{"id":"W4403331846","doi":"10.23919/fusion59988.2024.10706354","title":"Enhancing Stock Trading Performance with Deep Q-Learning by Addressing Noisy Data through Advanced Denoising Techniques","year":2024,"lang":"en","type":"article","venue":"","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Noise reduction; Computer science; Deep learning; Artificial intelligence; Stock (firearms); Noisy data; Machine learning; Engineering","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.008413549,0.0004164709,0.0005457379,0.0003754512,0.0007905073,0.001613787,0.001895675,0.0001428084,0.0004589614],"category_scores_gemma":[0.004652124,0.0002894939,0.00007928241,0.002136132,0.0001773566,0.004078615,0.0007051589,0.00083947,0.0000482521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001559652,"about_ca_system_score_gemma":0.0001481055,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003594823,"about_ca_topic_score_gemma":0.0000511766,"domain_scores_codex":[0.9942808,0.0005399855,0.0009686869,0.001662633,0.001798619,0.0007493022],"domain_scores_gemma":[0.9927647,0.005138393,0.0003000265,0.001441249,0.0002125657,0.0001430607],"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":[0.00006295361,0.00001461358,0.001125826,0.00006163761,0.00002936899,0.00002266377,0.001185953,0.0001672721,0.03246072,0.00007323962,0.002502398,0.9622934],"study_design_scores_gemma":[0.0004812997,0.0006475056,0.0006418605,0.003015475,0.0001254482,0.0004984831,0.003375224,0.500149,0.299175,0.003169193,0.1871281,0.001593461],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1489518,0.001805943,0.8156159,0.0002429762,0.0003844542,0.0003386732,0.000007643784,0.001089184,0.03156343],"genre_scores_gemma":[0.5450196,0.00004979767,0.4520709,0.0001262669,0.0001509488,0.00002163468,0.00001538181,0.00007521809,0.00247026],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9606999,"threshold_uncertainty_score":0.9999557,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1652417143692586,"score_gpt":0.4361459240807093,"score_spread":0.2709042097114507,"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."}}