{"id":"W4321636122","doi":"10.1109/icast55766.2022.10039530","title":"Feedback Based Telecom Churn Prediction Using Machine Learning","year":2022,"lang":"en","type":"article","venue":"","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Competition (biology); Preference; Quarter (Canadian coin); Customer retention; Value (mathematics); Customer lifetime value; Telecommunications; Artificial intelligence; Machine learning; Marketing; Business; Statistics","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002758106,0.0001021114,0.00009277245,0.000252348,0.0006542384,0.000153553,0.00009951666,0.00001806013,0.00704427],"category_scores_gemma":[0.00001812215,0.0001049404,0.00005478581,0.0004886917,0.00001131116,0.0005162614,0.0001215426,0.0001936128,0.00009711552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009060104,"about_ca_system_score_gemma":0.00001469002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001001312,"about_ca_topic_score_gemma":0.00005498376,"domain_scores_codex":[0.9991621,0.00001809497,0.0001753921,0.0001867657,0.0002813958,0.0001762766],"domain_scores_gemma":[0.9997337,0.00001461732,0.0001154493,0.00009002059,0.00003847945,0.0000076802],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002472293,0.0004357834,0.7010326,0.0001991196,0.00006793894,0.00001765912,0.0001587644,0.2294311,0.0359459,0.002451109,0.008602095,0.02141074],"study_design_scores_gemma":[0.0008251327,0.00001490294,0.007944052,0.000004813401,0.00003661483,0.000002324053,0.0004450883,0.8987425,0.0001654955,0.00007253095,0.09159493,0.0001516379],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9593446,0.00004477311,0.007147558,0.0007572403,0.0008211599,0.0002922812,0.000006255319,0.0004856031,0.03110058],"genre_scores_gemma":[0.9952894,9.147802e-7,0.0004765639,0.002003776,0.0004049302,0.00001545487,0.0002365902,0.00002440665,0.001547895],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6930885,"threshold_uncertainty_score":0.9938634,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02352073227171434,"score_gpt":0.2163500492570249,"score_spread":0.1928293169853106,"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."}}