{"id":"W4206768619","doi":"10.1016/j.ejor.2021.12.047","title":"An integrated data-driven method using deep learning for a newsvendor problem with unobservable features","year":2022,"lang":"en","type":"article","venue":"European Journal of Operational Research","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":45,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Newsvendor model; Unobservable; Computer science; Artificial intelligence; Mathematical optimization; Econometrics; Supply chain; Economics; Mathematics; Business","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":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.02915474,0.0001002011,0.0001988711,0.0004326137,0.002274906,0.0006087092,0.002333351,0.00001302998,0.0003428807],"category_scores_gemma":[0.002365703,0.00006645395,0.00005562231,0.001188605,0.00009105891,0.0006498495,0.0007079542,0.0009712038,0.000005918607],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001105126,"about_ca_system_score_gemma":0.0005163157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003658604,"about_ca_topic_score_gemma":0.00001596229,"domain_scores_codex":[0.9927956,0.003670618,0.0006317426,0.0003919574,0.002233691,0.0002763493],"domain_scores_gemma":[0.995121,0.001350832,0.0003236487,0.0005045483,0.00254509,0.0001548616],"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":[0.0005814079,0.0002254408,0.0009001211,0.000005297687,0.00004852369,0.00008057903,0.001021214,0.904069,0.008564101,0.005987062,0.01901195,0.05950527],"study_design_scores_gemma":[0.0006371342,0.002328804,0.001177112,0.00003262221,0.00001378638,0.0005983496,0.002247135,0.684305,0.0002664432,0.001810478,0.3064415,0.0001417117],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06991995,0.0001027501,0.9260458,0.001915945,0.0000465007,0.0005503193,0.00007161377,0.00002608175,0.001320989],"genre_scores_gemma":[0.3628153,0.000003687581,0.6358042,0.00006553213,0.0001618032,0.0000152798,0.00006202405,0.00002801466,0.001044127],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2928953,"threshold_uncertainty_score":0.9996895,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4883560514829957,"score_gpt":0.5348500805684767,"score_spread":0.04649402908548106,"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."}}