{"id":"W2911455822","doi":"10.3390/su11030699","title":"An Empirical Comparison of Machine-Learning Methods on Bank Client Credit Assessments","year":2019,"lang":"en","type":"article","venue":"Sustainability","topic":"Financial Distress and Bankruptcy Prediction","field":"Business, Management and Accounting","cited_by":141,"is_retracted":false,"has_abstract":true,"ca_institutions":"Microsoft (Canada)","funders":"National Research Foundation of Korea; Chungbuk National University; National Research Foundation","keywords":"Machine learning; Artificial intelligence; Computer science; Random forest; Benchmark (surveying); Support vector machine; Feature selection; Artificial neural network; Feature engineering; Gradient boosting; Deep 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":[0.03592633,0.000782904,0.0007842148,0.004792453,0.000499781,0.002125401,0.001247616,0.001706429,0.001619939],"category_scores_gemma":[0.1024795,0.0002510948,0.0008416516,0.005074846,0.001052687,0.002815432,0.001464431,0.002128556,0.001123593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001960042,"about_ca_system_score_gemma":0.0009107731,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006756119,"about_ca_topic_score_gemma":0.005543431,"domain_scores_codex":[0.9836945,0.009525809,0.0008351687,0.001139777,0.004227862,0.0005769433],"domain_scores_gemma":[0.8051322,0.161669,0.008794356,0.007606139,0.0144155,0.002382804],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001493198,0.0008070018,0.7383468,0.0003788988,0.0005130413,0.0001588306,0.0008161968,0.1039586,0.0004423528,0.003726171,0.009676738,0.1396822],"study_design_scores_gemma":[0.00005327331,0.0004696937,0.5952768,0.0002490623,0.0000747425,0.000228712,0.0009622701,0.3951913,0.001049065,0.003326795,0.003044358,0.00007407814],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9708564,0.004892839,0.01390502,0.0009095048,0.0001186571,0.0001088594,0.001849158,0.0003699273,0.006989641],"genre_scores_gemma":[0.9944268,0.000412561,0.003006716,0.00005568528,0.00005637592,0.00004452792,0.001241439,0.00002819907,0.0007276182],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03592633,"threshold_uncertainty_score":0.1899989,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02764923030033414,"score_gpt":0.3990697382803922,"score_spread":0.371420507980058,"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."}}