{"id":"W4312127937","doi":"10.3390/jrfm15120597","title":"The Value of Open Banking Data for Application Credit Scoring: Case Study of a Norwegian Bank","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":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Norges Forskningsråd","keywords":"Credit score; Profitability index; Computer science; Database transaction; Norwegian; Credit rating; Transaction data; Credit history; Predictive modelling; Business; Machine learning; Artificial intelligence; Finance; Database","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":[0.001742265,0.0001007747,0.0002471184,0.0001731508,0.000721422,0.0001375305,0.0008395411,0.00001838346,0.000006827314],"category_scores_gemma":[0.0001057048,0.00007938333,0.00005641524,0.0003498626,0.00003409547,0.0005763489,0.0014938,0.0001383894,1.619337e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002378629,"about_ca_system_score_gemma":0.00002258882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001602915,"about_ca_topic_score_gemma":0.000280161,"domain_scores_codex":[0.9987386,0.00002582193,0.0005931107,0.0001886065,0.0003207626,0.0001330316],"domain_scores_gemma":[0.9982323,0.00006285244,0.001173501,0.0003677795,0.000154789,0.000008747642],"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":[0.00106998,0.001492611,0.04776831,0.0004833072,0.0001429037,0.0002064182,0.0007348729,0.002143522,0.0000254566,0.08177046,0.007360529,0.8568016],"study_design_scores_gemma":[0.007468751,0.001078894,0.2819921,0.0001780328,0.001673223,0.00009298923,0.02573071,0.01507816,0.000008981719,0.01986295,0.6464168,0.0004183073],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9725702,0.0002674158,0.02447461,0.0001061836,0.0007793736,0.001262179,0.0001012267,0.00000630826,0.0004324909],"genre_scores_gemma":[0.9989623,0.0001260547,0.0002437499,0.00003682172,0.0005330073,0.00005723734,0.00001439216,0.00001068955,0.00001574074],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8563833,"threshold_uncertainty_score":0.5548668,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02584519731767793,"score_gpt":0.2669887423584239,"score_spread":0.241143545040746,"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."}}