{"id":"W4410734606","doi":"10.1002/for.3284","title":"Default Prediction Framework With Optimal Feature Set and Matching Ratio","year":2025,"lang":"en","type":"article","venue":"Journal of Forecasting","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"National Natural Science Foundation of China","keywords":"Feature (linguistics); Matching (statistics); Computer science; Set (abstract data type); Pattern recognition (psychology); Artificial intelligence; Econometrics; Mathematics; Statistics","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":[0.0004217395,0.00007978655,0.0001269987,0.0001525509,0.000132113,0.0002086642,0.0002987227,0.00006727083,9.190893e-7],"category_scores_gemma":[0.0001744862,0.0000603758,0.00002328637,0.0003026786,0.000025821,0.0008365639,0.00008105297,0.0003767909,2.380626e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004495844,"about_ca_system_score_gemma":0.00008044873,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001462505,"about_ca_topic_score_gemma":7.333048e-7,"domain_scores_codex":[0.999304,0.00003257498,0.0002334067,0.0001256821,0.0001894698,0.0001148579],"domain_scores_gemma":[0.9991438,0.0001428421,0.0003223034,0.0001704642,0.0001809229,0.00003965778],"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":[0.0004280307,0.0001969734,0.0515462,0.0004710474,0.0004529501,0.0002977221,0.01150678,0.01559643,0.01955514,0.229866,0.03841371,0.631669],"study_design_scores_gemma":[0.001956358,0.001227779,0.05260691,0.005621728,0.0001170993,0.004175908,0.001188074,0.8312175,0.02935258,0.06178568,0.01010847,0.0006418728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0408996,0.0001054463,0.9572275,0.00122234,0.000147045,0.00006091531,0.000003393226,0.00005607625,0.0002776487],"genre_scores_gemma":[0.437691,0.00001052506,0.562067,0.00011841,0.00006183758,0.000001669081,0.000001084005,0.000003278542,0.00004521985],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8156211,"threshold_uncertainty_score":0.2462053,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01887874567049567,"score_gpt":0.2666547613807316,"score_spread":0.2477760157102359,"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."}}