{"id":"W2975392813","doi":"10.1109/cig.2019.8848033","title":"Mining Player In-game Time Spending Regularity for Churn Prediction in Free Online Games","year":2019,"lang":"en","type":"article","venue":"2019 IEEE Conference on Games (CoG)","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science","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":[0.0004349532,0.0002558051,0.0003577714,0.0005973072,0.00004048777,0.0002371236,0.0003149925,0.0001629132,0.0009615221],"category_scores_gemma":[0.0001015835,0.0002617713,0.00008576882,0.0003479479,0.00003839645,0.001163256,0.00007913825,0.000233036,0.0007229157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008565131,"about_ca_system_score_gemma":0.0000395684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003151498,"about_ca_topic_score_gemma":0.0005667325,"domain_scores_codex":[0.998312,0.00002166338,0.0004436831,0.0005005294,0.0002920606,0.0004300747],"domain_scores_gemma":[0.9991747,0.00008744367,0.0002448233,0.0003719585,0.0000998647,0.00002123482],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002940336,0.002648818,0.5484434,0.002141768,0.0002813576,0.0000683768,0.003269852,0.004264793,0.101906,0.02719651,0.1128944,0.1939444],"study_design_scores_gemma":[0.01363072,0.0003047056,0.4840984,0.002445244,0.0001774795,0.000007395679,0.002444799,0.4508136,0.001860124,0.009253287,0.0333533,0.001610909],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9867133,0.00007461233,0.0002381939,0.000919255,0.001163476,0.001016186,0.00005080831,0.0000992262,0.009724963],"genre_scores_gemma":[0.9878367,0.00002477068,0.0003090713,0.0005733648,0.0006493737,0.0000526998,0.0002816401,0.00003987915,0.0102325],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4465488,"threshold_uncertainty_score":0.9999834,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03699918568312889,"score_gpt":0.2615649434211816,"score_spread":0.2245657577380527,"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."}}