{"id":"W2947630478","doi":"10.1109/access.2019.2919727","title":"Automatically Detecting Peer-to-Peer Lending Intermediary Risk—Top Management Team Profile Textual Features Perspective","year":2019,"lang":"en","type":"article","venue":"IEEE Access","topic":"FinTech, Crowdfunding, Digital Finance","field":"Business, Management and Accounting","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Higher Education Discipline Innovation Project; Ministry of Education, India; National Social Science Fund of China; National Natural Science Foundation of China; McGill University","keywords":"Computer science; Artificial intelligence; Classifier (UML); Risk management; Natural language processing; Perspective (graphical); Knowledge management; Machine learning; Finance; Business","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008209376,0.0004688404,0.000437261,0.0007969025,0.0003111924,0.002118265,0.00138493,0.0001497785,0.0003734236],"category_scores_gemma":[0.0009738213,0.0004460373,0.0001765152,0.001183198,0.00008905896,0.003667122,0.001119751,0.0005930591,0.00313616],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003230864,"about_ca_system_score_gemma":0.00002756865,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006200675,"about_ca_topic_score_gemma":0.0001528169,"domain_scores_codex":[0.9967067,0.00002039312,0.0004864355,0.0009379314,0.001013724,0.000834791],"domain_scores_gemma":[0.998202,0.0001464609,0.0004284627,0.0005785627,0.00059676,0.0000477354],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0006627113,0.0008651348,0.3325723,0.00284986,0.0008279705,0.0002891912,0.002726993,0.001188636,0.004032882,0.106304,0.3872539,0.1604263],"study_design_scores_gemma":[0.004636509,0.0003244496,0.7544069,0.003182618,0.0006026037,0.00006458558,0.02040628,0.0195824,0.01380737,0.02721419,0.1504313,0.005340799],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6919442,0.0000272703,0.003065107,0.0009832317,0.001843952,0.001357593,0.0000232494,0.0006362048,0.3001192],"genre_scores_gemma":[0.9830453,0.000002722752,0.001228095,0.001060164,0.001080368,0.0001466414,0.00001919291,0.000103793,0.01331371],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4218346,"threshold_uncertainty_score":0.9997991,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01219611242789934,"score_gpt":0.2757399790230653,"score_spread":0.2635438665951659,"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."}}