{"id":"W4410539009","doi":"10.1016/j.rtbm.2025.101408","title":"Airfare prediction: Leveraging market data for better decision-making","year":2025,"lang":"en","type":"article","venue":"Research in Transportation Business & Management","topic":"Aviation Industry Analysis and Trends","field":"Economics, Econometrics and Finance","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Big data; Business; Artificial intelligence; Machine learning; Data mining","routes":{"ca_aff":true,"ca_fund":false,"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":[],"consensus_categories":[],"category_scores_codex":[0.002872633,0.0001073761,0.0002223988,0.001191285,0.0002045471,0.0001268812,0.0004665775,0.00007437127,0.0005154599],"category_scores_gemma":[0.0000699492,0.0001277066,0.00004870048,0.002101728,0.00003497511,0.0005766742,0.00004846431,0.0001700571,0.00002072665],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001402745,"about_ca_system_score_gemma":0.00002257784,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007197409,"about_ca_topic_score_gemma":0.0001869261,"domain_scores_codex":[0.9981542,0.00002010323,0.0007474418,0.0006082751,0.0001409306,0.0003290492],"domain_scores_gemma":[0.9988536,0.0002235296,0.0001197527,0.0006219287,0.0001504821,0.00003067171],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002595513,0.0003362347,0.4875606,0.0008612046,0.0003795014,0.00005678767,0.0002034686,0.008591637,6.90022e-7,0.167951,0.04173416,0.2920651],"study_design_scores_gemma":[0.0006231152,0.000003492204,0.8422408,0.0002892404,0.00001527864,8.231557e-8,0.0002165482,0.008432955,7.430031e-7,0.03456607,0.1135149,0.00009677916],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0336444,0.001228043,0.9050061,0.01066745,0.0007877801,0.001228583,0.001429852,0.00007111279,0.04593665],"genre_scores_gemma":[0.9929357,0.0002763832,0.004134052,0.0001143888,0.00007327533,0.0001172223,0.000763932,0.0000136521,0.001571392],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9592913,"threshold_uncertainty_score":0.5643924,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1354570561351908,"score_gpt":0.3655750451827587,"score_spread":0.2301179890475679,"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."}}