{"id":"W2910159406","doi":"10.3390/jrfm12010017","title":"Trend Prediction Classification for High Frequency Bitcoin Time Series with Deep Learning","year":2019,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":84,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Time series; Series (stratigraphy); Machine learning; Cryptocurrency; Deep learning; Baseline (sea); Classifier (UML); Profit (economics); Econometrics; Odds; Mathematics; Logistic regression; 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":[],"consensus_categories":[],"category_scores_codex":[0.003618092,0.000104322,0.0002575573,0.0003553719,0.0001663444,0.0001160213,0.0001877821,0.00005020606,0.00005956316],"category_scores_gemma":[0.001086525,0.0000695945,0.00006831178,0.0003854152,0.00004062065,0.0003860506,0.00003974009,0.000163544,0.00001199068],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003810495,"about_ca_system_score_gemma":0.00001813829,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003668165,"about_ca_topic_score_gemma":0.00001256215,"domain_scores_codex":[0.9983582,0.0001820109,0.0005399007,0.0002117369,0.000563285,0.0001448011],"domain_scores_gemma":[0.998295,0.0005481173,0.0007891182,0.0001528225,0.0001622812,0.0000526751],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0005663825,0.00002900643,0.095002,0.00001539204,0.00001928742,0.000005582784,0.0003248886,0.0003490609,0.0000880452,0.004093918,0.0004830321,0.8990234],"study_design_scores_gemma":[0.00130865,0.001311288,0.9082066,0.00007149792,0.0001107043,0.00003446279,0.0006172932,0.001519963,0.00003637839,0.03753253,0.0491186,0.000132037],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6733208,0.0001389643,0.323496,0.0001437235,0.0005795601,0.0002993817,0.00001126629,0.00001472056,0.001995691],"genre_scores_gemma":[0.8957728,0.0001606575,0.1015313,0.00001829029,0.0002316237,0.00000962021,0.000002872742,0.00001220712,0.002260583],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8988914,"threshold_uncertainty_score":0.2837981,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02576748199051209,"score_gpt":0.2906265897207604,"score_spread":0.2648591077302483,"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."}}