{"id":"W2768301016","doi":"10.1016/j.jedc.2017.11.002","title":"Moment matching machine learning methods for risk management of large variable annuity portfolios","year":2017,"lang":"en","type":"article","venue":"Journal of Economic Dynamics and Control","topic":"Insurance, Mortality, Demography, Risk Management","field":"Social Sciences","cited_by":45,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Portfolio; Computer science; Liberian dollar; Valuation (finance); Monte Carlo method; Econometrics; Variable (mathematics); Project portfolio management; Machine learning; Actuarial science; Economics; Artificial intelligence; Mathematical optimization; Mathematics; Finance; Project management; Statistics","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":[0.007155244,0.0001265598,0.0004592662,0.000125884,0.0008710566,0.0002044233,0.0004155325,0.00005983804,0.00002869324],"category_scores_gemma":[0.0000507872,0.0001211018,0.0002122257,0.00002543236,0.0001022871,0.0003375186,0.00008996637,0.0001900931,6.075944e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000158982,"about_ca_system_score_gemma":0.0000505669,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001186937,"about_ca_topic_score_gemma":0.0008520284,"domain_scores_codex":[0.9985895,0.0001996796,0.0006146774,0.000166412,0.0001281337,0.0003016081],"domain_scores_gemma":[0.997592,0.0001219845,0.001859474,0.0002226611,0.0000988171,0.0001050131],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002173717,0.0001554677,0.1802659,0.0001236642,0.001489436,0.000008715678,0.0008537994,0.00322248,0.00001126962,0.7262779,0.00005820982,0.08731582],"study_design_scores_gemma":[0.0122437,0.0005221092,0.1759057,0.0002335464,0.001654415,0.000007956465,0.006943584,0.4317499,0.000006944183,0.3059398,0.06409568,0.0006967701],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3011706,0.00106044,0.6758654,0.0007361207,0.001353161,0.000838587,0.0001839299,0.00001366867,0.01877809],"genre_scores_gemma":[0.9682624,0.002874159,0.0281295,0.00004456774,0.0001752824,0.00001113353,0.000002105744,0.00001341407,0.0004874534],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6670918,"threshold_uncertainty_score":0.6699551,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01035025769941447,"score_gpt":0.3418259321824908,"score_spread":0.3314756744830764,"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."}}