{"id":"W3094918329","doi":"10.3390/jrfm13110265","title":"Neural Network Models for Empirical Finance","year":2020,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Economic and Social Research Council","keywords":"Computer science; Machine learning; Artificial intelligence; Overfitting; Model selection; Artificial neural network; Leverage (statistics); Deep learning; Hyperparameter; Dropout (neural networks); Context (archaeology); Regularization (linguistics)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003764901,0.0001253658,0.0003992472,0.0001061489,0.000182952,0.000114314,0.0004549955,0.00005160203,0.000009809093],"category_scores_gemma":[0.003279492,0.00008980654,0.000206852,0.0005519165,0.00004931915,0.0002369595,0.0001895339,0.0002090163,0.000002844779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000149393,"about_ca_system_score_gemma":0.00002451336,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001179269,"about_ca_topic_score_gemma":0.000001854213,"domain_scores_codex":[0.9978978,0.0001903722,0.0007763948,0.0002585286,0.0006278501,0.0002490209],"domain_scores_gemma":[0.9976385,0.001230289,0.0006318766,0.0001523737,0.0002187033,0.0001282755],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005202815,0.00001781412,0.004172979,0.000008781792,0.000007912736,0.00002899932,0.0004049488,0.05252743,4.381851e-7,0.0031941,0.05398873,0.8851276],"study_design_scores_gemma":[0.001267738,0.0006315379,0.06928471,0.00003393083,0.00008820826,0.00001975284,0.0001439611,0.1694221,0.000003210342,0.3367498,0.4221675,0.000187662],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1154719,0.0007684741,0.8805052,0.001397564,0.0007787337,0.0002072719,0.000008024915,0.000008177503,0.0008546335],"genre_scores_gemma":[0.7984043,0.0004416221,0.198258,0.001455171,0.001270545,0.000006530981,2.210249e-7,0.00001237676,0.0001512326],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8849399,"threshold_uncertainty_score":0.3926095,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1404369829245352,"score_gpt":0.3837848372831986,"score_spread":0.2433478543586633,"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."}}