{"id":"W3157935082","doi":"10.1007/s00500-021-05833-y","title":"An adaptive sequential-filtering learning system for credit risk modeling","year":2021,"lang":"en","type":"article","venue":"Soft Computing","topic":"Financial Distress and Bankruptcy Prediction","field":"Business, Management and Accounting","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Wilfrid Laurier University; Concordia University","funders":"","keywords":"Credit risk; Computer science; Machine learning; Partition (number theory); Support vector machine; Risk management; Filter (signal processing); Structural risk minimization; Artificial intelligence; Data mining; Finance; Mathematics","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":[0.0004549416,0.0001770094,0.0002244577,0.0000936846,0.0008633732,0.0004580129,0.0001478918,0.00008109158,0.00001133401],"category_scores_gemma":[0.000169531,0.0001963252,0.0001238975,0.0002472537,0.00001254927,0.0007006767,0.0001590935,0.0002164874,0.00002075625],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000612763,"about_ca_system_score_gemma":0.00003143282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004493397,"about_ca_topic_score_gemma":0.00003773198,"domain_scores_codex":[0.9986767,0.00002586561,0.0003249373,0.0004263476,0.000187772,0.0003584075],"domain_scores_gemma":[0.999159,0.00004582288,0.0002526181,0.0001694911,0.0003568893,0.00001615418],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008273609,0.00006060384,0.005865324,0.0006238828,0.00005826018,0.00003203572,0.00020427,0.9162093,0.003118502,0.01866897,0.0000970183,0.05497905],"study_design_scores_gemma":[0.000378349,0.00001994351,0.000568948,0.0002830819,0.00007552952,0.000003790952,0.001513002,0.9953805,0.0001762042,0.0004140624,0.0009611791,0.0002254354],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3736656,0.00007496627,0.6236736,0.00001418511,0.0009269209,0.0001163239,0.000005621745,0.0004053916,0.00111736],"genre_scores_gemma":[0.9919487,0.000002105207,0.003416663,0.0000577633,0.004386789,0.00001013873,0.0001134752,0.00004222147,0.00002209489],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.620257,"threshold_uncertainty_score":0.8005909,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02477184167103155,"score_gpt":0.2333861576789779,"score_spread":0.2086143160079464,"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."}}