{"id":"W3205693690","doi":"10.3390/jrfm14100486","title":"Univariate and Multivariate Machine Learning Forecasting Models on the Price Returns of Cryptocurrencies","year":2021,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Minnesota","keywords":"Univariate; Exponential smoothing; Multivariate statistics; Cryptocurrency; Autoregressive model; Computer science; Artificial neural network; Artificial intelligence; Autoregressive integrated moving average; Econometrics; Machine learning; Time series; Economics","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008201536,0.0001381553,0.0003673335,0.0002522221,0.0002899391,0.0001281723,0.0002824994,0.00004652062,0.00002502787],"category_scores_gemma":[0.01208625,0.00008195551,0.0001085394,0.000603982,0.00008260488,0.0001922003,0.0003614771,0.000430748,5.798536e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002066686,"about_ca_system_score_gemma":0.00004309839,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000197086,"about_ca_topic_score_gemma":0.00001065424,"domain_scores_codex":[0.9973577,0.0007221066,0.0007539497,0.0002285956,0.0007533378,0.0001843002],"domain_scores_gemma":[0.9947483,0.00347196,0.001098203,0.0002079058,0.0004042044,0.00006940691],"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":[0.0003678866,0.00007886381,0.008794226,0.00004012583,0.00005321883,0.0001129798,0.003603126,0.007485684,0.0001151953,0.04621705,0.0002401164,0.9328915],"study_design_scores_gemma":[0.002362856,0.0007333917,0.2387745,0.0007590384,0.0002756846,0.0001883048,0.004390131,0.1829022,0.0004167934,0.5305217,0.03826633,0.0004090485],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6089113,0.001191092,0.383895,0.0003812002,0.0004747152,0.0001601549,0.00001113413,0.000006798969,0.004968519],"genre_scores_gemma":[0.9602631,0.0009562466,0.03834409,0.00005912889,0.00009020105,0.00000156574,2.443148e-7,0.000008664083,0.0002768045],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9324825,"threshold_uncertainty_score":0.9962354,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0988580055736412,"score_gpt":0.3256142055934538,"score_spread":0.2267562000198126,"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."}}