{"id":"W4382118239","doi":"10.2139/ssrn.4490516","title":"Pooling and Boosting for Demand Prediction in Retail: A Transfer Learning Approach","year":2023,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Boosting (machine learning); Pooling; Transfer of learning; Gradient boosting; Computer science; On demand; Artificial intelligence; Machine learning; Business; Commerce","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":[0.005699934,0.0009930596,0.002624905,0.001110253,0.0006607862,0.0009814318,0.002014561,0.001613984,0.001992045],"category_scores_gemma":[0.008604851,0.0006879898,0.001347668,0.001186108,0.0008528336,0.002708646,0.001529273,0.001766731,0.0004939907],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005926955,"about_ca_system_score_gemma":0.0008284599,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003478257,"about_ca_topic_score_gemma":0.001980014,"domain_scores_codex":[0.9991717,0.0003764248,0.0000518894,0.0001700313,0.0001102453,0.000119565],"domain_scores_gemma":[0.9948977,0.003854461,0.0001747004,0.0004504081,0.000475357,0.0001474334],"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":[0.0005109487,0.0004557707,0.003014926,0.0001292255,0.000206471,0.0001107363,0.0001550623,0.6750569,0.002852589,0.009850611,0.00272671,0.3049301],"study_design_scores_gemma":[0.000005486819,0.00003575236,0.000213293,0.00000299169,0.00001535329,0.000005653506,0.000005422973,0.9951985,0.000304254,0.004099888,0.0001090076,0.000004354843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1004205,0.001071838,0.8954842,0.0004517405,0.0001082201,0.00006611177,0.00008823772,0.0007681595,0.001540877],"genre_scores_gemma":[0.9229418,0.0004179667,0.07311369,0.0001211595,0.0002142705,0.00007316801,0.0001765709,0.00007641115,0.002864891],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005699934,"threshold_uncertainty_score":0.03014451,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08124982622709631,"score_gpt":0.3435170331532377,"score_spread":0.2622672069261414,"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."}}