{"id":"W4400062742","doi":"10.2139/ssrn.4870298","title":"Deep Reinforcement Learning for Online Assortment Customization: A Data-Driven Approach","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Supply Chain and Inventory Management","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Personalization; Computer science; Reinforcement; Online learning; Artificial intelligence; World Wide Web; Engineering","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":[0.001963955,0.0009433886,0.001763758,0.0007349254,0.0004255776,0.001135349,0.002445839,0.001934652,0.004375622],"category_scores_gemma":[0.006422754,0.0009865293,0.0007501491,0.0008816356,0.000846029,0.001780952,0.001319042,0.00294737,0.0005946865],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001504799,"about_ca_system_score_gemma":0.001877266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01167285,"about_ca_topic_score_gemma":0.01334791,"domain_scores_codex":[0.9994004,0.0002065669,0.00002535512,0.0001568004,0.0000932434,0.0001176494],"domain_scores_gemma":[0.9954734,0.003463462,0.0002336541,0.0002538311,0.0003934943,0.0001820915],"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":[0.0001433178,0.0001694192,0.001024739,0.00004052844,0.0000394438,0.00005550327,0.00002363052,0.9554285,0.0004997207,0.003340115,0.001453133,0.03778196],"study_design_scores_gemma":[0.000003066551,0.000004319996,0.00002997085,0.000001220936,0.000001425514,0.000001647848,0.000001096237,0.9989228,0.00006151918,0.0009428813,0.00002903265,0.00000102409],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1468035,0.0008052666,0.84444,0.001415275,0.0001244719,0.0001350293,0.0005341826,0.002157419,0.003584738],"genre_scores_gemma":[0.9331252,0.0001399411,0.06204635,0.000241204,0.00007312735,0.0001079835,0.0004676343,0.0001447186,0.003653933],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01167285,"threshold_uncertainty_score":0.02320981,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03420030727734476,"score_gpt":0.2653606851813817,"score_spread":0.2311603779040369,"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."}}