{"id":"W3133751382","doi":"10.1109/access.2021.3064929","title":"Cancel-for-Any-Reason Insurance Recommendation Using Customer Transaction-Based Clustering","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Cluster analysis; Data mining; Revenue; Market segmentation; Database transaction; DBSCAN; Generalized entropy index; Index (typography); Artificial neural network; Artificial intelligence; Business; Database; Fuzzy clustering; Marketing; Finance","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":[0.0001691799,0.0001508947,0.0001648968,0.0001700299,0.0002631365,0.0005370492,0.0001505667,0.00006077181,0.0004024098],"category_scores_gemma":[0.00002430674,0.0001666765,0.0000865592,0.0005596633,0.00002091183,0.002049056,0.00001785655,0.00008920438,0.00003573387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001139404,"about_ca_system_score_gemma":0.00005671301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009752944,"about_ca_topic_score_gemma":0.001126053,"domain_scores_codex":[0.9990388,0.00001285924,0.0002558386,0.000295993,0.0001590321,0.0002374928],"domain_scores_gemma":[0.9993681,0.00004175856,0.0001831626,0.0001453649,0.0002475617,0.00001408152],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007419196,0.0006014664,0.1380141,0.002760343,0.0002189364,0.00003474644,0.0002893082,0.1691512,0.1524415,0.0004104818,0.008053361,0.5272827],"study_design_scores_gemma":[0.006246892,0.00001438896,0.03935769,0.0004494848,0.0003110473,0.000009860478,0.0004496527,0.7171359,0.09654389,0.0004713172,0.1375729,0.001436989],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6964504,0.00006930765,0.2952187,0.001313034,0.003283269,0.0004145756,0.00002416568,0.0001654561,0.003061154],"genre_scores_gemma":[0.9958247,0.00001276715,0.0005780369,0.002387838,0.0008770477,0.00004776873,0.0001450214,0.00003322437,0.00009359785],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5479847,"threshold_uncertainty_score":0.6796869,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07444771464393604,"score_gpt":0.3239853776228311,"score_spread":0.249537662978895,"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."}}