{"id":"W4407688788","doi":"10.32996/jbms.2023.5.6.13","title":"Machine Learning-Based Risk Prediction Model for Loan Applications: Enhancing Decision-Making and Default Prevention","year":2023,"lang":"en","type":"article","venue":"Journal of Business and Management Studies","topic":"Insurance and Financial Risk Management","field":"Economics, Econometrics and Finance","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Loan; Computer science; Machine learning; Credit risk; Predictive modelling; Actuarial science; Artificial intelligence; Business; Risk analysis (engineering); Finance","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":[0.002387033,0.0006921039,0.001024682,0.0007525202,0.0004361198,0.001443057,0.001293096,0.001303299,0.001956507],"category_scores_gemma":[0.00690495,0.0004161183,0.0006251989,0.000579589,0.0004378694,0.001536715,0.0007745391,0.002080534,0.0005557426],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001132479,"about_ca_system_score_gemma":0.001842301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008616053,"about_ca_topic_score_gemma":0.008625239,"domain_scores_codex":[0.9994222,0.000196269,0.00004529838,0.0001437933,0.0001010881,0.00009148238],"domain_scores_gemma":[0.9971552,0.001780864,0.0002623403,0.0001314067,0.0005405173,0.000129736],"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":[0.000111502,0.0002178325,0.006700322,0.00005601336,0.00004765394,0.000109907,0.00008104384,0.9206499,0.0007919277,0.005364843,0.002093897,0.06377514],"study_design_scores_gemma":[0.000001927349,0.000009815319,0.0001596246,0.00000609059,0.000003245787,0.000005466405,0.000003967238,0.9980037,0.0001007866,0.001602166,0.0001011825,0.000002090073],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2139134,0.001368308,0.773691,0.003697735,0.0001311285,0.0002049851,0.0004278764,0.001141202,0.005424402],"genre_scores_gemma":[0.9220671,0.0004359764,0.07361395,0.0003074078,0.00008106725,0.0001258435,0.0003535419,0.00003376918,0.00298124],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008616053,"threshold_uncertainty_score":0.01713181,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03065219126867584,"score_gpt":0.2744454330430675,"score_spread":0.2437932417743916,"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."}}