{"id":"W4400698552","doi":"10.1186/s40854-024-00637-z","title":"Deep learning systems for forecasting the prices of crude oil and precious metals","year":2024,"lang":"en","type":"article","venue":"Financial Innovation","topic":"Market Dynamics and Volatility","field":"Economics, Econometrics and Finance","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Crude oil; Precious metal; Deep learning; Economics; Petroleum engineering; Natural resource economics; Econometrics; Monetary economics; Environmental science; Computer science; Artificial intelligence; Geology; Metallurgy; Materials science; Metal","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":[0.0007483399,0.001079338,0.0005181827,0.0005519565,0.0002824662,0.0007072159,0.000875323,0.0009387867,0.001958383],"category_scores_gemma":[0.002124969,0.0004012377,0.0006006139,0.0005636318,0.0002502641,0.001024328,0.0005371138,0.001547394,0.0004882198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001217101,"about_ca_system_score_gemma":0.001274876,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03775802,"about_ca_topic_score_gemma":0.02683728,"domain_scores_codex":[0.9998057,0.00003157269,0.00001892584,0.00005289559,0.00004254887,0.00004833444],"domain_scores_gemma":[0.9993737,0.0002556584,0.00007337684,0.00004779328,0.0002116354,0.00003787534],"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":[0.0001481178,0.0001810733,0.003860191,0.00005281272,0.00005906627,0.00005785393,0.00002438367,0.9380776,0.002714985,0.0008325176,0.001428089,0.05256325],"study_design_scores_gemma":[0.000002368021,0.00000863891,0.0001758779,0.000001791227,0.000002691277,0.000001184472,0.000001795401,0.999103,0.00046694,0.0001753385,0.00005878645,0.000001633717],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7786031,0.002357588,0.2051162,0.001191708,0.00037952,0.00009422516,0.001544219,0.004313264,0.006400046],"genre_scores_gemma":[0.9788862,0.0002291367,0.01854179,0.00007840421,0.00002356754,0.00003103602,0.0007378625,0.00002534778,0.001446622],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03775802,"threshold_uncertainty_score":0.07507652,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04569695881410248,"score_gpt":0.2430380624379921,"score_spread":0.1973411036238896,"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."}}