{"id":"W3028645543","doi":"10.1016/j.eswa.2020.114486","title":"Super-app behavioral patterns in credit risk models: Financial, statistical and regulatory implications","year":2020,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"FinTech, Crowdfunding, Digital Finance","field":"Business, Management and Accounting","cited_by":62,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"Canada Excellence Research Chairs, Government of Canada","keywords":"Computer science; Boosting (machine learning); Gradient boosting; Credit risk; Contrast (vision); Finance; Econometrics; Machine learning; Artificial intelligence; Business; Random forest; Economics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001119642,0.0002356661,0.0002869166,0.0001391656,0.0002356592,0.0003085078,0.0002689699,0.00009737365,0.00001721184],"category_scores_gemma":[0.00004495787,0.0002252427,0.00003019258,0.0005531455,0.000119457,0.0009338316,0.0001307291,0.0002024531,0.00008632282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006140695,"about_ca_system_score_gemma":0.00004937936,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002146785,"about_ca_topic_score_gemma":0.0002943096,"domain_scores_codex":[0.9984601,0.00001088802,0.0004250766,0.0005853179,0.0001996607,0.000319018],"domain_scores_gemma":[0.9991767,0.00005334266,0.0002029936,0.0003914786,0.0001209367,0.00005452751],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007398106,0.0004798952,0.2319602,0.0004422205,0.00002434914,0.00001503402,0.0008140926,0.0007586816,0.0005319386,0.724583,0.03060505,0.009711517],"study_design_scores_gemma":[0.003364833,0.0002092819,0.4112571,0.0005963108,0.0001696895,0.00004993389,0.003692818,0.09113478,0.00007975438,0.01213092,0.4746163,0.002698247],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.345451,0.001042296,0.6426039,0.002336283,0.0001283729,0.003028127,0.0005114072,0.0006291228,0.00426953],"genre_scores_gemma":[0.9954262,0.00003405465,0.000855851,0.0004544031,0.0005806455,0.002397423,0.0001494144,0.00005055601,0.00005143895],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7124521,"threshold_uncertainty_score":0.9185129,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03047966361103665,"score_gpt":0.2449706552683956,"score_spread":0.214490991657359,"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."}}