{"id":"W3158095307","doi":"10.3390/jrfm14050198","title":"Predicting Gold and Silver Price Direction Using Tree-Based Classifiers","year":2021,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Market Dynamics and Volatility","field":"Economics, Econometrics and Finance","cited_by":63,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Random forest; Gradient boosting; Decision tree; Boosting (machine learning); Econometrics; Portfolio; Computer science; Bootstrap aggregating; Artificial intelligence; Hedge; Tree (set theory); Machine learning; Economics; Mathematics; Statistics; Financial economics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.0007813033,0.00009289513,0.0002580237,0.0001650681,0.0001109866,0.000073527,0.0000489061,0.00005869254,0.00001891229],"category_scores_gemma":[0.0001525324,0.00009994517,0.00007945588,0.000187258,0.00002905538,0.0001466223,0.00005008025,0.0001670314,4.714054e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006896775,"about_ca_system_score_gemma":0.00001882222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006373751,"about_ca_topic_score_gemma":0.00005381508,"domain_scores_codex":[0.9991317,0.00002480324,0.0004719395,0.0001851815,0.00004740659,0.0001389106],"domain_scores_gemma":[0.999265,0.00004605441,0.0004761291,0.00009745001,0.00004790415,0.00006753254],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00007488888,0.00007969105,0.9301537,0.00008828101,0.00003845196,0.00003910977,0.0001363476,0.00011982,0.00001059442,0.008904582,0.00007824981,0.06027628],"study_design_scores_gemma":[0.001055248,0.00006979196,0.8383226,0.00006426263,0.00005756141,0.00001150363,0.0001220658,0.1096751,0.000007827756,0.009856778,0.04059646,0.000160808],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9319816,0.002118796,0.05941711,0.00007473543,0.0005196687,0.00007384233,0.00002417799,0.000005685421,0.005784389],"genre_scores_gemma":[0.9933801,0.002079434,0.004148182,0.00007246197,0.0001222211,0.000001007531,0.000001125693,0.000008257274,0.0001872224],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1095553,"threshold_uncertainty_score":0.4075646,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01585809016406823,"score_gpt":0.2059953128721503,"score_spread":0.1901372227080821,"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."}}