{"id":"W4306317496","doi":"10.1145/3511808.3557436","title":"Risk-Aware Bid Optimization for Online Display Advertisement","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"HEC Montréal","funders":"Mitacs","keywords":"Bidding; Real-time bidding; Profit (economics); Budget constraint; Display advertising; Computer science; Common value auction; Lagrangian relaxation; Online advertising; Operations research; Mathematical optimization; Microeconomics; The Internet; Economics; Engineering; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001903587,0.0002154894,0.0002297181,0.0008174571,0.0005133985,0.0003617519,0.003597939,0.00004179428,0.001485479],"category_scores_gemma":[0.002421511,0.000161069,0.0001854288,0.0008633451,0.00009546256,0.001273205,0.002631045,0.0002968893,0.0001589295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000462229,"about_ca_system_score_gemma":0.00005297356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005310049,"about_ca_topic_score_gemma":0.00001177762,"domain_scores_codex":[0.9957556,0.00003927346,0.00105229,0.0003552727,0.002514256,0.0002833547],"domain_scores_gemma":[0.9953591,0.0002557409,0.001135747,0.0004618738,0.002709405,0.00007811009],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00140195,0.001303563,0.002829904,0.0002960603,0.0004560816,2.588379e-7,0.006235208,0.3016038,0.00009126233,0.2002704,0.104456,0.3810555],"study_design_scores_gemma":[0.001914558,0.0001851665,0.002658697,0.0001097743,0.00004307778,0.000003130858,0.006556103,0.4422413,0.0002427285,0.0261995,0.5194927,0.0003531488],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06299778,0.00007391806,0.7413202,0.01658371,0.007566815,0.008273478,0.004182011,0.0003134009,0.1586887],"genre_scores_gemma":[0.9314655,0.000210449,0.04218888,0.0003752113,0.0002298635,0.001454839,0.0006548929,0.00003599803,0.02338436],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8684677,"threshold_uncertainty_score":0.9994273,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1311048228999324,"score_gpt":0.4138531594511498,"score_spread":0.2827483365512173,"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."}}