{"id":"W7106312712","doi":"10.1016/j.ejor.2025.11.028","title":"A hybrid multi-layered ensemble model based on heterogeneous information network for small and medium-sized enterprise default prediction","year":2025,"lang":"en","type":"article","venue":"European Journal of Operational Research","topic":"Financial Distress and Bankruptcy Prediction","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"Southwestern University of Finance and Economics; National Social Science Fund of China; National Natural Science Foundation of China","keywords":"Boosting (machine learning); Gradient boosting; Decision tree; Artificial neural network; Construct (python library); Enterprise private network; Credit risk; Component (thermodynamics); Graph","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":[],"consensus_categories":[],"category_scores_codex":[0.00244909,0.0001133908,0.0001444128,0.0004111761,0.0004478242,0.0004872403,0.0001880252,0.00002699042,0.00001169734],"category_scores_gemma":[0.0007964787,0.00009709261,0.00007981247,0.0001904278,0.00004755223,0.000808711,0.00007586761,0.0002546684,0.00001531559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006061442,"about_ca_system_score_gemma":0.0001780077,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000104406,"about_ca_topic_score_gemma":0.00000931558,"domain_scores_codex":[0.9985662,0.00009714935,0.0005087763,0.0001347406,0.000465327,0.0002277967],"domain_scores_gemma":[0.9983148,0.0001214603,0.0001705108,0.0001053997,0.001261927,0.00002592155],"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":[0.003670784,0.0003092773,0.002112942,0.0002819669,0.00007711868,0.00003438086,0.00006231006,0.8976074,0.001614557,0.005508154,0.03589561,0.0528255],"study_design_scores_gemma":[0.002572322,0.0001247213,0.01132826,0.000251085,0.00002154904,0.000004656582,0.00001896585,0.9735998,0.0001462482,0.0006014985,0.01125155,0.00007934236],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2128386,0.0001122771,0.7785195,0.002688534,0.0006441968,0.0006893725,0.0000634584,0.00003447821,0.00440968],"genre_scores_gemma":[0.9942715,0.00002692961,0.003693219,0.0009763181,0.0007632439,0.00001741052,0.0001062532,0.00001394924,0.0001312408],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7814329,"threshold_uncertainty_score":0.469847,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0472078277216731,"score_gpt":0.2908680964868873,"score_spread":0.2436602687652142,"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."}}