{"id":"W4389849991","doi":"10.5267/j.dsl.2023.12.006","title":"Using machine learning algorithms with improved accuracy to analyze and predict employee attrition","year":2023,"lang":"en","type":"article","venue":"Decision Science Letters","topic":"AI and HR Technologies","field":"Business, Management and Accounting","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Attrition; Decision tree; Computer science; Machine learning; Human resource management; IBM; Human resources; Random forest; Logistic regression; Artificial intelligence; Knowledge management; Management","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":[0.0007563746,0.000135865,0.0001463244,0.001088875,0.0006177758,0.0007012402,0.0004035618,0.00003470761,0.00001361581],"category_scores_gemma":[0.0008196101,0.0001019091,0.00002540436,0.003525031,0.0002420867,0.001711743,0.0004778572,0.0001473831,0.00007349363],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000319465,"about_ca_system_score_gemma":0.00001259662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002141617,"about_ca_topic_score_gemma":0.00002702578,"domain_scores_codex":[0.9984564,0.000004223312,0.0001788122,0.0004671216,0.000522313,0.0003711531],"domain_scores_gemma":[0.9994428,0.0001102414,0.0001035697,0.0002228088,0.00009642467,0.00002416715],"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":[0.0001203018,0.00002561604,0.392824,0.00004255369,0.00001732812,0.0001165133,0.0001698227,0.004348306,0.3383078,0.000274487,0.003264959,0.2604883],"study_design_scores_gemma":[0.001214028,0.0000991643,0.3403223,0.0002580326,0.00005665741,0.00002520731,0.001003407,0.637738,0.002678785,0.001136269,0.01471287,0.000755286],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9656204,0.00001277956,0.02993909,0.003651264,0.0001217829,0.0001851841,0.000001517912,0.000420198,0.00004779821],"genre_scores_gemma":[0.9865636,0.00000903269,0.01034319,0.002882946,0.0001543124,0.000009332007,0.000005428458,0.0000159235,0.00001620517],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6333897,"threshold_uncertainty_score":0.6762075,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04545694630643957,"score_gpt":0.3009237058749221,"score_spread":0.2554667595684825,"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."}}