{"id":"W2012290523","doi":"10.1016/j.eswa.2011.09.058","title":"Gradient boosting trees for auto insurance loss cost modeling and prediction","year":2011,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":251,"is_retracted":false,"has_abstract":false,"ca_institutions":"Royal Bank of Canada","funders":"","keywords":"Computer science; Gradient boosting; Softmax function; Support vector machine; Feature selection; Data mining; Parameterized complexity; Generalized linear model; Hinge loss; Artificial neural network; Data pre-processing; Machine learning; Artificial intelligence; Algorithm; Mathematical optimization; Random forest; Mathematics","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":[0.003945287,0.0006988691,0.001916794,0.001095439,0.0004706851,0.0009674121,0.001690314,0.001477408,0.001728938],"category_scores_gemma":[0.007469957,0.0007188075,0.0008285326,0.001206655,0.0004236295,0.001518502,0.0006556535,0.001922548,0.0007175068],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007760111,"about_ca_system_score_gemma":0.0009020456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004047426,"about_ca_topic_score_gemma":0.004151616,"domain_scores_codex":[0.9991721,0.0003718915,0.00004902322,0.000129637,0.0001981928,0.00007917862],"domain_scores_gemma":[0.9972772,0.001864399,0.0001430592,0.0002252772,0.0004091862,0.00008087009],"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":[0.0001070762,0.0001141603,0.001404484,0.00005536719,0.00006347003,0.0000440677,0.00003639313,0.8271843,0.0007528865,0.01206032,0.004449253,0.1537284],"study_design_scores_gemma":[0.000001624004,0.00000418365,0.0000644207,0.000002012904,0.000003162475,0.000003720029,9.69007e-7,0.9965428,0.00007814548,0.003147951,0.0001496426,0.000001444359],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01726013,0.0008897771,0.9803104,0.0002324196,0.00006891465,0.00002933138,0.0001218998,0.0004975559,0.0005896931],"genre_scores_gemma":[0.6859136,0.001097189,0.305214,0.0002141195,0.0002979552,0.0002078765,0.0007745901,0.0002204207,0.006060367],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004047426,"threshold_uncertainty_score":0.02086496,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04805340199553818,"score_gpt":0.2653546485366028,"score_spread":0.2173012465410646,"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."}}