{"id":"W4392345811","doi":"10.1007/s10844-024-00851-2","title":"Ensemble of temporal Transformers for financial time series","year":2024,"lang":"en","type":"article","venue":"Journal of Intelligent Information Systems","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Time series; Heteroscedasticity; Estimator; Transformer; Artificial intelligence; Machine learning; Autoregressive integrated moving average; Embedding; Ensemble learning; Deep learning; Autoregressive conditional heteroskedasticity; Data mining; Econometrics; Finance; Volatility (finance); Statistics","routes":{"ca_aff":true,"ca_fund":false,"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":[0.01112823,0.0001356065,0.0004945914,0.0009491611,0.00006623776,0.0003759867,0.0003836997,0.0001081012,0.00009165049],"category_scores_gemma":[0.004841962,0.00008999796,0.0004079917,0.0007055938,0.0000540842,0.002542315,0.00002015376,0.000161877,0.0001163049],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009126568,"about_ca_system_score_gemma":0.0004113229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008117383,"about_ca_topic_score_gemma":0.000001117631,"domain_scores_codex":[0.9953547,0.0001650177,0.002912593,0.00008725793,0.00130151,0.0001789352],"domain_scores_gemma":[0.9951977,0.001755785,0.001204244,0.0001322052,0.001611194,0.00009885409],"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":[0.001294605,0.00004497039,0.0004232147,0.0008347835,0.0001757041,0.00000722302,0.01020349,0.004825316,0.001200357,0.009620919,0.1104928,0.8608766],"study_design_scores_gemma":[0.0003376047,0.0009900822,0.000123717,0.0006817468,0.00004778414,0.0005698667,0.004269594,0.03352348,0.01235825,0.004438931,0.9424548,0.0002042175],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02058219,0.0004806582,0.966244,0.0002304603,0.004503184,0.0004666017,0.00006035859,0.00002201134,0.007410491],"genre_scores_gemma":[0.9829816,0.00003982126,0.01361004,0.00005308782,0.0004642159,0.00001752653,0.000007505924,0.00001502807,0.002811174],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9623994,"threshold_uncertainty_score":0.5796631,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07442814628610717,"score_gpt":0.3738199868221773,"score_spread":0.2993918405360702,"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."}}