{"id":"W4406226656","doi":"10.1016/j.trpro.2024.12.158","title":"Disaggregate travel demand analysis using big data sources: unsupervised learning methods for data-driven trip purpose estimation","year":2025,"lang":"en","type":"article","venue":"Transportation research procedia","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institut de Valorisation des Données","keywords":"Computer science; Big data; Estimation; Unsupervised learning; Trip generation; Data science; Transport engineering; Data mining; Machine learning; Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0109775,0.0001626394,0.0004072253,0.0009721636,0.001871869,0.0003051535,0.001319714,0.0001686571,0.0001110965],"category_scores_gemma":[0.002989265,0.0001665365,0.0001372955,0.004655605,0.0004477536,0.0007475967,0.00003936329,0.0003794208,0.000005279317],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001338918,"about_ca_system_score_gemma":0.001317986,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.008510296,"about_ca_topic_score_gemma":0.04894281,"domain_scores_codex":[0.9959741,0.001172068,0.0006278889,0.0009091598,0.0007832681,0.0005335179],"domain_scores_gemma":[0.9964148,0.001515969,0.0001629576,0.0009002159,0.0008202368,0.0001858234],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003314497,0.0005373968,0.06704219,0.001265739,0.002302615,0.000004141988,0.06024453,0.1828331,0.001219054,0.007028446,0.0003440459,0.6768473],"study_design_scores_gemma":[0.0005808112,0.00002898794,0.01735716,0.00007179865,0.001398227,1.936143e-8,0.01051611,0.9635547,0.0001489916,0.001719597,0.004428507,0.0001951291],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07996205,0.0003437414,0.9173313,0.0007052512,0.00005609516,0.001133604,0.0002328458,0.0001089979,0.0001261386],"genre_scores_gemma":[0.9419523,0.0002279304,0.04915992,0.00004720342,0.000157589,0.0001675227,0.007512226,0.00002418236,0.0007511029],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8681713,"threshold_uncertainty_score":0.9994276,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3244072314668524,"score_gpt":0.5307941429974004,"score_spread":0.2063869115305479,"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."}}