{"id":"W2956961633","doi":"10.3390/risks7030079","title":"Individual Loss Reserving Using a Gradient Boosting-Based Approach","year":2019,"lang":"en","type":"article","venue":"Risks","topic":"Probability and Risk Models","field":"Decision Sciences","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Boosting (machine learning); Gradient boosting; Portfolio; Computer science; Payment; Aggregate (composite); Property (philosophy); Econometrics; Contrast (vision); Artificial intelligence; Machine learning; Mathematics; Economics; Finance","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":[0.005079732,0.0001647508,0.0003159696,0.0002397687,0.0002474841,0.0003020118,0.001155737,0.0001394936,0.00018159],"category_scores_gemma":[0.00123735,0.0001172618,0.0001618006,0.0007201769,0.0001224891,0.0003237666,0.0003493736,0.0002976159,0.0003371652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006965444,"about_ca_system_score_gemma":0.0001696296,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003067265,"about_ca_topic_score_gemma":0.00002925398,"domain_scores_codex":[0.9964043,0.0003499485,0.0005522018,0.0007076154,0.001552268,0.0004336375],"domain_scores_gemma":[0.9975635,0.0008013473,0.0002382795,0.00105604,0.0001929972,0.000147818],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001417204,0.0004443105,0.5277033,0.00005856818,0.00003933917,0.00001635518,0.003030938,0.4418036,0.0005054151,0.005192817,0.0009958546,0.02006782],"study_design_scores_gemma":[0.0009790857,0.0001277483,0.028674,0.00005930167,0.00002982601,0.00001658289,0.0005300406,0.8964288,0.0006807678,0.06850208,0.003566539,0.0004051819],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9561406,0.0001482904,0.03695768,0.0001695936,0.0003088042,0.0003516083,0.00002150973,0.00005995015,0.00584201],"genre_scores_gemma":[0.986401,0.000001361856,0.01301855,0.0002143935,0.00007110067,0.000006580943,0.0000058765,0.00001365737,0.0002674898],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4990293,"threshold_uncertainty_score":0.4781796,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4077657538496265,"score_gpt":0.4322815124342119,"score_spread":0.02451575858458538,"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."}}