{"id":"W3183461380","doi":"10.3390/jrfm14070337","title":"Bitcoin Return Volatility Forecasting: A Comparative Study between GARCH and RNN","year":2021,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Market Dynamics and Volatility","field":"Economics, Econometrics and Finance","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Volatility (finance); Econometrics; Autoregressive conditional heteroskedasticity; EWMA chart; Financial market; Value at risk; Risk management; Computer science; Implied volatility; Economics; Finance; Process (computing)","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":[0.001706127,0.0001404697,0.000588382,0.0001736244,0.0001635186,0.00009111567,0.0001051636,0.00005367473,0.0000371431],"category_scores_gemma":[0.0001862585,0.0001407336,0.00009027943,0.0002355413,0.00005188318,0.000145328,0.0001781184,0.0002932964,0.00000116712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004315279,"about_ca_system_score_gemma":0.00001778646,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006775883,"about_ca_topic_score_gemma":0.000141863,"domain_scores_codex":[0.998579,0.00006889469,0.0008080666,0.0002848708,0.00007475046,0.0001844582],"domain_scores_gemma":[0.9989294,0.0001245224,0.0005718925,0.0001789684,0.00009375633,0.0001014863],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00007031255,0.0001736043,0.9693288,0.00004400697,0.0000676714,0.00005343747,0.001472247,0.000001659862,2.246765e-7,0.002975569,0.0001268683,0.02568565],"study_design_scores_gemma":[0.001108717,0.0002435583,0.9352046,0.00002510786,0.00005506417,0.000008708954,0.0007135082,0.006556876,0.000001286292,0.04051447,0.0154234,0.0001446669],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9823211,0.001665401,0.01267371,0.00007074476,0.0001888009,0.0002065746,0.00007383931,0.000004618264,0.002795199],"genre_scores_gemma":[0.9974765,0.000615459,0.00156795,0.00002207303,0.0001289455,0.000002924101,0.000002502007,0.000006882929,0.0001768251],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0375389,"threshold_uncertainty_score":0.5738949,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05212448732138118,"score_gpt":0.2560470661621788,"score_spread":0.2039225788407976,"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."}}