{"id":"W4410959326","doi":"10.3390/jrfm18060300","title":"Forecasting Sovereign Credit Risk Amidst a Political Crisis: A Machine Learning and Deep Learning Approach","year":2025,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Credit Risk and Financial Regulations","field":"Economics, Econometrics and Finance","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Credit risk; Politics; Artificial intelligence; Financial crisis; Sovereignty; Business; Financial system; Political science; Machine learning; Economics; Computer science; Actuarial science; Keynesian economics; Law","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001157867,0.000211023,0.0005602363,0.000619571,0.0005869241,0.0001498392,0.0001409871,0.0001268979,0.00001534481],"category_scores_gemma":[0.0006867994,0.000218547,0.0001678558,0.0003916685,0.00009138579,0.0002162934,0.0001817754,0.0007659384,0.000003880278],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001025417,"about_ca_system_score_gemma":0.00001961514,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002558631,"about_ca_topic_score_gemma":0.00002088987,"domain_scores_codex":[0.9982382,0.00005514429,0.0008813376,0.0003325604,0.00009008197,0.0004026747],"domain_scores_gemma":[0.9988124,0.0001077066,0.0007558452,0.0001138741,0.00007042895,0.0001397199],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0001218517,0.0001074538,0.3012179,0.00008379778,0.00007617915,0.000022305,0.0006206715,0.0008229928,3.241022e-7,0.5556379,0.0002033105,0.1410853],"study_design_scores_gemma":[0.003332238,0.0004854299,0.4849347,0.000169437,0.0003462806,0.00006994053,0.003024133,0.06158316,0.000003436447,0.2184542,0.2270133,0.0005836602],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4395217,0.0222952,0.5018775,0.0002314787,0.0007979248,0.0003858124,0.00007980176,0.00005147751,0.03475909],"genre_scores_gemma":[0.9832341,0.009742132,0.006239706,0.00002614293,0.0003682671,0.000008920239,0.000005419677,0.00001802201,0.0003572572],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5437124,"threshold_uncertainty_score":0.8912086,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0138937225881117,"score_gpt":0.2134474795322018,"score_spread":0.1995537569440901,"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."}}