{"id":"W4304207555","doi":"10.3390/jrfm16030159","title":"Dissecting the Explanatory Power of ESG Features on Equity Returns by Sector, Capitalization, and Year with Interpretable Machine Learning","year":2023,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Financial Markets and Investment Strategies","field":"Economics, Econometrics and Finance","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Université Paris-Saclay; BNP Paribas Cardif","keywords":"Equity (law); Explanatory power; Econometrics; Market capitalization; Capitalization; Benchmark (surveying); Gradient boosting; Economics; Corporate governance; Financial economics; Predictive power; Boosting (machine learning); Business; Computer science; Random forest; Machine learning; Finance; Stock market","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00561237,0.0007937506,0.00046544,0.002549327,0.0002721821,0.001713455,0.0006275232,0.0007949871,0.002755978],"category_scores_gemma":[0.0174376,0.0001130532,0.0008105762,0.001666233,0.0008502278,0.001498247,0.0009852692,0.001110056,0.000471744],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000322637,"about_ca_system_score_gemma":0.0003193195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002109565,"about_ca_topic_score_gemma":0.001582618,"domain_scores_codex":[0.9989755,0.0004506771,0.00006507614,0.0001739358,0.0001807567,0.0001540879],"domain_scores_gemma":[0.9800186,0.0147909,0.002206658,0.001816345,0.0007243801,0.0004432806],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003787478,0.0003381039,0.8432808,0.00007640801,0.0005209409,0.0004508348,0.0003083214,0.08347049,0.002292912,0.007961419,0.002015676,0.0589054],"study_design_scores_gemma":[0.0000530368,0.0002883053,0.5548063,0.00006830398,0.0001705361,0.0001311972,0.0003769346,0.4163831,0.003232213,0.02263951,0.001799144,0.00005152577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9898492,0.0001781567,0.007864732,0.000342854,0.00001803698,0.000009937302,0.0004248083,0.00006920152,0.001243],"genre_scores_gemma":[0.9983501,0.00002929333,0.0008752972,0.00002255882,0.00002219799,0.000004000192,0.0005272562,0.0000102941,0.0001589037],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00561237,"threshold_uncertainty_score":0.02968144,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009812140842958403,"score_gpt":0.2026113281809548,"score_spread":0.1927991873379964,"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."}}