{"id":"W4386027977","doi":"10.1142/s2424786323500238","title":"High-frequency stock return prediction using state-of-the-art deep learning models","year":2023,"lang":"en","type":"article","venue":"International Journal of Financial Engineering","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Wilfrid Laurier University; University of Ottawa","funders":"","keywords":"Computer science; Stock (firearms); Benchmark (surveying); Artificial intelligence; Deep learning; Machine learning; Econometrics; Data mining; Economics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007761943,0.0008798012,0.0005970058,0.0009325898,0.0002580347,0.0008650133,0.0009924548,0.0008083662,0.001843362],"category_scores_gemma":[0.002111009,0.0003249649,0.0005306931,0.0009556158,0.0002086769,0.001559734,0.0005149184,0.001396005,0.0008370082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006587518,"about_ca_system_score_gemma":0.0007438333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01149245,"about_ca_topic_score_gemma":0.01495418,"domain_scores_codex":[0.9997545,0.00003600306,0.00001999011,0.00007648637,0.00006059365,0.00005239664],"domain_scores_gemma":[0.9993781,0.000308236,0.00007912593,0.00005377955,0.000150819,0.00002999664],"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":[0.0003136534,0.0004062016,0.01676803,0.0001519397,0.0002509671,0.0001673206,0.00007674666,0.5564043,0.0069606,0.00297538,0.006100866,0.409424],"study_design_scores_gemma":[0.000003060698,0.00001043728,0.0006730502,0.00000507625,0.000006934799,0.000005379941,0.00000394062,0.9978712,0.0006096266,0.0006642358,0.0001439539,0.000003171771],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5189851,0.004181111,0.4622884,0.001518231,0.0003010295,0.00006471283,0.001738566,0.003468083,0.00745477],"genre_scores_gemma":[0.9572249,0.0007340707,0.03763519,0.0001663124,0.00009412275,0.00003663856,0.001387503,0.00003963379,0.002681611],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01149245,"threshold_uncertainty_score":0.02285111,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07436283700729719,"score_gpt":0.3372976158623459,"score_spread":0.2629347788550487,"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."}}