{"id":"W4283741364","doi":"10.1002/for.2885","title":"Predicting earnings management through machine learning ensemble classifiers","year":2022,"lang":"en","type":"article","venue":"Journal of Forecasting","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Saint Mary's University; Concordia University","funders":"Social Sciences and Humanities Research Council of Canada; New Brunswick Innovation Foundation","keywords":"Artificial intelligence; Computer science; Ensemble forecasting; Support vector machine; Ensemble learning; Machine learning; Principal component analysis; Random subspace method; Context (archaeology); Feature selection; Pattern recognition (psychology); Classifier (UML)","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":[0.001608104,0.0001264399,0.0002022088,0.000231249,0.0006492697,0.0001227859,0.001071534,0.00002630837,0.00003250747],"category_scores_gemma":[0.0002165161,0.0001244323,0.0001046573,0.0005725196,0.00002575434,0.0009277394,0.0007247868,0.0008693906,0.000002539265],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002212174,"about_ca_system_score_gemma":0.00005032513,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008931564,"about_ca_topic_score_gemma":5.539089e-7,"domain_scores_codex":[0.9980178,0.0001873044,0.0005977693,0.0002243541,0.0006782981,0.0002944243],"domain_scores_gemma":[0.9982416,0.0001463599,0.00116779,0.0002601127,0.0001210087,0.00006310423],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001914235,0.0004579089,0.1286565,0.0002778329,0.0005154076,0.001639909,0.01636925,0.04922246,0.01851786,0.07403336,0.01419376,0.6959243],"study_design_scores_gemma":[0.001430884,0.001248161,0.004578315,0.000235136,0.0000623571,0.003165222,0.002661399,0.7740473,0.007654974,0.007430702,0.1969118,0.0005737561],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04265976,0.0001409463,0.9436274,0.0007300116,0.0005199466,0.0001281271,0.000002522309,0.0002069461,0.01198432],"genre_scores_gemma":[0.7428754,0.00002596901,0.2563777,0.0001507015,0.00008477298,0.00001079539,0.000003295971,0.00001543177,0.0004559455],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7248248,"threshold_uncertainty_score":0.5074202,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04131222352818766,"score_gpt":0.2561634504400872,"score_spread":0.2148512269118995,"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."}}