{"id":"W4411965264","doi":"10.1016/j.dajour.2025.100601","title":"A data-driven approach to customer lifetime value prediction using probability and machine learning models","year":2025,"lang":"en","type":"article","venue":"Decision Analytics Journal","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Langara College","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Machine learning; Value (mathematics); Artificial intelligence; Customer value; Economics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001337244,0.0001728726,0.0002513752,0.0007937849,0.000481669,0.0008088177,0.0003370649,0.00007417909,0.00004179173],"category_scores_gemma":[0.0003483522,0.0001492641,0.00006537705,0.00090304,0.00003436644,0.001457053,0.0004905628,0.0003942552,0.00002798616],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001089761,"about_ca_system_score_gemma":0.00005209031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006886195,"about_ca_topic_score_gemma":0.00001486549,"domain_scores_codex":[0.9983328,0.00003657117,0.0005239222,0.0003924705,0.0004851339,0.0002291081],"domain_scores_gemma":[0.9990864,0.00006407465,0.0002162735,0.0003143816,0.0002681461,0.00005066935],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002120913,0.0002504398,0.02015739,0.00008700285,0.0001343753,0.000007574732,0.0001271307,0.9313836,0.0002891196,0.006564963,0.005851855,0.03493451],"study_design_scores_gemma":[0.000622782,0.00000720359,0.002536557,0.0000823981,0.0001916329,0.0000213544,0.0001374995,0.9791563,0.00000230813,0.007052919,0.01005707,0.0001320347],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1695011,0.0001517981,0.821016,0.0003468368,0.0003669318,0.0003063523,0.00001608394,0.000063003,0.008231937],"genre_scores_gemma":[0.9609544,0.00007005552,0.03678164,0.001169488,0.0005489215,0.00000292859,0.0001062214,0.00002573473,0.0003406281],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7914533,"threshold_uncertainty_score":0.7799448,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1077419021977437,"score_gpt":0.3044053623112366,"score_spread":0.1966634601134929,"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."}}