{"id":"W4367676883","doi":"10.1287/inte.2023.1164","title":"Bombardier Aftermarket Demand Forecast with Machine Learning","year":2023,"lang":"en","type":"article","venue":"INFORMS Journal on Applied Analytics","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Group for Research in Decision Analysis; HEC Montréal; Mila - Quebec Artificial Intelligence Institute; Bombardier (Canada)","funders":"","keywords":"Spare part; Demand forecasting; Computer science; Analytics; On demand; Process (computing); Economic shortage; Operations research; Data mining; Engineering; Operations management","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002959779,0.0002219705,0.0003397197,0.0006731346,0.0005615178,0.000646637,0.0006785368,0.00009281396,0.0002525481],"category_scores_gemma":[0.0003184628,0.0001265537,0.0001526201,0.001709962,0.0001122665,0.000218444,0.0001447228,0.0007327832,0.0007838725],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006108126,"about_ca_system_score_gemma":0.00007209552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002336211,"about_ca_topic_score_gemma":0.000008895786,"domain_scores_codex":[0.9970991,0.00002381639,0.0007744792,0.0002683148,0.001397193,0.0004370853],"domain_scores_gemma":[0.9980662,0.0004542444,0.0005376745,0.000439095,0.0002377327,0.0002650821],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001121887,0.0001788333,0.04083661,0.00002998946,0.0003848406,0.0003263778,0.001284046,0.1370855,0.0003162569,0.05942119,0.1879048,0.5711097],"study_design_scores_gemma":[0.001213261,0.0005818519,0.008751144,0.00008777774,0.00006685783,0.0004313312,0.0006374107,0.1987083,0.0004986823,0.07195029,0.716444,0.0006291862],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4824075,0.00005169157,0.1573427,0.003963057,0.0003207618,0.000909635,0.00007966144,0.001061148,0.3538639],"genre_scores_gemma":[0.990665,0.0000835316,0.003610732,0.00046256,0.0001601943,0.00002005469,0.00001334255,0.00003010798,0.004954461],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5704805,"threshold_uncertainty_score":0.9999942,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07595793931106345,"score_gpt":0.3423356359571896,"score_spread":0.2663776966461261,"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."}}