{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002140728,0.00009543887,0.0002533264,0.0001410056,0.0003417104,0.0001648257,0.0006982362,0.00004362486,0.00003165716],"category_scores_gemma":[0.0009828208,0.00007604529,0.00003842195,0.0004427261,0.0006802574,0.001640127,0.0002378376,0.0001181318,0.000007321407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003494509,"about_ca_system_score_gemma":0.0003242787,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003265714,"about_ca_topic_score_gemma":0.000009460065,"domain_scores_codex":[0.9988672,0.00001884817,0.0005661655,0.0002336785,0.00008582218,0.0002283285],"domain_scores_gemma":[0.9987918,0.00007529268,0.0004694474,0.0004205396,0.0001728253,0.00007010835],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0001579579,0.0001190994,0.01273421,0.00007865409,0.0000218117,0.00002809497,0.0006207854,0.00006223721,0.002704868,0.9310921,0.03703668,0.01534352],"study_design_scores_gemma":[0.001710989,0.0005540705,0.6460899,0.0001691136,0.00005589017,0.0009037053,0.0006339555,0.02886279,0.001470857,0.132927,0.1860982,0.0005235176],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9846805,0.002022293,0.004862892,0.001913486,0.001357941,0.0001739076,0.0003110121,0.00002087158,0.004657081],"genre_scores_gemma":[0.9924542,0.002249099,0.004498155,0.0004102875,0.0002607215,0.000001089996,0.00001581254,0.00000855494,0.0001021303],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7981651,"threshold_uncertainty_score":0.3101037,"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."}}