{"id":"W4206760781","doi":"10.2139/ssrn.3981160","title":"Interpretable Deep Learning Approach to Churn Management","year":2020,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Quest University Canada","funders":"","keywords":"Deep learning; Artificial intelligence; Computer science; Data science; Business; Machine learning","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":[0.0006498551,0.0001657273,0.0001694579,0.0002032432,0.0002685044,0.0003583203,0.0003205498,0.00003452711,0.0001152881],"category_scores_gemma":[0.00003302724,0.0001552902,0.00009663039,0.0005477618,0.00001129082,0.0007193361,0.0001482971,0.0009825943,0.0005778716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002652057,"about_ca_system_score_gemma":0.00005000617,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003237569,"about_ca_topic_score_gemma":0.00003340175,"domain_scores_codex":[0.9978388,0.00001492203,0.0002525933,0.000254668,0.0002998633,0.001339129],"domain_scores_gemma":[0.9996707,0.000005888582,0.0001408698,0.00008359683,0.00005979088,0.0000391943],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000605719,0.0003636935,0.01299801,0.0003316095,0.000877049,0.00002777593,0.002224328,0.01711379,0.001555081,0.483213,0.00540345,0.4752865],"study_design_scores_gemma":[0.007943843,0.0005999634,0.007946496,0.000190149,0.000942417,0.0002741259,0.08339886,0.158552,0.0001248666,0.07400128,0.6632009,0.002825144],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.176109,0.0008561896,0.490633,0.006205741,0.000513276,0.000707068,3.326203e-7,0.0003602417,0.3246152],"genre_scores_gemma":[0.9925511,0.0002124697,0.0003866714,0.003833765,0.00113775,0.00001215267,0.00001173707,0.00003391749,0.001820457],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8164421,"threshold_uncertainty_score":0.7427564,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01037192232185233,"score_gpt":0.2079775157827171,"score_spread":0.1976055934608648,"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."}}