{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004900676,0.0002128772,0.0001856726,0.000503936,0.0007390296,0.0004906401,0.0003079885,0.000039612,0.0000935546],"category_scores_gemma":[0.0001159659,0.0002062837,0.00004461101,0.0005503169,0.00004786413,0.001073045,0.0006233783,0.00009865715,0.00002562683],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008581197,"about_ca_system_score_gemma":0.00001256538,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004142094,"about_ca_topic_score_gemma":0.00009885219,"domain_scores_codex":[0.9984052,0.00001758807,0.0003976093,0.0007045828,0.0002244951,0.000250587],"domain_scores_gemma":[0.9991351,0.000008640613,0.00009378168,0.0005727198,0.0001743039,0.00001540211],"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":[0.00004732328,0.0003768125,0.0004782555,0.0006819965,0.0002557061,7.573882e-7,0.00005964138,0.7842975,0.000008948642,0.1281542,0.0602036,0.02543522],"study_design_scores_gemma":[0.0004962707,0.000009230235,0.0003821276,0.00003066979,0.0001653851,2.904657e-7,0.000759939,0.5964099,0.000003344824,0.0001165271,0.4014813,0.0001451295],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002004798,0.0003656287,0.8977488,0.01411545,0.002106956,0.005182713,0.000003357041,0.0004675778,0.07800468],"genre_scores_gemma":[0.8322596,0.000842451,0.04635172,0.009361982,0.002770225,0.002033097,0.007318248,0.00007888051,0.09898381],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8513971,"threshold_uncertainty_score":0.8412005,"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."}}