{"id":"W4391743702","doi":"10.1093/jjfinec/nbag006","title":"Multi-Factor Timing with Deep Learning","year":2024,"lang":"en","type":"article","venue":"Journal of Financial Econometrics","topic":"Financial Markets and Investment Strategies","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; University of Guelph; University of Waterloo","funders":"","keywords":"Leverage (statistics); Artificial neural network; Computer science; Artificial intelligence; Deep learning; Profitability index; Machine learning; Task (project management); Deep neural networks; Factor (programming language); Recurrent neural network; Economics; Finance","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":[0.0007395021,0.000233078,0.0006244204,0.001700702,0.000139055,0.0003555164,0.0002874677,0.0001491434,0.0004531982],"category_scores_gemma":[0.0007047302,0.0002147048,0.0002539332,0.00138624,0.00008040068,0.001059366,0.00003998625,0.0006000207,0.0002169371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002419008,"about_ca_system_score_gemma":0.00013966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002464758,"about_ca_topic_score_gemma":0.00001236734,"domain_scores_codex":[0.998134,0.00001560337,0.001090275,0.0003115848,0.00007558565,0.0003729685],"domain_scores_gemma":[0.9987509,0.0001530737,0.000703034,0.0001475773,0.00009974533,0.0001456469],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000284013,0.0006011014,0.1726631,0.0006493006,0.0005399474,0.0008491925,0.002848038,0.003530739,0.00009188514,0.6392468,0.003716964,0.1749789],"study_design_scores_gemma":[0.001551713,0.001863922,0.3682814,0.0002889829,0.00005458283,0.0001870528,0.0001656246,0.01156665,0.00008876711,0.01250698,0.6025046,0.0009397626],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8135815,0.06212632,0.08209646,0.0007339903,0.005684707,0.0003394999,0.000103833,0.0001292047,0.03520444],"genre_scores_gemma":[0.9859664,0.00219237,0.009936607,0.0001622041,0.000675989,0.000004909459,0.000003100244,0.00005105216,0.001007296],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6267399,"threshold_uncertainty_score":0.8755408,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0552835753777989,"score_gpt":0.232074640129933,"score_spread":0.1767910647521341,"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."}}