{"id":"W2504431993","doi":"10.1145/2948068","title":"The Convergence Behavior of Naive Bayes on Large Sparse Datasets","year":2016,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Naive Bayes classifier; Computer science; Machine learning; Missing data; Bayes' theorem; Artificial intelligence; Convergence (economics); Data mining; Bayesian probability; Support vector machine","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03662071,0.001379853,0.002446742,0.003578983,0.00194114,0.002782564,0.002111165,0.00234012,0.001748873],"category_scores_gemma":[0.1798772,0.0008991663,0.001350531,0.002164804,0.003616876,0.006263993,0.00252599,0.003621093,0.0008480089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00243485,"about_ca_system_score_gemma":0.001975697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004712497,"about_ca_topic_score_gemma":0.003403174,"domain_scores_codex":[0.9835578,0.009208647,0.0007935746,0.002027664,0.00361214,0.0008002378],"domain_scores_gemma":[0.8319974,0.1399123,0.004686417,0.009698394,0.01208273,0.001622687],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00163393,0.0004143298,0.03283789,0.00106157,0.0005448213,0.0005932128,0.001679861,0.5049282,0.004500951,0.171064,0.01414255,0.2665986],"study_design_scores_gemma":[0.00006888292,0.0001527159,0.001955651,0.0001453485,0.00003623563,0.000284537,0.0001762059,0.8470767,0.001434693,0.1472828,0.001341053,0.00004518577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09432787,0.002971777,0.8919097,0.003434048,0.0001921118,0.000345948,0.0004199694,0.001186371,0.005212131],"genre_scores_gemma":[0.6786148,0.001512285,0.3140092,0.001321331,0.0003244362,0.0005516678,0.001200377,0.0003377174,0.002128234],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03662071,"threshold_uncertainty_score":0.1936711,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05267241250637728,"score_gpt":0.3180910509676954,"score_spread":0.2654186384613181,"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."}}