{"id":"W4310148203","doi":"10.3390/jrfm15120556","title":"Explainable AI for Credit Assessment in Banks","year":2022,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Financial Distress and Bankruptcy Prediction","field":"Business, Management and Accounting","cited_by":88,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Interpretability; Logistic regression; Credit risk; Computer science; Econometrics; Actuarial science; Artificial intelligence; Machine learning; Business; Economics","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":[0.0009436565,0.0001228757,0.0002396768,0.000455146,0.0003911139,0.0001177724,0.0001805229,0.00003150467,0.00006770925],"category_scores_gemma":[0.00005470079,0.0001181895,0.0001064379,0.0003546221,0.00002055031,0.0005663118,0.0002275229,0.0003121224,0.000001404565],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009730677,"about_ca_system_score_gemma":0.00002921296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001905754,"about_ca_topic_score_gemma":0.00005802412,"domain_scores_codex":[0.9988359,0.00001474258,0.0004420542,0.0001642743,0.0003119603,0.0002311058],"domain_scores_gemma":[0.9993725,0.00002526986,0.0004052735,0.00009192123,0.00009315536,0.00001180887],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0008835135,0.0007384458,0.08106758,0.0004945765,0.00003209725,0.0002431336,0.0002172958,0.003826936,0.0000166489,0.2756631,0.05314801,0.5836687],"study_design_scores_gemma":[0.001807432,0.0001213565,0.2998295,0.00004014797,0.00008563643,0.000003972074,0.0005903356,0.001730678,0.000001272036,0.02170943,0.6739361,0.0001442276],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8497571,0.001158221,0.1296345,0.001866908,0.005565944,0.001388695,0.00008075777,0.00005382998,0.01049401],"genre_scores_gemma":[0.997098,0.0002268974,0.00065278,0.0007051057,0.001077315,0.00008419801,0.00001157598,0.00001370425,0.0001304528],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.620788,"threshold_uncertainty_score":0.4819628,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007220187705390144,"score_gpt":0.2202542175043633,"score_spread":0.2130340297989732,"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."}}