{"id":"W4416400216","doi":"10.2139/ssrn.5638110","title":"Hybrid Deep Learning Architectures for Value-at-Risk Forecasting: Integrating LSTM and Kolmogorov-Arnold Networks","year":2025,"lang":"","type":"preprint","venue":"SSRN Electronic Journal","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"","keywords":"Interpretability; Leverage (statistics); Deep learning; Artificial neural network; Benchmark (surveying); Suite; Volatility (finance)","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","metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":["metaresearch","metaepi_narrow"],"category_scores_codex":[0.08690121,0.002311354,0.003159297,0.002289907,0.006731186,0.00235235,0.003903827,0.001207649,0.0001440208],"category_scores_gemma":[0.08637275,0.001984104,0.002215208,0.001415074,0.0007961623,0.0002480044,0.004591938,0.03270352,0.000008750709],"about_ca_system_candidate":true,"about_ca_system_consensus":true,"about_ca_system_score_codex":0.0047352,"about_ca_system_score_gemma":0.007728316,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000304298,"about_ca_topic_score_gemma":0.00188931,"domain_scores_codex":[0.9690723,0.007889331,0.005067455,0.003911376,0.002847258,0.01121232],"domain_scores_gemma":[0.9531631,0.03542995,0.00727307,0.001561386,0.001697294,0.0008752267],"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":[0.001396045,0.00006715339,0.01054695,0.00009669318,0.001041736,0.00001537305,0.001009337,0.2321041,0.00001682231,0.004679488,0.0001062689,0.7489201],"study_design_scores_gemma":[0.001563024,0.0011981,0.0005484492,0.0008851178,0.0007017846,0.003086103,0.0018932,0.5412851,0.00006171738,0.4452132,0.00244321,0.001121011],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2108515,0.03059748,0.7492943,0.0003897596,0.003771509,0.001901875,0.00004895224,0.0001469307,0.002997641],"genre_scores_gemma":[0.8881539,0.01290509,0.07867113,0.0002033964,0.003441418,0.0002530743,0.00003356571,0.0003002491,0.0160382],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.747799,"threshold_uncertainty_score":0.9990854,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03480274013096053,"score_gpt":0.334073926670498,"score_spread":0.2992711865395374,"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."}}