{"id":"W4406103854","doi":"10.2139/ssrn.5085103","title":"Revisiting the International Conditional Capital Asset Pricing Model: A Recurrent Neural Network Approach","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Capital asset pricing model; Sharpe ratio; Econometrics; Economics; Covariance; Portfolio; Financial economics; Benchmark (surveying); Portfolio optimization; Equity (law); Consumption-based capital asset pricing model; Mathematics; 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":["metaresearch","metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04510305,0.000566955,0.0007718104,0.0005314783,0.0009973485,0.001463069,0.004681613,0.0003308667,0.00008902098],"category_scores_gemma":[0.008883151,0.0003848087,0.0008199029,0.0007416436,0.0001630202,0.000299417,0.002466395,0.01119789,0.00001342413],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002294437,"about_ca_system_score_gemma":0.007247203,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000230665,"about_ca_topic_score_gemma":0.00004248137,"domain_scores_codex":[0.9886629,0.001882043,0.001897524,0.001179871,0.003488429,0.002889228],"domain_scores_gemma":[0.992137,0.003704449,0.002010445,0.0009179903,0.001076877,0.0001532249],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001176596,0.00003971466,0.00265579,0.00001573031,0.0004737636,0.000004940739,0.0003687809,0.6664619,0.000003749423,0.1069498,0.004835893,0.2180723],"study_design_scores_gemma":[0.0002152708,0.00002301801,0.0004871532,0.0001339927,0.00006646179,0.0004399841,0.0005736783,0.4737003,7.34929e-7,0.5234119,0.0007166965,0.0002308145],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0400932,0.005022386,0.9245377,0.006573335,0.005603835,0.000715307,0.0001235502,0.0001032399,0.01722741],"genre_scores_gemma":[0.9370309,0.001387187,0.04087455,0.0008168009,0.01163636,0.0001381385,0.0002217066,0.00008439736,0.00780995],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8969377,"threshold_uncertainty_score":0.9998604,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08199227540511068,"score_gpt":0.3892514271705148,"score_spread":0.3072591517654041,"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."}}