{"id":"W4394983035","doi":"10.1016/j.resourpol.2024.105008","title":"Fossil energy market price prediction by using machine learning with optimal hyper-parameters: A comparative study","year":2024,"lang":"en","type":"article","venue":"Resources Policy","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Econometrics; Fossil fuel; Energy (signal processing); Economics; Computer science; Machine learning; Artificial intelligence; Natural resource economics; Ecology; Statistics; Mathematics; Biology","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":[],"consensus_categories":[],"category_scores_codex":[0.0001357211,0.0002613867,0.0002428623,0.0002642638,0.0001577216,0.0002084163,0.0001273734,0.00006664817,0.00003284794],"category_scores_gemma":[0.0000144615,0.0002219215,0.00005198929,0.0005877702,0.0000458056,0.0001933091,0.00004530879,0.0003075065,0.000004206814],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001421066,"about_ca_system_score_gemma":0.00002396331,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001343003,"about_ca_topic_score_gemma":0.00005567692,"domain_scores_codex":[0.9988049,0.0000950967,0.0002243367,0.0002773902,0.0002258335,0.0003724458],"domain_scores_gemma":[0.9995673,0.0001222526,0.00003489935,0.0001430044,0.00001883988,0.0001137377],"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":[0.00009034589,0.00009256624,0.00412253,0.0001148069,0.0005317988,0.00004447377,0.01666043,0.9648889,0.002992535,0.00007783608,0.001198141,0.009185684],"study_design_scores_gemma":[0.0003115363,0.0003294433,0.0001874258,0.0001656337,0.00005531227,0.00007177255,0.0007726806,0.9036912,0.0008063596,0.000003864267,0.09335545,0.0002493492],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9764559,0.003249914,0.003467533,0.00001594049,0.0001021837,0.0001011927,0.00003744779,0.0007179303,0.01585198],"genre_scores_gemma":[0.9975348,0.00003715507,0.0007520943,0.00001196066,0.0003219583,0.00002036052,0.00001531477,0.00006626185,0.001240078],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0921573,"threshold_uncertainty_score":0.9049695,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01639525395504762,"score_gpt":0.2421425134712465,"score_spread":0.2257472595161988,"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."}}