{"id":"W7161307961","doi":"10.1145/3800000.3800105","title":"Machine Learning for Corporate Default Risk: Improving Prediction Accuracy in an Era of Globalization and Digitalization","year":2025,"lang":"","type":"article","venue":"","topic":"Financial Distress and Bankruptcy Prediction","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Interpretability; Random forest; Credit risk; Gradient boosting; Financial risk; Predictive modelling; Predictive power; Financial risk management; Logistic regression; Boosting (machine learning)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002179426,0.0005584696,0.0006721174,0.001659284,0.0003028761,0.0009975857,0.0005849983,0.0008928686,0.001028341],"category_scores_gemma":[0.006231206,0.0001385913,0.0004358329,0.001049014,0.0002338578,0.001722065,0.000591632,0.001105915,0.0003742356],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005108205,"about_ca_system_score_gemma":0.000566027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006701295,"about_ca_topic_score_gemma":0.004920201,"domain_scores_codex":[0.9994967,0.0001734336,0.00003982135,0.0001105742,0.0001204294,0.00005908141],"domain_scores_gemma":[0.998276,0.001053995,0.0001824607,0.0001332563,0.0002766612,0.00007762459],"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":[0.000297072,0.0005008861,0.1475666,0.0001545942,0.0001511816,0.0001791582,0.0001394174,0.3213237,0.001382156,0.003488274,0.01004054,0.5147765],"study_design_scores_gemma":[0.000007066384,0.0000406343,0.009690059,0.00002786051,0.00001340395,0.00002437329,0.00003441945,0.9868795,0.0004692557,0.002250692,0.0005547873,0.000007884399],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7928793,0.008015058,0.1841896,0.00478705,0.0002760834,0.00009065747,0.0008459284,0.002025519,0.0068909],"genre_scores_gemma":[0.980629,0.0008502768,0.0170644,0.0001366328,0.00009780341,0.00002120026,0.0004654136,0.00001461812,0.0007205602],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006701295,"threshold_uncertainty_score":0.01332456,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01182047192751281,"score_gpt":0.2304991131904454,"score_spread":0.2186786412629325,"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."}}