{"id":"W4308702592","doi":"10.2991/978-94-6463-005-3_71","title":"Risk Decision and Predicting of Customer Churn Based on Principal Component Analysis","year":2022,"lang":"en","type":"book-chapter","venue":"","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Principal component analysis; Component (thermodynamics); Business; Computer science; Artificial intelligence","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004822985,0.0002977416,0.0005010043,0.001510014,0.00021772,0.00009778961,0.000163037,0.0001141427,0.008226371],"category_scores_gemma":[0.00003713339,0.0002672519,0.0002862011,0.0002611782,0.00004864519,0.0002278166,0.0002296659,0.0003117053,0.00007701582],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007090061,"about_ca_system_score_gemma":0.00001514204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005511623,"about_ca_topic_score_gemma":0.0001914438,"domain_scores_codex":[0.9980955,0.000009419432,0.0005298744,0.0004499132,0.0007504977,0.0001647662],"domain_scores_gemma":[0.9986443,0.0001645558,0.0007410581,0.0003257827,0.0001055124,0.00001877481],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002111421,0.0008921,0.4440544,0.001586749,0.005887469,0.0001164418,0.0003559777,0.06522498,0.0002202831,0.2474012,0.009352561,0.2227964],"study_design_scores_gemma":[0.003337504,0.00009701645,0.08607822,0.000299933,0.009080509,0.000001498091,0.0002261834,0.3925079,0.00002325856,0.002079923,0.5048449,0.001423151],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.04358688,0.00007382832,0.001339431,0.00008523779,0.0003438671,0.0004976409,0.00006170269,0.0001230993,0.9538883],"genre_scores_gemma":[0.9626221,0.0001034948,0.0004324727,0.0007695793,0.0004285875,0.00001780106,0.0006911758,0.00007872891,0.03485604],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9190353,"threshold_uncertainty_score":0.9999779,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01622367994344255,"score_gpt":0.2274305348430883,"score_spread":0.2112068548996458,"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."}}