{"id":"W4401414508","doi":"10.2139/ssrn.4905824","title":"Stability-Weighted Ensemble Feature Importance for Financial Applications","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto; York University","funders":"","keywords":"Financial stability; Feature (linguistics); Stability (learning theory); Artificial intelligence; Pattern recognition (psychology); Computer science; Mathematics; Economics; Machine learning; Financial system; Philosophy","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":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0311144,0.0005562091,0.0009005867,0.0005816231,0.0005711048,0.000793662,0.002450949,0.0007302713,0.0001092698],"category_scores_gemma":[0.008334043,0.0004339633,0.0009861361,0.001118981,0.0001355915,0.0001220512,0.0009739352,0.009872646,0.00008746576],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002216525,"about_ca_system_score_gemma":0.01635877,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008777056,"about_ca_topic_score_gemma":0.0009717506,"domain_scores_codex":[0.9916083,0.0006094883,0.001441729,0.001542933,0.001669053,0.003128468],"domain_scores_gemma":[0.9927978,0.003026258,0.001186708,0.001515927,0.001239358,0.0002339755],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002564835,0.00009757359,0.001179903,0.00008291374,0.0002167564,0.000006109463,0.0002490859,0.00007156745,0.0001689688,0.177511,0.01862797,0.8015317],"study_design_scores_gemma":[0.0002873645,0.0001352235,0.0002423315,0.00006074987,0.0001264297,0.0002660707,0.0002859667,0.001617551,0.0001253775,0.9057624,0.09069277,0.0003977562],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05419067,0.03695885,0.8901445,0.006373424,0.003799844,0.002875178,0.000269018,0.0002325651,0.005155939],"genre_scores_gemma":[0.6822733,0.00658754,0.2264716,0.0008231501,0.01602233,0.003752057,0.0001968188,0.0005808283,0.06329232],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8011339,"threshold_uncertainty_score":0.9998112,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06045018118074068,"score_gpt":0.385143611186587,"score_spread":0.3246934300058463,"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."}}