{"id":"W4399171888","doi":"10.1287/msom.2022.0453","title":"Pooling and Boosting for Demand Prediction in Retail: A Transfer Learning Approach","year":2024,"lang":"en","type":"article","venue":"Manufacturing & Service Operations Management","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Pooling; Computer science; Exploit; Boosting (machine learning); Gradient boosting; Leverage (statistics); Scalability; Econometrics; Machine learning; Artificial intelligence; Random forest; Economics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003881976,0.001424346,0.002216596,0.001184539,0.0005034676,0.001012034,0.002283242,0.001475771,0.002252199],"category_scores_gemma":[0.007175034,0.000564865,0.001472994,0.00145147,0.0009125294,0.002549201,0.001587158,0.001694703,0.0007891388],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008447998,"about_ca_system_score_gemma":0.0009325831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003960983,"about_ca_topic_score_gemma":0.00232146,"domain_scores_codex":[0.9989837,0.0003566418,0.00005307393,0.0002664721,0.0001984648,0.0001415345],"domain_scores_gemma":[0.9973598,0.00150936,0.0001849218,0.000403593,0.0004209208,0.0001214335],"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":[0.0003202079,0.0003199692,0.005270317,0.0001184418,0.0002158489,0.000168882,0.0001296603,0.7578788,0.002374978,0.006629452,0.004081573,0.2224918],"study_design_scores_gemma":[0.000007925412,0.00003142091,0.0003323054,0.000004694075,0.00001531746,0.000009715782,0.00000701086,0.9935943,0.0003644518,0.005370241,0.0002569567,0.000005641245],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0894173,0.0009917837,0.9038225,0.0008261916,0.0001117701,0.000108272,0.0002877743,0.0017305,0.002703938],"genre_scores_gemma":[0.8943256,0.0003361317,0.1011755,0.0003553395,0.0002906291,0.0001292748,0.0005420712,0.0001241937,0.002721278],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003960983,"threshold_uncertainty_score":0.0205301,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07303055777460699,"score_gpt":0.3259016177324117,"score_spread":0.2528710599578047,"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."}}