{"id":"W4283836917","doi":"10.1287/msom.2022.1128","title":"Online Personalized Assortment Optimization with High-Dimensional Customer Contextual Data","year":2022,"lang":"en","type":"article","venue":"Manufacturing & Service Operations Management","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Regret; Scalability; Set (abstract data type); Relevance (law); Optimization problem; Curse of dimensionality; Benchmark (surveying); Mathematical optimization; Data mining; Machine learning; Algorithm; Database","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":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001568908,0.0002852678,0.0003163136,0.0005340594,0.001522613,0.0005054013,0.002163188,0.00003090816,0.008370225],"category_scores_gemma":[0.00005573601,0.0002231493,0.00004487035,0.0009327478,0.00007076819,0.0009288339,0.003441792,0.0003517473,0.0002905797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003704299,"about_ca_system_score_gemma":0.00009875912,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003319202,"about_ca_topic_score_gemma":0.0004867163,"domain_scores_codex":[0.9937331,0.0003632129,0.0006264572,0.001204642,0.003610088,0.0004624776],"domain_scores_gemma":[0.9972529,0.0002145804,0.0001523279,0.001896887,0.000331663,0.0001516222],"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":[0.00011033,0.0004390093,0.00001599058,0.000008930356,0.000121552,0.00006830971,0.0001883105,0.9892077,0.000007014086,0.0003584339,0.003656409,0.005817986],"study_design_scores_gemma":[0.002883332,0.0001808431,0.002261754,0.00001630463,0.00008631307,0.00003174496,0.004946192,0.8627703,0.0001878181,0.0001891959,0.1259438,0.0005024041],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3030987,0.0002360733,0.6386277,0.0436153,0.001544561,0.005852329,0.003486945,0.0005579741,0.00298038],"genre_scores_gemma":[0.7909303,0.00003071996,0.1618896,0.005631957,0.0003102142,0.0004486701,0.007891469,0.0001097081,0.03275733],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4878316,"threshold_uncertainty_score":0.9997773,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09720745596710767,"score_gpt":0.3677456167158194,"score_spread":0.2705381607487117,"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."}}