{"id":"W3092616113","doi":"10.1007/978-3-030-59830-3_15","title":"A Hybrid Multiple Classifier System Applied in Life Insurance Underwriting","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Underwriting; Computer science; Classifier (UML); Life insurance; Insurance industry; Linear discriminant analysis; CHAID; Artificial intelligence; Medical underwriting; Support vector machine; Machine learning; Data mining; Pattern recognition (psychology); Insurance policy; Actuarial science; General insurance; Decision tree; Business","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":[0.0007852003,0.0004351896,0.0009969538,0.000877669,0.0005749462,0.000958784,0.0008232539,0.001083483,0.00270364],"category_scores_gemma":[0.001038002,0.0002788295,0.0004946273,0.0006865136,0.0001212524,0.0007793364,0.0004590678,0.0006400171,0.001141229],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003951273,"about_ca_system_score_gemma":0.0005282699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003478391,"about_ca_topic_score_gemma":0.004824103,"domain_scores_codex":[0.9996018,0.00006756448,0.00003437704,0.0001093401,0.0001378983,0.00004916728],"domain_scores_gemma":[0.9994816,0.0001416133,0.00002253856,0.00003587391,0.0002871861,0.0000312301],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000640383,0.0003821317,0.005170946,0.000120278,0.0001516119,0.0003180679,0.00005890549,0.03636045,0.04268061,0.0009650444,0.006021407,0.9071302],"study_design_scores_gemma":[0.00001934324,0.0001918176,0.002668301,0.00001220548,0.00009425575,0.0001405312,0.00002532395,0.9822206,0.01160025,0.000611119,0.002393581,0.00002251858],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2200525,0.003922127,0.7629424,0.0005042497,0.001447782,0.0001985847,0.0004594571,0.004163426,0.006309476],"genre_scores_gemma":[0.8081372,0.0008051046,0.178092,0.0002531868,0.0003656486,0.00009962776,0.0004844926,0.00008594865,0.01167673],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003478391,"threshold_uncertainty_score":0.009044588,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02210711609038819,"score_gpt":0.2090633479821192,"score_spread":0.186956231891731,"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."}}