{"id":"W4412662697","doi":"10.1002/ijfe.70012","title":"Using Deep Learning Conditional Value‐at‐Risk Based Utility Function in Cryptocurrency Portfolio Optimisation","year":2025,"lang":"en","type":"article","venue":"International Journal of Finance & Economics","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Trent University; Nottingham Trent University","keywords":"Cryptocurrency; Economics; Portfolio; Econometrics; Value at risk; Expected shortfall; Value (mathematics); Financial economics; Portfolio optimization; Function (biology); Computer science; Risk management; Machine learning; Finance","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00622587,0.0001501188,0.0003406793,0.001068779,0.0001391477,0.0001682512,0.0006985925,0.0001070177,0.0005314017],"category_scores_gemma":[0.007104306,0.000154024,0.0002346814,0.0003648988,0.00009096909,0.0006877019,0.00009543089,0.0004420439,0.00001356097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008299603,"about_ca_system_score_gemma":0.0004856283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003015641,"about_ca_topic_score_gemma":0.00003658689,"domain_scores_codex":[0.9969443,0.0004195069,0.001574154,0.0003351271,0.0005408025,0.0001861307],"domain_scores_gemma":[0.9948376,0.001994583,0.002002479,0.000189987,0.0009273531,0.00004795915],"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":[0.0005363469,0.00006779943,0.275988,0.000001726371,0.00003967945,0.000008379577,0.00005258336,0.5675735,0.00004301417,0.004373767,0.0002681789,0.151047],"study_design_scores_gemma":[0.0009425087,0.00004913514,0.4102128,0.00005944444,0.00001800741,0.0000305254,0.0000610171,0.4877542,0.000168717,0.09193061,0.00866843,0.0001045112],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6493533,0.0001139401,0.3450622,0.0002384528,0.002301962,0.00007109909,0.00001618113,0.000005933669,0.002836931],"genre_scores_gemma":[0.9603963,0.00006480991,0.03897121,0.0001707343,0.0001964194,0.000003488952,0.000009754948,0.000008604908,0.0001786906],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.311043,"threshold_uncertainty_score":0.8505031,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08745596305420789,"score_gpt":0.3955948221646041,"score_spread":0.3081388591103962,"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."}}