{"id":"W4411535804","doi":"10.3390/jrfm18070346","title":"Price Forecasting of Crude Oil Using Hybrid Machine Learning Models","year":2025,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Market Dynamics and Volatility","field":"Economics, Econometrics and Finance","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Gradient boosting; Crude oil; Artificial neural network; Computer science; Artificial intelligence; Boosting (machine learning); Machine learning; Random forest; Deep learning; Partial least squares regression; Process (computing); Reliability (semiconductor); Engineering; Petroleum engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007182026,0.0004972537,0.0007148202,0.0006010701,0.0001911395,0.0007024515,0.0006533409,0.0006084884,0.0004787947],"category_scores_gemma":[0.001143238,0.0002494598,0.0006892466,0.0005465351,0.0001906911,0.000634146,0.0003151982,0.0005651098,0.0001386665],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004358179,"about_ca_system_score_gemma":0.0004228861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01152215,"about_ca_topic_score_gemma":0.008946944,"domain_scores_codex":[0.999779,0.000064789,0.00001428154,0.00004976488,0.00006150103,0.00003065466],"domain_scores_gemma":[0.9995325,0.0002487196,0.00006621302,0.00002998949,0.0001082009,0.00001438225],"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":[0.00002908143,0.00002109301,0.001447582,0.000008558916,0.00003400142,0.00002082316,0.000007292294,0.985544,0.0005153802,0.0005130658,0.00009486997,0.01176413],"study_design_scores_gemma":[4.635246e-7,0.000003113347,0.00009661217,4.538973e-7,0.000001481259,0.000001160465,6.299492e-7,0.999744,0.00005648676,0.00007948381,0.0000150511,9.802825e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6403355,0.0009951185,0.3520927,0.0003157852,0.00009320753,0.00004095333,0.0002216097,0.0006144966,0.005290532],"genre_scores_gemma":[0.9860538,0.0001354779,0.01293945,0.00002119219,0.00001771961,0.00001441439,0.00009350916,0.000007783468,0.000716557],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01152215,"threshold_uncertainty_score":0.02291018,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02752525700010511,"score_gpt":0.2131043322066272,"score_spread":0.1855790752065221,"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."}}