{"id":"W4401550660","doi":"10.62051/pg1hn367","title":"Deep Learning for Temporal Stock Prediction: A Comparison","year":2024,"lang":"en","type":"article","venue":"Transactions on Computer Science and Intelligent Systems Research","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Trinity College; University of Toronto","funders":"","keywords":"Deep learning; Computer science; Artificial intelligence; Categorization; Machine learning; Recurrent neural network; Perspective (graphical); Artificial neural network","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":["metaresearch","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.03302479,0.0001855921,0.0003378726,0.002259745,0.001818905,0.003046274,0.001041165,0.0000977072,0.00008231527],"category_scores_gemma":[0.00106788,0.0001376704,0.0001225224,0.004439729,0.0007990008,0.0006690557,0.00005259068,0.0007920952,0.0001575914],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000278497,"about_ca_system_score_gemma":0.000383939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007925198,"about_ca_topic_score_gemma":0.0000110397,"domain_scores_codex":[0.9924214,0.0008788828,0.0008281703,0.001216925,0.003962813,0.0006917755],"domain_scores_gemma":[0.9907935,0.006474173,0.00007143049,0.0005374086,0.001797958,0.000325593],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005628165,0.0000634457,0.0003516338,0.00006116254,0.00002049933,0.000003582238,0.001627695,0.04531949,0.00008500272,0.0009066395,0.002299069,0.9492055],"study_design_scores_gemma":[0.00008582908,0.0009239198,0.0002814805,0.0001641454,0.000005527495,0.00004530824,0.0008560371,0.9128879,0.0004643349,0.0006876535,0.08347639,0.0001215119],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005939266,0.0006899517,0.9874915,0.0004138198,0.003452844,0.001004354,0.000007320352,0.0001735785,0.0008273682],"genre_scores_gemma":[0.9826227,0.00003411432,0.0132859,0.00001734645,0.000360969,0.0002147674,0.000001226759,0.00002034294,0.003442578],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9766835,"threshold_uncertainty_score":0.9994806,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3656439796638002,"score_gpt":0.5104055559702646,"score_spread":0.1447615763064644,"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."}}