{"id":"W2351547823","doi":"","title":"Application of Clustering Analysis in Family Customer Segmentation in Telecom Industry","year":2008,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Market segmentation; Computer science; Cluster analysis; Segmentation; Telecommunications; Government (linguistics); Service (business); Enhanced Telecom Operations Map; Customer intelligence; Data mining; Customer advocacy; Marketing; Business; Service quality; Service provider; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001468416,0.0001323249,0.0002274473,0.001241101,0.00007262504,0.00003443532,0.0001992719,0.0001112821,0.00002023865],"category_scores_gemma":[5.696282e-7,0.0001517375,0.00007262991,0.00308289,0.00003954749,0.0004391119,0.00008373304,0.0001815323,0.00009556194],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008876411,"about_ca_system_score_gemma":0.00001625135,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009844073,"about_ca_topic_score_gemma":0.001382127,"domain_scores_codex":[0.9988679,0.000010524,0.0004922761,0.0003043476,0.0001463219,0.0001786166],"domain_scores_gemma":[0.9994723,0.0000225667,0.0002213806,0.0001981843,0.00007495841,0.00001058009],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001845476,0.0004157204,0.8523763,0.00009837113,0.00006368924,0.000002348198,0.0004300021,0.01623361,0.03592498,0.0007216288,0.0002537711,0.09346111],"study_design_scores_gemma":[0.0008466628,0.000002897595,0.9389262,0.00001291423,0.00007418261,0.000002091127,0.0003067694,0.03826421,0.0005922399,0.0001245651,0.02061135,0.0002359404],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6617923,0.00005043258,0.3351499,0.0001378445,0.00001343055,0.0008016558,0.000004218317,0.00005398238,0.001996244],"genre_scores_gemma":[0.9904262,0.0000158463,0.008293178,0.0004932499,0.0001334037,0.0003966614,0.0001916404,0.00001446993,0.00003534724],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3286339,"threshold_uncertainty_score":0.6187675,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01545242694526022,"score_gpt":0.242888798867585,"score_spread":0.2274363719223248,"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."}}