{"id":"W4410086347","doi":"10.1038/s41598-025-99119-0","title":"Integrating generative AI and machine learning classifiers for solving heterogenous MCGDM: a case of employee churn prediction","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI and HR Technologies","field":"Business, Management and Accounting","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Science and Technology Development Fund","keywords":"Machine learning; Computer science; Artificial intelligence; Generative grammar; Ranking (information retrieval); Analytic hierarchy process; Boosting (machine learning); Random forest; Naive Bayes classifier; Support vector machine; Operations research; Engineering","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":[0.0008449705,0.0001304311,0.0001958673,0.0004255018,0.0008445518,0.0004475067,0.00007304293,0.00007768715,0.00001003725],"category_scores_gemma":[0.0006506611,0.0001113806,0.00006839343,0.0004695488,0.0002161312,0.0005133207,0.0001656067,0.0001538161,6.954427e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002802319,"about_ca_system_score_gemma":0.00003669879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000254714,"about_ca_topic_score_gemma":0.0003974584,"domain_scores_codex":[0.998785,0.000006101676,0.0004157251,0.0004563587,0.0001230984,0.0002137313],"domain_scores_gemma":[0.9991027,0.00003250576,0.000347419,0.0002455722,0.0002636904,0.00000814851],"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":[0.0000868706,0.0001962521,0.6119649,0.00180237,0.0003082514,0.001597093,0.001989082,0.001203103,0.1712369,0.01556338,0.02698939,0.1670624],"study_design_scores_gemma":[0.002065756,0.0002540599,0.004446163,0.001442229,0.0008150422,0.001876398,0.01679792,0.5887596,0.1043282,0.1503876,0.1273663,0.001460805],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9767893,0.0003392853,0.01872909,0.0003053806,0.001999378,0.0004401184,0.000003474323,0.0002465791,0.001147413],"genre_scores_gemma":[0.9978537,0.000003388437,0.0009696326,0.00008703151,0.00008236507,0.00003996732,0.00003848034,0.00001122883,0.0009142317],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6075187,"threshold_uncertainty_score":0.6495695,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02249062470679131,"score_gpt":0.2528563090251582,"score_spread":0.2303656843183669,"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."}}