{"id":"W4403197003","doi":"10.1080/03081060.2024.2411611","title":"Travel mode choice prediction: developing new techniques to prioritize variables and interpret black-box machine learning techniques","year":2024,"lang":"en","type":"article","venue":"Transportation Planning and Technology","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval; Concordia University; Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Black box; Mode choice; Mode (computer interface); Machine learning; Computer science; Engineering; Transport engineering; Artificial intelligence; Public transport; Human–computer interaction","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000129182,0.0002323666,0.0002236763,0.0007721745,0.00009233318,0.00008157217,0.0001078799,0.0002592166,0.000005936451],"category_scores_gemma":[0.00001766748,0.0002488215,0.00002296078,0.000504208,0.000067229,0.000218613,0.00001452905,0.0004227844,0.000001844552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004360009,"about_ca_system_score_gemma":0.00002325708,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005962925,"about_ca_topic_score_gemma":0.00003550199,"domain_scores_codex":[0.9989802,0.00001028323,0.0003211814,0.0003502104,0.0001056011,0.0002325107],"domain_scores_gemma":[0.9997126,0.0000440613,0.00001865003,0.0001143612,0.00002831076,0.00008194133],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006430355,0.00003989637,0.01580129,0.002085045,0.0004963398,0.0001674596,0.008269392,0.001589405,0.06960884,0.1179222,0.02654889,0.7574069],"study_design_scores_gemma":[0.000818014,0.0009037029,0.01554466,0.00545576,0.0003814281,0.0001824999,0.001474439,0.1352515,0.2704204,0.009009605,0.5586045,0.001953549],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02148627,0.001521652,0.9452024,0.001219528,0.0001396388,0.0004201131,0.0000529292,0.02866845,0.001289014],"genre_scores_gemma":[0.9410297,0.0009206179,0.05746481,0.00008844248,0.00007891695,0.00009696662,0.00009320723,0.00005231852,0.0001750664],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9195434,"threshold_uncertainty_score":0.9999964,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007807652114184692,"score_gpt":0.2425755632876937,"score_spread":0.234767911173509,"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."}}