{"id":"W4413856579","doi":"10.28991/esj-2025-09-04-05","title":"Gradient Descent Decision Tree Algorithm and Nonlinear Programming for Credit Risk Assessment and Credit Strategy","year":2025,"lang":"en","type":"article","venue":"Emerging Science Journal","topic":"Financial Distress and Bankruptcy Prediction","field":"Business, Management and Accounting","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina","funders":"","keywords":"Decision tree; Gradient descent; Computer science; Nonlinear system; Credit risk; Stochastic gradient descent; Algorithm; Mathematical optimization; Artificial intelligence; Mathematics; Business; Actuarial science; Artificial neural network","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001472362,0.0001483638,0.0001616829,0.0004231942,0.001626077,0.001507434,0.0002161432,0.00004176546,0.0000105249],"category_scores_gemma":[0.000184545,0.0001218521,0.00005525369,0.0006149305,0.0002075835,0.001505279,0.0001529641,0.0002266547,8.176833e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008638437,"about_ca_system_score_gemma":0.0001134846,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008992138,"about_ca_topic_score_gemma":0.00004755835,"domain_scores_codex":[0.9984969,0.000006165333,0.000331538,0.0003406016,0.0004304771,0.000394305],"domain_scores_gemma":[0.9992358,0.00003537586,0.0002527813,0.0001061526,0.0003292636,0.00004059062],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000192667,0.00006283337,0.01363837,0.00003401939,0.000009019092,0.00000461987,0.00002551896,0.000179516,0.00009658147,0.002023079,0.0008093047,0.9830979],"study_design_scores_gemma":[0.001186261,0.0001006962,0.3512358,0.0003145068,0.0001165498,0.0000166931,0.000628597,0.5994081,0.00003187745,0.007861096,0.03886668,0.0002331202],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6511673,0.0005295717,0.3436354,0.00075398,0.002696938,0.0003969106,0.000007227933,0.00006161272,0.0007509548],"genre_scores_gemma":[0.9080103,0.000400493,0.08870977,0.000191837,0.002565788,0.00002872878,0.000008331896,0.00001664657,0.00006812148],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9828647,"threshold_uncertainty_score":0.9996737,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01327503223081951,"score_gpt":0.2942720290235957,"score_spread":0.2809969967927762,"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."}}