{"id":"W4384068820","doi":"10.1007/s00146-023-01718-w","title":"Identifying arbitrage opportunities in retail markets with artificial intelligence","year":2023,"lang":"en","type":"article","venue":"AI & Society","topic":"Financial Markets and Investment Strategies","field":"Economics, Econometrics and Finance","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; HEC Montréal","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Arbitrage; Profit (economics); Purchasing; Yield (engineering); Economics; Computer science; Artificial intelligence; Marketing; Business; Econometrics; Microeconomics; Financial economics","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":[],"consensus_categories":[],"category_scores_codex":[0.0007729589,0.0001553555,0.0002778581,0.0001088873,0.000141626,0.0001564562,0.0001873489,0.00009820898,0.0003822085],"category_scores_gemma":[0.00003471316,0.0001639486,0.000128096,0.0005523827,0.0001536849,0.0004438673,0.00006260203,0.0002590407,0.0002544364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000732711,"about_ca_system_score_gemma":0.0000540228,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002260538,"about_ca_topic_score_gemma":0.00009161176,"domain_scores_codex":[0.9987071,0.00001419452,0.0004825421,0.0003521657,0.00005769796,0.0003862921],"domain_scores_gemma":[0.9995026,0.00005150885,0.0001494413,0.0002218222,0.00002143826,0.00005320659],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003048849,0.00006359316,0.01503595,0.00009646248,0.00004719292,0.00004705215,0.003699187,0.0000427706,0.0000225205,0.9674674,0.008180819,0.005266538],"study_design_scores_gemma":[0.0002778322,0.0001433873,0.1910844,0.0001526759,0.00001075564,0.000005159941,0.01668184,0.01098478,0.0001991577,0.7420279,0.03758093,0.0008511198],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9113725,0.001144477,0.003092913,0.005560697,0.0006235969,0.0003684471,0.00009124263,0.0002418766,0.0775042],"genre_scores_gemma":[0.9940931,0.002230358,0.0004701079,0.001181963,0.00008638776,0.00004444629,0.00002870574,0.00002676592,0.001838196],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2254395,"threshold_uncertainty_score":0.668563,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1490211714588685,"score_gpt":0.2644756011596642,"score_spread":0.1154544297007957,"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."}}