{"id":"W2970944481","doi":"","title":"Machine Learning vs Traditional Forecasting Methods: An Application to South African GDP","year":2019,"lang":"en","type":"preprint","venue":"RePEc: Research Papers in Economics","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Autoregressive model; Gross domestic product; Quarter (Canadian coin); Machine learning; Computer science; Mean squared error; Econometrics; Artificial intelligence; Order (exchange); Support vector machine; Statistics; Economics; Mathematics; Geography; Finance; Macroeconomics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003675997,0.0004537457,0.0006033801,0.001747962,0.0004369577,0.0009258271,0.0004436581,0.0009032333,0.001623939],"category_scores_gemma":[0.01362304,0.0001503357,0.0004672895,0.004871333,0.0003749184,0.0009422469,0.0008570281,0.0008248157,0.0001404014],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001001133,"about_ca_system_score_gemma":0.0007156153,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02099434,"about_ca_topic_score_gemma":0.01434886,"domain_scores_codex":[0.9991179,0.0006063808,0.00003976775,0.00004912858,0.0001348168,0.00005193146],"domain_scores_gemma":[0.9920807,0.007089749,0.000235943,0.000166286,0.0003775274,0.00004975206],"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":[0.0009414298,0.0005584732,0.06348845,0.001166633,0.0003302146,0.001179694,0.001923792,0.4847274,0.002179672,0.02864873,0.003706262,0.4111491],"study_design_scores_gemma":[0.00007591718,0.0003009962,0.03446123,0.0001880505,0.00007848707,0.000171673,0.001806972,0.9446877,0.001939496,0.01171213,0.004532943,0.00004445575],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9343491,0.004313249,0.04903332,0.002430544,0.0001254682,0.000135565,0.0003940646,0.0001540466,0.009064709],"genre_scores_gemma":[0.9551024,0.003587069,0.03924096,0.00007974387,0.00006316815,0.00006726318,0.0001458148,0.00002249187,0.001690965],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02099434,"threshold_uncertainty_score":0.04174429,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2726753483654092,"score_gpt":0.4515184918929035,"score_spread":0.1788431435274943,"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."}}