{"id":"W2950598571","doi":"10.48550/arxiv.1508.06378","title":"Insurance Premium Prediction via Gradient Tree-Boosted Tweedie Compound Poisson Models","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Insurance, Mortality, Demography, Risk Management","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Logarithm; Generalized linear model; Poisson distribution; Econometrics; Data mining; Mathematics; Statistics; Machine learning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003716572,0.0006151924,0.001402058,0.001259832,0.000442797,0.001023222,0.002087972,0.001440745,0.002958218],"category_scores_gemma":[0.01244144,0.0005615944,0.0009617208,0.0008847653,0.0005158134,0.001546603,0.0009937505,0.001818958,0.0009870426],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006938914,"about_ca_system_score_gemma":0.0008513113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004966372,"about_ca_topic_score_gemma":0.005576172,"domain_scores_codex":[0.9993455,0.0003171693,0.00002772442,0.0001236344,0.0001162844,0.00006967285],"domain_scores_gemma":[0.9955956,0.003044679,0.0003977129,0.0002963163,0.0004745763,0.0001910427],"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":[0.0002350198,0.0001395048,0.008635601,0.0001011807,0.0001069111,0.0001556717,0.0001099861,0.8568231,0.001335963,0.01621674,0.005813578,0.1103266],"study_design_scores_gemma":[0.000005397153,0.000005694836,0.000160932,0.000002691256,0.00000314772,0.000005999471,0.000001635218,0.9966353,0.00007797859,0.002946379,0.0001515293,0.000003388102],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05955599,0.0004255968,0.9371476,0.0005122508,0.00008799707,0.00005140843,0.0003338178,0.001067822,0.0008175571],"genre_scores_gemma":[0.7003334,0.0003766411,0.2925655,0.0003625205,0.0002641579,0.0001646271,0.001183308,0.0003048936,0.004444908],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004966372,"threshold_uncertainty_score":0.01965535,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1074023590198188,"score_gpt":0.2253139777013255,"score_spread":0.1179116186815067,"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."}}