{"id":"W4386848513","doi":"10.3390/risks11090164","title":"Machine Learning in Forecasting Motor Insurance Claims","year":2023,"lang":"en","type":"article","venue":"Risks","topic":"Insurance and Financial Risk Management","field":"Economics, Econometrics and Finance","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Actuarial science; Random forest; Quarter (Canadian coin); Econometrics; Computer science; Economics; Business; Artificial intelligence","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006899615,0.0001234142,0.0002803756,0.0003776951,0.000125059,0.00003961168,0.0001716983,0.00007535218,0.00007100184],"category_scores_gemma":[0.0001495766,0.0001496295,0.00007804098,0.0007509851,0.00002220374,0.0001657564,0.00007908725,0.0002747143,0.001901392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006680414,"about_ca_system_score_gemma":0.00000666971,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001057397,"about_ca_topic_score_gemma":0.0001518004,"domain_scores_codex":[0.9987825,0.00001241931,0.0004483805,0.000324362,0.00003833084,0.0003940309],"domain_scores_gemma":[0.9995558,0.00004276848,0.0001776443,0.0001769818,0.00001156454,0.00003525919],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001749201,0.00002484339,0.9310257,0.00002993058,0.000008603443,0.00003700674,0.0003655362,0.00273217,0.000005731174,0.03737754,0.0002254753,0.02814992],"study_design_scores_gemma":[0.0005067293,0.00004873253,0.8443452,0.00002739873,9.401296e-7,8.902613e-7,0.00004779451,0.0558998,0.0000100411,0.02117854,0.07771499,0.000218922],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9533656,0.001259528,0.0005573612,0.0002491501,0.0004729958,0.0002248799,0.00007938243,0.0001668323,0.04362423],"genre_scores_gemma":[0.9954053,0.001387142,0.0001549925,0.00009957271,0.0001095793,0.00004734916,0.00002228353,0.00002710209,0.002746706],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08668052,"threshold_uncertainty_score":0.9988757,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09004306024869731,"score_gpt":0.2568708583974556,"score_spread":0.1668277981487583,"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."}}