{"id":"W3009818944","doi":"10.3390/jrfm13030048","title":"The Predictability of the Exchange Rate When Combining Machine Learning and Fundamental Models","year":2020,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Japan Society for the Promotion of Science","keywords":"Random walk; Predictability; Machine learning; Random walk hypothesis; Computer science; Artificial intelligence; Mean squared error; Random forest; Robustness (evolution); Support vector machine; Artificial neural network; Econometrics; Statistics; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008162597,0.001273832,0.001253681,0.001722847,0.0003473894,0.001884103,0.0006248885,0.0008957778,0.000768962],"category_scores_gemma":[0.0253136,0.0003481522,0.0009922303,0.00131778,0.0008224866,0.003823922,0.001528922,0.001857255,0.0002482471],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004738972,"about_ca_system_score_gemma":0.0007257464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003497698,"about_ca_topic_score_gemma":0.002280678,"domain_scores_codex":[0.9977856,0.00107406,0.0001479258,0.0003607342,0.0004837408,0.0001478676],"domain_scores_gemma":[0.9881502,0.008716104,0.0009976526,0.001175027,0.0007538517,0.0002070553],"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":[0.0006261941,0.000185392,0.129339,0.0002613414,0.0007419605,0.0005160726,0.0002797731,0.7250569,0.001830795,0.02102132,0.002367052,0.1177742],"study_design_scores_gemma":[0.00001880346,0.0001811616,0.01996448,0.00005809782,0.00009520244,0.0000810119,0.00007696814,0.9610583,0.0008050026,0.01697101,0.000651243,0.00003869311],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8216385,0.003831221,0.1631525,0.002235653,0.0003610051,0.0000727487,0.0005135661,0.0005965953,0.007598253],"genre_scores_gemma":[0.9896059,0.0005094309,0.009067313,0.0000716394,0.0001201015,0.00001225269,0.0003254654,0.00002288152,0.0002650831],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008162597,"threshold_uncertainty_score":0.04316849,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0665666561425755,"score_gpt":0.3158718074720996,"score_spread":0.2493051513295241,"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."}}