{"id":"W2022679375","doi":"10.1016/j.procs.2014.05.190","title":"Multi-scale Foreign Exchange Rates Ensemble for Classification of Trends in Forex Market","year":2014,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"CTS Forex (Canada); University of Calgary","funders":"","keywords":"Foreign exchange market; Computer science; Artificial intelligence; Foreign exchange; Machine learning; Naive Bayes classifier; Classifier (UML); Ensemble learning; Bayesian probability; Exchange rate; Econometrics; Support vector machine; Economics; Finance","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":[0.01666928,0.0001838977,0.0003854647,0.001281511,0.000178466,0.0002050305,0.001771446,0.00007687358,0.00009164072],"category_scores_gemma":[0.004240672,0.0001447061,0.0001081572,0.003613314,0.0004747185,0.0006429991,0.0003352289,0.00009882692,0.000007517171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006550473,"about_ca_system_score_gemma":0.0001258453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001060566,"about_ca_topic_score_gemma":0.00007585555,"domain_scores_codex":[0.9963628,0.0002194539,0.0007709754,0.0009780815,0.001141056,0.0005276496],"domain_scores_gemma":[0.9952005,0.002705384,0.0004576053,0.0006925554,0.000791296,0.0001526559],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005363669,0.00008176607,0.03230867,0.00002414724,0.000001561807,1.880508e-7,0.0008411842,0.00004598514,0.006587857,0.0005507613,0.006004633,0.9534996],"study_design_scores_gemma":[0.0004484045,0.000133514,0.2693477,0.000019341,0.000002601564,0.000004129159,0.00003938964,0.7148295,0.003243312,0.01075129,0.001053465,0.0001273789],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05978658,0.00002265953,0.9300247,0.0001848884,0.0005503325,0.000351721,0.000005893031,0.00004099743,0.009032168],"genre_scores_gemma":[0.5460633,7.721043e-7,0.4533375,0.00005537312,0.00008929182,0.00005972563,0.000001384276,0.000008143612,0.0003844901],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9533722,"threshold_uncertainty_score":0.5900944,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1653560080113247,"score_gpt":0.4141153214285095,"score_spread":0.2487593134171849,"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."}}