{"id":"W4402906614","doi":"10.24124/2024/59550","title":"Leveraging machine learning to decode insurance purchasing disparities in Canadian households: A PCA approach","year":2024,"lang":"en","type":"dissertation","venue":"","topic":"Impact of AI and Big Data on Business and Society","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Purchasing; Actuarial science; Business; Computer science; Artificial intelligence; Marketing; Data science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001862848,0.0005761879,0.0005697525,0.002172335,0.001804612,0.001978765,0.000971168,0.0006914381,0.002694049],"category_scores_gemma":[0.008335846,0.0002196175,0.0009587987,0.004437956,0.0005981395,0.0007112944,0.0008500613,0.001658101,0.00041266],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006567468,"about_ca_system_score_gemma":0.01663374,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.9596753,"about_ca_topic_score_gemma":0.9643859,"domain_scores_codex":[0.9993267,0.0001218188,0.00002380348,0.0001301482,0.0001419536,0.0002554633],"domain_scores_gemma":[0.9977599,0.0007793084,0.0001736992,0.0001824145,0.0009341833,0.0001705447],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002569335,0.0002693559,0.8331996,0.00006270957,0.0005228013,0.0002134433,0.001510113,0.01449607,0.0009710105,0.008450885,0.01695152,0.1230955],"study_design_scores_gemma":[0.00003743474,0.0000610267,0.7433636,0.0001340071,0.0004308308,0.0000956818,0.004940236,0.2267277,0.001058269,0.01068356,0.01234843,0.0001191945],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9674013,0.0008314372,0.01560357,0.003038855,0.00009950702,0.00006829717,0.007147945,0.000124942,0.005684195],"genre_scores_gemma":[0.986065,0.0003607845,0.006494014,0.0001708075,0.00003340556,0.00002440319,0.003776563,0.00002413402,0.003050998],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04032475,"threshold_uncertainty_score":0.08112442,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09041793301447533,"score_gpt":0.3476923555904572,"score_spread":0.2572744225759819,"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."}}