{"id":"W4394939445","doi":"10.2139/ssrn.4789671","title":"Pricing Catastrophe Bonds --- a Probabilistic Machine Learning Approach","year":2024,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Insurance and Financial Risk Management","field":"Economics, Econometrics and Finance","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Probabilistic logic; Bond; Machine learning; Artificial intelligence; Computer science; Economics; Financial 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":[0.002241111,0.000183583,0.0002892774,0.0002982838,0.0002760722,0.0002290831,0.0002628798,0.00006794106,0.00004935095],"category_scores_gemma":[0.0001077496,0.0001829962,0.0001427483,0.0004255848,0.00003426121,0.00028203,0.00005247354,0.002080346,0.0003632287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009741762,"about_ca_system_score_gemma":0.0002859032,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001945272,"about_ca_topic_score_gemma":0.0000752826,"domain_scores_codex":[0.9973323,0.00002138842,0.0005099776,0.0003770325,0.00007020423,0.001689048],"domain_scores_gemma":[0.9995738,0.00002490967,0.0001677564,0.0001601452,0.00001687696,0.00005647607],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001480649,0.00004990856,0.002416428,0.00005535275,0.0001137048,0.00001116849,0.000297725,0.001698913,0.000004771409,0.9707288,0.00008492478,0.02452353],"study_design_scores_gemma":[0.0005130203,0.0004835826,0.00105751,0.000053448,0.00003558525,0.0003080199,0.0004066712,0.05591579,0.000003423247,0.7278915,0.2128462,0.0004851735],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.167807,0.1543023,0.5761548,0.001185617,0.001522114,0.0007267594,0.00004904654,0.0003734399,0.09787896],"genre_scores_gemma":[0.9838409,0.009984168,0.0003844565,0.00004890495,0.0004146634,0.00001958455,0.00001793163,0.00004531777,0.00524405],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.816034,"threshold_uncertainty_score":0.9038182,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01198033674186415,"score_gpt":0.2028266636909538,"score_spread":0.1908463269490896,"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."}}