{"id":"W4414256523","doi":"10.21203/rs.3.rs-7550376/v1","title":"Smart classify and optimize for portfolio construction - a differentiable quadratic programming approach","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Leadership, Behavior, and Decision-Making Studies","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Quadratic programming; Support vector machine; Selection (genetic algorithm); Differentiable function; Quadratic equation; Hyperplane; Portfolio; Asset allocation","routes":{"ca_aff":true,"ca_fund":true,"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":[0.005699559,0.001275713,0.002968107,0.001448373,0.0007755458,0.002319962,0.002504023,0.002666946,0.006383715],"category_scores_gemma":[0.01701259,0.001357843,0.001386224,0.001624955,0.00158789,0.003988994,0.002662448,0.004187906,0.001088012],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001511746,"about_ca_system_score_gemma":0.00240959,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003281824,"about_ca_topic_score_gemma":0.003592242,"domain_scores_codex":[0.998199,0.0009522042,0.00007598243,0.0002671207,0.0003301313,0.0001755121],"domain_scores_gemma":[0.9934562,0.004485901,0.0003758231,0.0006227805,0.0007473429,0.0003120039],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001144826,0.0001849011,0.001573049,0.0001466025,0.00009195907,0.00005733818,0.00008366423,0.7707394,0.0005489035,0.1165616,0.007171971,0.1027261],"study_design_scores_gemma":[0.000005568687,0.00001731194,0.00006558342,0.000007133431,0.000003747699,0.000004515909,0.0000053382,0.9798742,0.00008028738,0.01962064,0.0003129192,0.000002807663],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007281463,0.0001451861,0.9904821,0.0004301555,0.0000297932,0.00004564861,0.00006785743,0.0001638446,0.001353842],"genre_scores_gemma":[0.2823526,0.0004478822,0.7038444,0.0004292823,0.000247315,0.0004634361,0.0007235949,0.000556891,0.0109346],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006383715,"threshold_uncertainty_score":0.03014249,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3418591823469936,"score_gpt":0.5103792845587988,"score_spread":0.1685201022118051,"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."}}