{"id":"W4400584404","doi":"10.2139/ssrn.4890466","title":"Robust Stock Index Return Predictions Using Deep Learning *","year":2024,"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":"Kellogg's (Canada)","funders":"","keywords":"Index (typography); Econometrics; Stock (firearms); Stock market index; Artificial intelligence; Financial economics; Computer science; Economics; Stock market; Engineering; Geography; World Wide Web","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":[0.03879683,0.0006707849,0.0009386495,0.001853227,0.001064412,0.001788597,0.002390511,0.0007947261,0.0003589208],"category_scores_gemma":[0.01297151,0.0005527942,0.0008732368,0.001648268,0.0001779865,0.000261003,0.00260325,0.0289511,0.0000831122],"about_ca_system_candidate":true,"about_ca_system_consensus":true,"about_ca_system_score_codex":0.004325463,"about_ca_system_score_gemma":0.009493133,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001280608,"about_ca_topic_score_gemma":0.0008053702,"domain_scores_codex":[0.9870472,0.002436395,0.001902254,0.00147591,0.003180127,0.003958103],"domain_scores_gemma":[0.9941669,0.002001258,0.001539643,0.001054652,0.0009022957,0.0003353135],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002250435,0.00009273392,0.05169301,0.00005625878,0.001247945,0.00008217888,0.001303063,0.4563566,0.0001233041,0.004705876,0.001225354,0.4828886],"study_design_scores_gemma":[0.0001959374,0.0001284988,0.0005387571,0.000208117,0.0001804864,0.00204186,0.001489025,0.433394,0.000004402153,0.5595709,0.001878644,0.0003693581],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1752743,0.01097727,0.799338,0.0005415255,0.008110501,0.0004308342,0.00001068142,0.0002793007,0.005037536],"genre_scores_gemma":[0.9535114,0.001173824,0.01756988,0.00004677705,0.003825325,0.00002970998,0.000008328525,0.0002282806,0.02360652],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7817681,"threshold_uncertainty_score":0.9996924,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1179324572208644,"score_gpt":0.3886197587198238,"score_spread":0.2706873014989594,"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."}}