{"id":"W4223893383","doi":"10.48550/arxiv.2204.06122","title":"On the dynamics of credit history and social interaction features, and their impact on creditworthiness assessment performance","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Financial Distress and Bankruptcy Prediction","field":"Business, Management and Accounting","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Comisión Nacional de Investigación Científica y Tecnológica; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; European Commission","keywords":"Loan; Predictive power; Credit risk; Credit history; Value (mathematics); Credit score; Actuarial science; Portfolio; Credit rating; Business; Computer science; Finance; Machine learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001040237,0.0004155286,0.0002682817,0.002164559,0.0003200404,0.0008858636,0.0002946701,0.000515788,0.001781638],"category_scores_gemma":[0.005245702,0.0001122362,0.0003066495,0.001528444,0.0002936961,0.00103858,0.0005465937,0.0007281448,0.0005964541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004371352,"about_ca_system_score_gemma":0.0002627646,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0116344,"about_ca_topic_score_gemma":0.01494399,"domain_scores_codex":[0.9995635,0.0001156128,0.00003219049,0.0001505284,0.00008198161,0.00005619504],"domain_scores_gemma":[0.9961051,0.002004156,0.0008664248,0.0004149875,0.0003836693,0.0002256855],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001660988,0.0002576397,0.9175712,0.00006175351,0.0001382383,0.0001670579,0.0002434989,0.01616058,0.001621165,0.001121012,0.004130801,0.05836084],"study_design_scores_gemma":[0.000004625601,0.00008567004,0.8077329,0.00003605882,0.00005366905,0.000135943,0.0002724949,0.1862787,0.0009593825,0.001751891,0.002662343,0.00002626213],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9856738,0.0004957354,0.005517822,0.0005186282,0.00003816366,0.00002048261,0.005417476,0.00009310675,0.002224826],"genre_scores_gemma":[0.9932435,0.0001977234,0.001436541,0.00002720316,0.00003375868,0.00001303207,0.004245062,0.000006931903,0.0007962692],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0116344,"threshold_uncertainty_score":0.0231334,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03484912711335453,"score_gpt":0.1865530448306737,"score_spread":0.1517039177173191,"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."}}