{"id":"W4406837832","doi":"10.11591/ijeecs.v38.i1.pp622-631","title":"Study on postal life insurance attributes and its growth prediction using machine learning algorithms","year":2025,"lang":"en","type":"article","venue":"Indonesian Journal of Electrical Engineering and Computer Science","topic":"Insurance and Financial Risk Management","field":"Economics, Econometrics and Finance","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"VISTA Science & Technology","funders":"","keywords":"Computer science; Machine learning; Life insurance; Algorithm; Artificial intelligence; Data mining; Actuarial science; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007267251,0.0001147799,0.0002743587,0.000620003,0.0001867027,0.0001217166,0.0001734688,0.00003292544,3.363981e-7],"category_scores_gemma":[0.0001559341,0.0001141441,0.00003519207,0.0008928212,0.00003146589,0.0003043275,0.00006115469,0.0002928414,7.941308e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005837852,"about_ca_system_score_gemma":0.00003515243,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001009602,"about_ca_topic_score_gemma":1.255111e-7,"domain_scores_codex":[0.9990165,0.00001104381,0.0004190411,0.0002362168,0.00009151242,0.000225744],"domain_scores_gemma":[0.9995442,0.00004450412,0.0001721605,0.00006308343,0.00008315844,0.00009290978],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001050438,0.0004007898,0.8865581,0.00006584008,0.000121023,0.00009844075,0.0006893614,0.03270553,0.0003908595,0.05785837,0.0000107192,0.02099597],"study_design_scores_gemma":[0.0005822924,0.0006434128,0.5061429,0.0000478668,0.000005334804,0.00002719359,0.000007502794,0.4920701,0.000113722,0.0002058299,0.00005329542,0.0001005414],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.845628,0.001807076,0.1520098,0.00009458039,0.0003350287,0.00008667347,0.000003631721,0.00001334534,0.00002187568],"genre_scores_gemma":[0.9987558,0.0001821122,0.0008929794,0.00005530353,0.0001017394,0.000001266456,1.631345e-7,0.000005571988,0.000005043652],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4593645,"threshold_uncertainty_score":0.4654662,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01525109485688612,"score_gpt":0.2090849347231303,"score_spread":0.1938338398662442,"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."}}