{"id":"W4320009219","doi":"10.2139/ssrn.4344952","title":"Integration of Traditional and Telematics Data for Efficient Insurance Claims Prediction","year":2023,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Insurance and Financial Risk Management","field":"Economics, Econometrics and Finance","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Telematics; Data science; Computer science; Business; Actuarial science; Telecommunications","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":[0.002042168,0.00007807607,0.0001878424,0.0001971659,0.0001373064,0.00002717401,0.0001955525,0.00004693298,0.000004680372],"category_scores_gemma":[0.0001197812,0.0000815692,0.00004796378,0.0002164789,0.00003384214,0.0001838867,0.00002428933,0.0002849196,0.0000150964],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001456477,"about_ca_system_score_gemma":0.0001007872,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000140912,"about_ca_topic_score_gemma":0.00004356839,"domain_scores_codex":[0.9987296,0.000007650935,0.000472579,0.0001903981,0.00005369408,0.0005460079],"domain_scores_gemma":[0.999414,0.00004672706,0.0002917544,0.000185098,0.00004004977,0.0000223992],"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":[0.00003262964,0.00006759341,0.005380761,0.00003294661,0.00005495349,2.566352e-7,0.000144419,0.0005084218,0.00005444283,0.9793776,0.0004371561,0.01390878],"study_design_scores_gemma":[0.0008028785,0.0003270659,0.0921251,0.00003370181,0.00001130522,0.00001571787,0.0004410524,0.04388963,0.00002701489,0.8590234,0.003181651,0.0001215208],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.81102,0.001471329,0.1847034,0.0004488281,0.0004773868,0.0003038358,0.001003505,0.00002490254,0.0005467696],"genre_scores_gemma":[0.9936183,0.005427819,0.0003661843,0.00002063157,0.0001932348,0.00001458719,0.0001572104,0.00001178275,0.0001902549],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1843372,"threshold_uncertainty_score":0.3326296,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04985614610392074,"score_gpt":0.2410096467474835,"score_spread":0.1911535006435628,"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."}}