{"id":"W3208423201","doi":"10.1016/j.ecosta.2021.10.011","title":"Multivariate time-series modeling with generative neural networks","year":2021,"lang":"en","type":"article","venue":"Econometrics and Statistics","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Copula (linguistics); Autoregressive conditional heteroskedasticity; Econometrics; Univariate; Marginal distribution; Multivariate statistics; Principal component analysis; Series (stratigraphy); Joint probability distribution; Computer science; Time series; Mathematics; Statistics; Random variable; Volatility (finance)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001688612,0.0001545187,0.0003430184,0.0003225153,0.0002324116,0.0005497591,0.0001737959,0.00005656642,0.0003632544],"category_scores_gemma":[0.007977386,0.0001190117,0.0000286905,0.001438945,0.00007794415,0.000210195,0.0001580759,0.0001561458,0.00001309902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002605175,"about_ca_system_score_gemma":0.00006586157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000113173,"about_ca_topic_score_gemma":0.0000240511,"domain_scores_codex":[0.9982346,0.0002428181,0.0004670156,0.0004846173,0.0003175168,0.0002534434],"domain_scores_gemma":[0.9952929,0.00355972,0.0001827268,0.0003028543,0.0005152398,0.0001465744],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009669169,0.00004721354,0.01015593,0.000007164781,0.00007741872,0.0001316912,0.0004316733,0.4998776,0.00001129016,0.03468879,0.00215255,0.452322],"study_design_scores_gemma":[0.0002415545,0.00008815587,0.002788748,0.000003223562,0.00001401299,0.00003373418,0.0001297339,0.9736242,0.000009423178,0.02225728,0.0006419699,0.0001679507],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01926552,0.0003906424,0.9771941,0.000111565,0.0002846947,0.00007210763,0.0001647128,0.0000170358,0.002499645],"genre_scores_gemma":[0.1762082,0.00005097676,0.8209275,0.0001317526,0.0001089365,0.000005891447,0.00002512365,0.00001972395,0.002521877],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4737467,"threshold_uncertainty_score":0.9550253,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1407767531817722,"score_gpt":0.3582987306385353,"score_spread":0.2175219774567631,"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."}}