{"id":"W4412125311","doi":"10.1080/10920277.2025.2517149","title":"Recurrent Neural Networks for Multivariate Loss Reserving and Risk Capital Analysis","year":2025,"lang":"en","type":"article","venue":"North American Actuarial Journal","topic":"Probability and Risk Models","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Shared Hierarchical Academic Research Computing Network; McMaster University","keywords":"Multivariate statistics; Multivariate analysis; Artificial neural network; Computer science; Econometrics; Artificial intelligence; Economics; Machine learning","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":[0.001014406,0.001000765,0.0006847506,0.0005397592,0.0002076567,0.000733106,0.001041351,0.0007189144,0.002013991],"category_scores_gemma":[0.003800948,0.0003821829,0.0006375801,0.0006256996,0.0004664644,0.001244969,0.0007309981,0.001910041,0.0004370446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001085147,"about_ca_system_score_gemma":0.0006382691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01133762,"about_ca_topic_score_gemma":0.009815261,"domain_scores_codex":[0.9997062,0.00008279748,0.00001952515,0.00007683427,0.00007172635,0.00004284161],"domain_scores_gemma":[0.9991605,0.0005002562,0.0001072683,0.00006563047,0.0001365396,0.0000297626],"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":[0.00004908591,0.00002999351,0.0009099888,0.00003170476,0.00003516932,0.0000495129,0.00002248517,0.9523906,0.0007039928,0.004818036,0.001163395,0.03979604],"study_design_scores_gemma":[7.683342e-7,0.000002611032,0.00005594049,0.000001786942,0.000001496578,0.000002554696,0.000001192269,0.998355,0.0001063526,0.00139725,0.00007359146,0.000001453465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05179348,0.001731736,0.9409492,0.0006539259,0.00009146435,0.00004154392,0.0004055493,0.001550499,0.002782752],"genre_scores_gemma":[0.8918092,0.001059024,0.09967823,0.0002483196,0.0001119885,0.0001123247,0.001082032,0.0002061597,0.005692759],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01133762,"threshold_uncertainty_score":0.02254325,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04420844994975798,"score_gpt":0.3664997982290382,"score_spread":0.3222913482792802,"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."}}