{"id":"W2909171489","doi":"10.3390/jrfm12010009","title":"Can We Forecast Daily Oil Futures Prices? Experimental Evidence from Convolutional Neural Networks","year":2019,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Market Dynamics and Volatility","field":"Economics, Econometrics and Finance","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Japan Society for the Promotion of Science","keywords":"Benchmark (surveying); Convolutional neural network; Futures contract; Computer science; Artificial neural network; Term (time); Artificial intelligence; Deep learning; Machine learning; Crude oil; Recurrent neural network; Econometrics; Economics; Financial economics; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005621274,0.0001560966,0.0003799457,0.0001454828,0.0001261785,0.00009034223,0.0002221736,0.00007826585,0.0002573045],"category_scores_gemma":[0.00004507475,0.0001529475,0.0001475749,0.0001243963,0.00003701458,0.0002660282,0.0001301611,0.0002555898,0.000006353412],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009999028,"about_ca_system_score_gemma":0.00001427768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003559096,"about_ca_topic_score_gemma":0.0001235887,"domain_scores_codex":[0.9987566,0.00002272597,0.0006440409,0.000265592,0.00008818709,0.0002228619],"domain_scores_gemma":[0.9988727,0.00008715209,0.0007282156,0.0001782417,0.00003721809,0.0000964874],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004480126,0.0001592231,0.8713241,0.00005360527,0.00008065098,0.00002878284,0.0008233622,0.0008170371,0.000004559305,0.02355002,0.0008838183,0.1018269],"study_design_scores_gemma":[0.001270129,0.0002201881,0.8369465,0.0001176476,0.00003116114,0.000007481577,0.0003014349,0.124824,0.00000234625,0.01431537,0.02167633,0.0002873589],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9691392,0.01880486,0.008967407,0.0002548262,0.001508078,0.0001020286,0.00009965558,0.000005879421,0.001118122],"genre_scores_gemma":[0.9906269,0.007549798,0.001032767,0.0001186333,0.0004097295,0.000004050212,0.000005331216,0.00001058812,0.0002422235],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.124007,"threshold_uncertainty_score":0.6237019,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01395482943018077,"score_gpt":0.2075414607710641,"score_spread":0.1935866313408833,"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."}}