{"id":"W3134631187","doi":"10.3390/su13052761","title":"An Effective Hybrid Approach for Forecasting Currency Exchange Rates","year":2021,"lang":"en","type":"article","venue":"Sustainability","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Exponential smoothing; Autoregressive integrated moving average; Mean absolute percentage error; Mean squared error; Foreign exchange market; Exchange rate; Econometrics; Moving average; Support vector machine; Random walk; Economics; Computer science; Statistics; Time series; Mathematics; Finance; Machine learning","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01996853,0.0003091213,0.0006111959,0.000226327,0.0005196438,0.0003935387,0.0008264115,0.0001084406,0.0001912569],"category_scores_gemma":[0.1784801,0.0002561516,0.0003375436,0.00137808,0.0002084136,0.000587578,0.0003586284,0.000277378,0.000003972492],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008037473,"about_ca_system_score_gemma":0.0007219379,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005100449,"about_ca_topic_score_gemma":0.00001891555,"domain_scores_codex":[0.9930502,0.002876308,0.0007827226,0.001587003,0.0009076797,0.0007961558],"domain_scores_gemma":[0.9799014,0.01153541,0.0003274647,0.001604793,0.006356531,0.0002744322],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001823362,0.0003475869,0.06213595,0.000283374,0.0000179357,0.00002139913,0.001035878,0.0003383632,0.00005470628,0.0008730875,0.001264717,0.9334447],"study_design_scores_gemma":[0.001177848,0.0005776445,0.07113576,0.00001837724,0.00005325025,0.0000868741,0.006785722,0.17738,0.005451541,0.7286392,0.008016577,0.000677167],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4667076,0.0002814022,0.5274653,0.000280626,0.000482482,0.001862972,0.00005404941,0.0001150826,0.002750473],"genre_scores_gemma":[0.9057858,9.924366e-7,0.09198327,0.00005591834,0.0002898522,0.0007445652,0.00004012311,0.00003193547,0.001067527],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9327675,"threshold_uncertainty_score":0.9999891,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1161914337501394,"score_gpt":0.4440631469366597,"score_spread":0.3278717131865203,"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."}}