{"id":"W2932005953","doi":"10.1177/0361198119839339","title":"Application of Machine Learning to Two Large-Sample Household Travel Surveys: A Characterization of Travel Modes","year":2019,"lang":"en","type":"article","venue":"Transportation Research Record Journal of the Transportation Research Board","topic":"Urban Transport and Accessibility","field":"Social Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"Giro (Canada); Polytechnique Montréal","funders":"","keywords":"Mode choice; TRIPS architecture; Context (archaeology); Travel behavior; Public transport; Sample (material); Random forest; Travel survey; Mode (computer interface); Transportation planning; Transport engineering; Computer science; Confusion matrix; Marketing; Business; Geography; Engineering; Machine learning","routes":{"ca_aff":true,"ca_fund":false,"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":[0.002029917,0.0004389803,0.0003040171,0.001522281,0.0002660275,0.0005008063,0.0003013331,0.0003311422,0.0004103868],"category_scores_gemma":[0.00978116,0.0001237782,0.0004246485,0.001076875,0.0002360843,0.0004416841,0.0002927707,0.0003462546,0.0001057156],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005510729,"about_ca_system_score_gemma":0.0007514671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02431218,"about_ca_topic_score_gemma":0.03944331,"domain_scores_codex":[0.9991222,0.0004762945,0.00004708962,0.0001844039,0.0001019627,0.00006807796],"domain_scores_gemma":[0.9961975,0.002585048,0.0004524945,0.0003132401,0.0003771021,0.00007473236],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003570234,0.0003354152,0.7423887,0.00009728833,0.0002322822,0.0001926102,0.0007415751,0.11169,0.004631991,0.0008165464,0.0008251391,0.1376914],"study_design_scores_gemma":[0.0000153884,0.0001943767,0.3487163,0.00002016401,0.00003144983,0.0001431788,0.0005819548,0.6468411,0.001678106,0.001115547,0.0006354001,0.00002692398],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.927338,0.00007926035,0.07135659,0.00006008519,0.000007757517,0.0001290057,0.0004589762,0.00008657508,0.000483798],"genre_scores_gemma":[0.9747006,0.00002612645,0.02463294,0.00001480824,0.000003851601,0.00004624674,0.0004471169,0.000004337142,0.0001238867],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02431218,"threshold_uncertainty_score":0.04834133,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08765186884221808,"score_gpt":0.3892511522777641,"score_spread":0.301599283435546,"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."}}