{"id":"W4416592923","doi":"10.3390/jrfm18120662","title":"A Two-Stage Machine Learning Approach to Bankruptcy Prediction: Integrating Full-Feature Modeling and Optimized Feature Selection","year":2025,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Financial Distress and Bankruptcy Prediction","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Feature selection; Random forest; Ensemble learning; Decision tree; Gradient boosting; Bankruptcy prediction; Ensemble forecasting; Feature (linguistics); Overfitting; Supervised learning","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":[0.0007009642,0.0002529187,0.0003743237,0.0006504793,0.0005816264,0.0003832208,0.000140135,0.0001225336,0.00000591722],"category_scores_gemma":[0.0001979119,0.0002137757,0.0001108046,0.0007691163,0.00002696109,0.0006808022,0.0002009911,0.0006910817,0.000001259199],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005838393,"about_ca_system_score_gemma":0.00002081307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001925917,"about_ca_topic_score_gemma":0.00007261462,"domain_scores_codex":[0.9987039,0.00003023294,0.0004151188,0.0003238039,0.0002724052,0.0002545398],"domain_scores_gemma":[0.9992743,0.00001888446,0.0003531323,0.00009640405,0.000226561,0.00003075924],"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":[0.003733024,0.0005334349,0.04179718,0.001752871,0.0002659006,0.00006314043,0.0008743943,0.2492805,0.0003270091,0.155724,0.00962467,0.5360239],"study_design_scores_gemma":[0.004174475,0.0001589364,0.02807988,0.000757904,0.0006591819,0.00002376593,0.001371785,0.8438258,0.000006652479,0.002527952,0.1179938,0.0004198344],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2294889,0.001911188,0.7558875,0.0005774029,0.0009703463,0.0005709336,0.00001839387,0.000105722,0.01046955],"genre_scores_gemma":[0.9776939,0.001055786,0.01851689,0.000451893,0.001326412,0.00002373874,0.00002470214,0.00002391812,0.0008828067],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7482049,"threshold_uncertainty_score":0.8717521,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005954190856797798,"score_gpt":0.2053921880877767,"score_spread":0.1994379972309789,"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."}}