{"id":"W4385664847","doi":"10.1080/14697688.2023.2236148","title":"Distributionally robust end-to-end portfolio construction","year":2023,"lang":"en","type":"article","venue":"Quantitative Finance","topic":"Risk and Portfolio Optimization","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Portfolio; Computer science; Robustness (evolution); Ambiguity; Minimax; Portfolio optimization; Robust optimization; Mathematical optimization; Modern portfolio theory; End-to-end principle; Operations research; Artificial intelligence; Economics; Mathematics; Finance","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001527064,0.0001654949,0.000272709,0.0004438487,0.0003027243,0.0001639816,0.0004054546,0.00007729098,0.0005264952],"category_scores_gemma":[0.002564583,0.0001422815,0.0001045907,0.003908953,0.0002037742,0.0005022876,0.0000929466,0.00012339,0.004730256],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004748841,"about_ca_system_score_gemma":0.0001562363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003612124,"about_ca_topic_score_gemma":0.00002435497,"domain_scores_codex":[0.9972698,0.0001356182,0.0006098088,0.0005847706,0.00105926,0.0003407621],"domain_scores_gemma":[0.9977797,0.0007454834,0.0003102184,0.0003978066,0.0006710776,0.00009574896],"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":[0.00009874145,0.00004280653,0.02707213,0.000001926929,0.00001824433,0.00004543119,0.0005385009,0.1431603,0.0002008893,0.6187959,0.1359287,0.07409641],"study_design_scores_gemma":[0.0004098667,0.0002330884,0.4521818,0.00003309693,0.00001288498,0.00002364723,0.0009075711,0.03616215,0.0006156522,0.06379507,0.4451873,0.0004378617],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6065867,0.0001726395,0.3704032,0.002946162,0.00178497,0.0004298477,0.0007597054,0.0002418984,0.01667481],"genre_scores_gemma":[0.9366847,0.001010999,0.05006614,0.000248352,0.0001359661,0.00006271768,0.0003317361,0.00002432369,0.01143502],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5550009,"threshold_uncertainty_score":0.9960447,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1182543136914453,"score_gpt":0.3858309063248573,"score_spread":0.267576592633412,"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."}}