{"id":"W4414661800","doi":"10.1080/23249935.2025.2563182","title":"Railway booking demand forecasting for revenue management: a deep probabilistic approach","year":2025,"lang":"en","type":"article","venue":"Transportmetrica A Transport Science","topic":"Transportation Planning and Optimization","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Demand forecasting; Probabilistic logic; Revenue; Probabilistic forecasting; Economic forecasting","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","sts"],"consensus_categories":[],"category_scores_codex":[0.002736669,0.000246889,0.0003402957,0.001173231,0.002011348,0.0001085131,0.0007863696,0.0001328361,0.00002497936],"category_scores_gemma":[0.0001494713,0.0002598333,0.0001844045,0.006816451,0.0009385462,0.0006280998,0.000004902935,0.0001741329,0.000001953827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001674845,"about_ca_system_score_gemma":0.0004809777,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001898462,"about_ca_topic_score_gemma":0.0004365208,"domain_scores_codex":[0.9967432,0.00004263934,0.000637399,0.0008589528,0.0008566598,0.0008611607],"domain_scores_gemma":[0.9987569,0.0002026641,0.000174227,0.0003103177,0.0003287993,0.00022707],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0006381529,0.001101121,0.1406227,0.00260383,0.0002631964,0.000107716,0.05636266,0.1266337,0.0001998538,0.5923276,0.0003705322,0.07876896],"study_design_scores_gemma":[0.01282733,0.0004721064,0.57544,0.002148445,0.003200499,0.00001433465,0.01684247,0.09261817,0.0007793323,0.03589018,0.2552446,0.004522597],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02730229,0.0003302101,0.9025347,0.0003029278,0.0004351195,0.002180374,0.00008491604,0.0003075181,0.06652198],"genre_scores_gemma":[0.9395037,0.0001059874,0.05729732,0.0001455664,0.00005049698,0.0002736008,0.0000978191,0.00002003197,0.002505481],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9122014,"threshold_uncertainty_score":0.9999854,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03064569934036214,"score_gpt":0.2920402080063593,"score_spread":0.2613945086659972,"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."}}