{"id":"W3048514459","doi":"10.3390/jrfm13080180","title":"Use of Machine Learning Techniques to Create a Credit Score Model for Airtime Loans","year":2020,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Financial Distress and Bankruptcy Prediction","field":"Business, Management and Accounting","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Default; Loan; Microfinance; Logistic regression; Profitability index; Credit score; Random forest; Econometrics; Business; Machine learning; Actuarial science; Computer science; Artificial intelligence; Economics; Finance","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00136994,0.0006702144,0.0006047877,0.0008934814,0.0003972657,0.001037814,0.0006784953,0.0007560296,0.001926245],"category_scores_gemma":[0.003478971,0.0002528953,0.0008587856,0.0007419265,0.0003002165,0.0007979247,0.0004197681,0.001426298,0.0007453258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007276835,"about_ca_system_score_gemma":0.0009907858,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01371571,"about_ca_topic_score_gemma":0.01053115,"domain_scores_codex":[0.999716,0.0001046062,0.00002506328,0.00005188119,0.00006684281,0.00003564678],"domain_scores_gemma":[0.9989269,0.0007112321,0.00009031456,0.00004136882,0.0002068141,0.00002336587],"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":[0.00005022091,0.00008073103,0.005213846,0.00003666379,0.00004159503,0.0001029727,0.00005301554,0.9068062,0.001138429,0.002258083,0.001024315,0.08319385],"study_design_scores_gemma":[0.000002586022,0.00001169905,0.0004716897,0.000005144743,0.00000398396,0.00001308461,0.000005230598,0.9982154,0.0002181421,0.0008444785,0.0002048136,0.000003820245],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1320249,0.0004094916,0.8621947,0.0005027897,0.00007621651,0.000135891,0.0003209285,0.001198449,0.003136629],"genre_scores_gemma":[0.8444279,0.0003360669,0.1494874,0.00008132779,0.00006452619,0.0001873064,0.0006864727,0.00007497714,0.004653964],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01371571,"threshold_uncertainty_score":0.02727175,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0250419681264919,"score_gpt":0.2159378333126277,"score_spread":0.1908958651861358,"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."}}