{"id":"W3175426713","doi":"10.3905/jfds.2021.1.070","title":"Weak Supervision and Black-Litterman for Automated ESG Portfolio Construction","year":2021,"lang":"en","type":"article","venue":"The Journal of Financial Data Science","topic":"Financial Markets and Investment Strategies","field":"Economics, Econometrics and Finance","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Black–Litterman model; Computer science; Portfolio; Portfolio optimization; Key (lock); Project portfolio management; Consistency (knowledge bases); Machine learning; Artificial intelligence; Replicating portfolio; Business; Engineering; Finance; Systems engineering; Project management","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":[0.007079773,0.000973317,0.00101055,0.001450437,0.0006395513,0.001802839,0.001406054,0.001271725,0.003921616],"category_scores_gemma":[0.02114762,0.0007408603,0.0008936828,0.001377893,0.001310151,0.003670182,0.00248763,0.002645613,0.001068469],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000993273,"about_ca_system_score_gemma":0.001573477,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002023256,"about_ca_topic_score_gemma":0.002067052,"domain_scores_codex":[0.9964611,0.001992216,0.000220697,0.0005156272,0.0006822695,0.0001280289],"domain_scores_gemma":[0.9926798,0.004252049,0.0008083797,0.00118358,0.0008750493,0.0002010534],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000266053,0.0003914433,0.005918832,0.0001749037,0.0001596226,0.0002494018,0.0004553759,0.344037,0.004937292,0.1606153,0.007793103,0.4750016],"study_design_scores_gemma":[0.00001193588,0.00003206205,0.0003016135,0.00001045824,0.000006348295,0.00002022321,0.0000167345,0.9482459,0.001315199,0.04877983,0.001249084,0.00001054999],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009140961,0.00006881256,0.9885565,0.0003269747,0.00002971362,0.00004178273,0.00006117509,0.0004774066,0.001296706],"genre_scores_gemma":[0.2977774,0.000148642,0.6974767,0.0003383223,0.0001412536,0.0001768298,0.0004669247,0.0002023014,0.00327154],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007079773,"threshold_uncertainty_score":0.03744191,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04686496758925521,"score_gpt":0.2650234908089764,"score_spread":0.2181585232197212,"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."}}