{"id":"W4411133328","doi":"10.1177/10591478251351737","title":"Deep Reinforcement Learning for Online Assortment Customization: A Data-Driven Approach","year":2025,"lang":"en","type":"article","venue":"Production and Operations Management","topic":"Supply Chain and Inventory Management","field":"Business, Management and Accounting","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Natural Science Foundation of China","keywords":"Personalization; Reinforcement learning; Computer science; Reinforcement; Artificial intelligence; World Wide Web; Psychology","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":[0.001538553,0.001079507,0.001395324,0.0006671361,0.0003536964,0.0008613548,0.002088425,0.00132244,0.00254777],"category_scores_gemma":[0.003581468,0.0008874612,0.0006355624,0.0007314267,0.0007130427,0.00144481,0.001019051,0.002335016,0.0003596569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00170458,"about_ca_system_score_gemma":0.002029026,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01172936,"about_ca_topic_score_gemma":0.01219161,"domain_scores_codex":[0.9994835,0.0001473435,0.00002484468,0.0001391945,0.000101598,0.0001034469],"domain_scores_gemma":[0.9980026,0.001252964,0.0002120403,0.0001184385,0.0002606959,0.0001533858],"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":[0.0000398507,0.00006299854,0.0006942845,0.00002550674,0.00001755619,0.00004390506,0.00001630292,0.9788098,0.000411646,0.00174836,0.0005846643,0.01754521],"study_design_scores_gemma":[0.000002033093,0.000003405131,0.00002555095,0.000001139953,0.000001050276,0.000002057778,0.000001266582,0.9991906,0.0000666078,0.0006572425,0.00004795695,0.000001001934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05776781,0.0005164826,0.9370622,0.0006563152,0.00006018585,0.00009957485,0.000208897,0.001211171,0.002417333],"genre_scores_gemma":[0.8828514,0.0002153777,0.1133061,0.000267599,0.00005641321,0.0001723597,0.0004012577,0.0001382737,0.00259124],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01172936,"threshold_uncertainty_score":0.02332217,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03465199583859435,"score_gpt":0.2654748485403812,"score_spread":0.2308228527017869,"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."}}