{"id":"W7020644812","doi":"","title":"Machine Learning Techniques in Usage-Based Insurance:
\\nUse of Telematic Data in Auto Insurance","year":2023,"lang":"en","type":"dissertation","venue":"Spectrum Research Repository (Concordia University)","topic":"Probability and Risk Models","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Telematics; Gradient boosting; Artificial neural network; Boosting (machine learning); Random forest; Ensemble learning; Logistic regression; Big data; Identification (biology); Global Positioning System","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.01052956,0.0004031157,0.00115082,0.006195982,0.0005684755,0.0001874268,0.004866496,0.0005926102,0.00004081175],"category_scores_gemma":[0.005286263,0.0003905071,0.0002139736,0.008034542,0.0005147211,0.0009984571,0.001029471,0.002834135,0.00004467562],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006983941,"about_ca_system_score_gemma":0.002194369,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.06080903,"about_ca_topic_score_gemma":0.284433,"domain_scores_codex":[0.9896955,0.003329912,0.001360881,0.001717883,0.003017808,0.0008779527],"domain_scores_gemma":[0.9920497,0.003866997,0.0007212848,0.002591866,0.000556056,0.0002140818],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0009544569,0.000291874,0.9884563,0.0004276743,0.00003321116,0.0008074221,0.00128015,0.0008359614,0.002102745,0.0002752483,0.00007681207,0.004458136],"study_design_scores_gemma":[0.0009412371,0.0003194159,0.9686856,0.001148689,0.00001276611,0.000004227943,0.00208112,0.007751871,0.009401499,0.006870386,0.002300191,0.0004830369],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9846158,0.0003608493,0.00009269494,0.0001796508,0.0003845012,0.001082264,0.0001357152,0.0001496941,0.01299883],"genre_scores_gemma":[0.982073,0.0004899864,0.000123749,0.000003208987,0.00005784552,0.00001132579,0.0002294021,0.00005178601,0.0169597],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.223624,"threshold_uncertainty_score":0.9998547,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1125395206394987,"score_gpt":0.3762009882773714,"score_spread":0.2636614676378726,"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."}}