{"id":"W4415684890","doi":"10.1155/atr/8794166","title":"Comparative Insights Into E‐Scooter Usage Prediction Through Machine Learning and Deep Learning Techniques","year":2025,"lang":"en","type":"article","venue":"Journal of Advanced Transportation","topic":"Urban Transport and Accessibility","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Yildiz Teknik Üniversitesi","keywords":"Deep learning; Boosting (machine learning); Artificial neural network; Plan (archaeology); Gradient boosting; Mean squared error; Investment (military)","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":[0.001508545,0.0005080982,0.0004065084,0.001504097,0.0001979966,0.0008139679,0.0005127435,0.0006099615,0.001419968],"category_scores_gemma":[0.004167445,0.0001443613,0.0004745396,0.001317824,0.0002147505,0.001285036,0.0004069205,0.0006614228,0.0002334361],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006166606,"about_ca_system_score_gemma":0.0006053873,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01133764,"about_ca_topic_score_gemma":0.01706832,"domain_scores_codex":[0.9995788,0.0001346335,0.00003427254,0.00007630546,0.000123661,0.00005224818],"domain_scores_gemma":[0.9978033,0.001588256,0.0001355101,0.0001315454,0.0002849704,0.00005649886],"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":[0.0001900521,0.0003320181,0.04772851,0.0001701064,0.0001580455,0.0001345703,0.0001225238,0.7073556,0.00204259,0.003590847,0.002583401,0.2355917],"study_design_scores_gemma":[0.000003389574,0.00004844599,0.007631775,0.00001635384,0.00001378629,0.00001596237,0.00007567903,0.9899255,0.0007917677,0.0009623804,0.0005084718,0.000006380004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8947995,0.00319892,0.08882818,0.001562517,0.00007899054,0.00003157222,0.0008351243,0.000599908,0.01006525],"genre_scores_gemma":[0.9780601,0.0007210156,0.01929564,0.00006423958,0.00002251343,0.00001340628,0.0006244075,0.0000223743,0.001176261],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01133764,"threshold_uncertainty_score":0.02254331,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01296179375027307,"score_gpt":0.3249948792990516,"score_spread":0.3120330855487786,"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."}}