{"id":"W4385988930","doi":"10.1016/j.jedc.2023.104725","title":"Machine learning goes global: Cross-sectional return predictability in international stock markets","year":2023,"lang":"en","type":"article","venue":"Journal of Economic Dynamics and Control","topic":"Financial Markets and Investment Strategies","field":"Economics, Econometrics and Finance","cited_by":44,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Narodowym Centrum Nauki; Narodowe Centrum Nauki","keywords":"Predictability; Economics; Robustness (evolution); Econometrics; Stock (firearms); Limiting; Arbitrage; Financial economics; Computer science; Mathematics; Engineering; Statistics","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":[0.001580224,0.0001367024,0.000398666,0.0002351884,0.000075945,0.0001924878,0.0002137588,0.0001020099,0.0001809882],"category_scores_gemma":[0.000195066,0.0001440899,0.0001400137,0.00009351289,0.00008275926,0.0004605128,0.00005254585,0.0002562426,0.00002169436],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004628479,"about_ca_system_score_gemma":0.00005644332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001714654,"about_ca_topic_score_gemma":0.0002386271,"domain_scores_codex":[0.9984417,0.00002908246,0.001028227,0.000237687,0.00004279584,0.000220536],"domain_scores_gemma":[0.9990056,0.0001013378,0.0006810054,0.0000946764,0.00004084335,0.00007654857],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001952247,0.00002868948,0.915644,0.000009937677,0.00006681099,0.000007973121,0.00002203003,0.001629575,0.000001502102,0.08164134,0.0000653042,0.0006876202],"study_design_scores_gemma":[0.001266051,0.00007367014,0.6605061,0.000008521009,0.000002474547,0.00001721696,0.0000213157,0.2924365,1.318777e-7,0.04381038,0.001767398,0.00009027665],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.985427,0.000707253,0.000419828,0.0008402064,0.001636228,0.0001142959,0.0004444924,0.00001671084,0.01039401],"genre_scores_gemma":[0.9981757,0.0008568052,0.00005279604,0.00008587836,0.0002603066,0.000005691706,0.00002054746,0.00001133345,0.0005309719],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2908069,"threshold_uncertainty_score":0.5875815,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01411212027254262,"score_gpt":0.2419340983346419,"score_spread":0.2278219780620993,"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."}}