{"id":"W4414936234","doi":"10.28924/2291-8639-23-2025-236","title":"Interpretable Gradient Boosted Modeling of Employee Attrition: A SHAP-Based Framework for HR Analytics","year":2025,"lang":"en","type":"article","venue":"International Journal of Analysis and Applications","topic":"AI and HR Technologies","field":"Business, Management and Accounting","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Mahasarakham University","keywords":"Attrition; Human resource management; Gradient boosting; Random forest; Analytics; Predictive analytics; Job embeddedness; Key (lock)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002022088,0.00008365769,0.0002540123,0.001077421,0.00007842854,0.0001236652,0.0003495327,0.00005788364,0.00002860136],"category_scores_gemma":[0.0001186766,0.00007341534,0.0002702638,0.0008183766,0.00004844991,0.0002074181,0.00006719652,0.00009659982,7.529913e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002798865,"about_ca_system_score_gemma":0.00002706898,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003914878,"about_ca_topic_score_gemma":0.00003151693,"domain_scores_codex":[0.9991155,0.00000292348,0.0004935253,0.0001215692,0.0001846291,0.00008188588],"domain_scores_gemma":[0.9983317,0.0001011647,0.000408723,0.0001269032,0.001023001,0.000008487355],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002613871,0.0005716097,0.1088758,0.0001838011,0.005680485,0.000002925727,0.00004543319,0.09434654,0.0006286882,0.7609172,0.00158205,0.02690399],"study_design_scores_gemma":[0.0006914758,0.00002778974,0.003841171,0.0002514411,0.002590566,0.000001302118,0.0004700354,0.7632116,0.0003072969,0.2164303,0.01201043,0.0001665925],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04704908,0.0002997406,0.9491378,0.002814734,0.00006104865,0.0001148928,0.00001704068,0.00001792276,0.0004877076],"genre_scores_gemma":[0.988997,0.00005558492,0.0101928,0.000470326,0.0001895908,0.00002700234,0.00002709956,0.000004789502,0.00003578978],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9419479,"threshold_uncertainty_score":0.2993791,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02635670434733407,"score_gpt":0.3036438104687137,"score_spread":0.2772871061213796,"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."}}