{"id":"W6892886310","doi":"10.5281/zenodo.12783618","title":"PREDICTING CHURN IN TELECOM SECTOR USING A POPULATION-BASED INCREMENTAL ANN LEARNING ALGORITHM","year":2024,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Churning; Artificial neural network; Customer retention; Profit (economics); Customer satisfaction; Probabilistic logic; Inefficiency; Customer intelligence; Simulated annealing","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":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006496538,0.0001366829,0.0001181408,0.0007002067,0.001133045,0.001835956,0.0002747413,0.00004875094,0.005130525],"category_scores_gemma":[0.0002008464,0.0001520833,0.00004742199,0.001121892,0.00003019059,0.0009617348,0.0003226205,0.0003000291,0.001428072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002804069,"about_ca_system_score_gemma":0.000004376087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006185587,"about_ca_topic_score_gemma":0.000006389705,"domain_scores_codex":[0.9986612,0.0000744901,0.0002770133,0.0003497349,0.0003365849,0.000300935],"domain_scores_gemma":[0.9995871,0.00002190155,0.00008877282,0.0001265656,0.0001506135,0.00002505992],"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":[0.0002047962,0.0005650606,0.02594755,0.001725351,0.0001802413,0.000223647,0.002548168,0.01760479,0.03270836,0.003177038,0.0197561,0.8953589],"study_design_scores_gemma":[0.0006924238,0.00003654734,0.01201462,0.0002088293,0.00002909414,0.00002079191,0.0007110958,0.7853094,0.0001110179,0.0001045195,0.2004834,0.0002782546],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9648519,0.0001204116,0.01067302,0.0003756789,0.0003962715,0.0006192047,0.00004447668,0.001815459,0.02110365],"genre_scores_gemma":[0.996051,0.000003965538,0.0004254082,0.0001707696,0.0005649808,7.079318e-8,0.002026354,0.0006498416,0.0001076355],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8950806,"threshold_uncertainty_score":0.9993494,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03312816622723147,"score_gpt":0.2463427079587965,"score_spread":0.2132145417315651,"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."}}