{"id":"W4398135784","doi":"10.3390/jrfm17050211","title":"Risk Characterization of Firms with ESG Attributes Using a Supervised Machine Learning Method","year":2024,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Risk Management in Financial Firms","field":"Business, Management and Accounting","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Characterization (materials science); Artificial intelligence; Computer science; Machine learning; Supervised learning; Business; Materials science; Artificial neural network; Nanotechnology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001350882,0.0002867531,0.0005112208,0.0009105629,0.0002654565,0.0003368128,0.00025353,0.00007963969,0.00003229978],"category_scores_gemma":[0.0001662929,0.0002220921,0.0001694781,0.001125689,0.00006091519,0.00128746,0.0002406413,0.0004506987,0.000008698946],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004685891,"about_ca_system_score_gemma":0.00002288847,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003798717,"about_ca_topic_score_gemma":0.00002858936,"domain_scores_codex":[0.9981334,0.00005841107,0.0007413964,0.0003037835,0.0004630051,0.0003000473],"domain_scores_gemma":[0.9985643,0.00008295871,0.0009348036,0.0001695929,0.0002233078,0.00002501462],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0006790675,0.0002073883,0.2593437,0.001756414,0.0002919141,0.0005246057,0.00049948,0.003297027,0.0005219962,0.01896386,0.0002355602,0.713679],"study_design_scores_gemma":[0.003083521,0.0004217964,0.4719197,0.001947729,0.003218836,0.00006056232,0.0004391977,0.1192854,0.0001968429,0.008758888,0.3896962,0.0009713458],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6126637,0.0008091963,0.3852071,0.00009656334,0.00054487,0.0003017347,0.00001548766,0.00004945296,0.0003118975],"genre_scores_gemma":[0.9856147,0.003710155,0.009315229,0.0001019677,0.001041987,0.000006174989,0.00002463522,0.00005478326,0.0001304075],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7127076,"threshold_uncertainty_score":0.9056652,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0118957316889476,"score_gpt":0.2241467199144215,"score_spread":0.2122509882254739,"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."}}