{"id":"W3127196675","doi":"","title":"Rethinking Representations in P&C Actuarial Science with Deep Neural Networks","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Complement (music); Representation (politics); Variety (cybernetics); Computer science; Task (project management); External Data Representation; Process (computing); Raw data; Data science; Artificial neural network; Space (punctuation); Artificial intelligence; Deep learning; Machine learning; Data mining; Engineering; Systems engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002388086,0.0006899287,0.0006990673,0.0007912691,0.0003934366,0.002277658,0.001541191,0.00140253,0.002393864],"category_scores_gemma":[0.01089817,0.0004898887,0.0006282308,0.001074474,0.001616485,0.004861199,0.002185464,0.003967153,0.0005481309],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001483444,"about_ca_system_score_gemma":0.001128013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006145488,"about_ca_topic_score_gemma":0.006152665,"domain_scores_codex":[0.9991916,0.0003644814,0.00004102488,0.0001339417,0.0002060982,0.00006294961],"domain_scores_gemma":[0.9972547,0.001792945,0.0002091897,0.0004129912,0.0002410498,0.00008912823],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000067051,0.00006418359,0.00145377,0.00008957205,0.00008503722,0.00006769266,0.0001526833,0.630285,0.001024971,0.2367787,0.004619194,0.1253122],"study_design_scores_gemma":[0.000003915093,0.000007332166,0.00008293372,0.00001405472,0.000003624849,0.000007003277,0.000007961768,0.8862101,0.0002217932,0.1124656,0.000970252,0.000005519324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.016347,0.001039157,0.9744347,0.003513835,0.0001454192,0.00002591017,0.0002066371,0.00050909,0.003778212],"genre_scores_gemma":[0.7599776,0.002433655,0.2288792,0.001022337,0.0004387428,0.0001358862,0.0005802049,0.0002174012,0.006314974],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006145488,"threshold_uncertainty_score":0.01262957,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06976237591015816,"score_gpt":0.230304412148615,"score_spread":0.1605420362384569,"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."}}