{"id":"W2137539029","doi":"10.1109/icdm.2003.1250975","title":"Comparing naive Bayes, decision trees, and SVM with AUC and accuracy","year":2004,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":235,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Support vector machine; Naive Bayes classifier; Computer science; Machine learning; Decision tree; Artificial intelligence; Receiver operating characteristic; Measure (data warehouse); Data mining; Bayes' theorem; Statistical classification; Bayesian probability","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":[0.0001216823,0.0000980916,0.0001163749,0.0000746104,0.0001005007,0.0002139312,0.0003338693,0.00003245587,0.000003062905],"category_scores_gemma":[0.00004320432,0.00007226935,0.000007159459,0.0001796029,0.00006701989,0.0008340417,0.0002499028,0.00007504496,0.000006599925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003208216,"about_ca_system_score_gemma":0.00003519023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009121053,"about_ca_topic_score_gemma":0.0001007419,"domain_scores_codex":[0.9992243,0.00001193521,0.0001296673,0.0003427536,0.000153951,0.0001374112],"domain_scores_gemma":[0.9992791,0.0001093248,0.00005756942,0.0004348558,0.00004407367,0.00007508155],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00004281009,0.0001084183,0.02603385,0.00001920893,0.00001973868,0.00002476329,0.0008394358,0.00004816058,0.003610101,0.6153198,0.002693424,0.3512402],"study_design_scores_gemma":[0.004955229,0.0007770135,0.7198321,0.0004617418,0.00002281913,0.0005234833,0.0002283538,0.05175205,0.07923075,0.1134746,0.02740342,0.001338347],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06235385,0.00009062247,0.9350342,0.0005762143,0.00001896248,0.0001270434,0.000001251377,0.0003008349,0.001497088],"genre_scores_gemma":[0.6306667,0.0000531858,0.3690935,0.0001397254,0.000005938151,0.000006087796,0.000002151246,0.000003406055,0.00002929126],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6937983,"threshold_uncertainty_score":0.2947059,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0216262061828978,"score_gpt":0.2627378892251433,"score_spread":0.2411116830422455,"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."}}