677738,0.000681461,0.000786572,0.0007167721,0.0008378936,0.001057818,0.001768316],"category_scores_gemma":[0.002226194,0.0002713279,0.0008757643,0.0008178942,0.0002892207,0.0008837437,0.0008088216,0.001056448,0.0001652256],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001278475,"about_ca_system_score_gemma":0.0007138049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03436265,"about_ca_topic_score_gemma":0.0284231,"domain_scores_codex":[0.9996005,0.0002148075,0.0000172634,0.00005607618,0.00005696355,0.00005445648],"domain_scores_gemma":[0.9988976,0.0006492023,0.00005117467,0.0001103702,0.0002148485,0.00007685012],"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":[0.00019996,0.0004725049,0.02484885,0.00004456237,0.00008438873,0.0009174671,0.0001544487,0.9432597,0.0008857516,0.002093149,0.0009286506,0.02611066],"study_design_scores_gemma":[0.000006208575,0.00006915277,0.002454176,0.000003212336,0.00001374519,0.00003662967,0.00008711687,0.9962676,0.0003313947,0.0004554509,0.0002674714,0.000007783866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9623475,0.0001238646,0.03455164,0.0002839842,0.00002381559,0.00006398534,0.000248723,0.0001039774,0.002252558],"genre_scores_gemma":[0.9825395,0.00007995434,0.01565354,0.00001417998,0.000007489517,0.0000427408,0.0001801555,0.00001066412,0.001471667],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03436265,"threshold_uncertainty_score":0.06832528,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07244231297133959,"score_gpt":0.3850144158304051,"score_spread":0.3125721028590655,"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."}}