{"id":"W2023639956","doi":"10.1111/j.0824-7935.2004.t01-1-00228.x","title":"A Multiple Resampling Method for Learning from Imbalanced Data Sets","year":2004,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":1022,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Medical Protective Association; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Dalhousie University","keywords":"Undersampling; Oversampling; Resampling; Computer science; Machine learning; Artificial intelligence; Class (philosophy); Scheme (mathematics); Task (project management); Data mining; Pattern recognition (psychology); Mathematics; Bandwidth (computing); Engineering","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":[0.0005912044,0.000170555,0.0001904352,0.0001114447,0.0002466361,0.0002240389,0.002510355,0.00007432677,0.000007587821],"category_scores_gemma":[0.001042111,0.0001820849,0.00004833495,0.0003715914,0.0000523561,0.0008704952,0.0006677986,0.0002127445,0.00006528133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001046047,"about_ca_system_score_gemma":0.0001884907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001156245,"about_ca_topic_score_gemma":0.00001310205,"domain_scores_codex":[0.9980307,0.00007360439,0.0004202985,0.0008785095,0.0003250194,0.0002719278],"domain_scores_gemma":[0.996691,0.001698712,0.0002172096,0.001003679,0.0003043317,0.00008505763],"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":[0.00002143019,0.00007855353,0.0002387481,0.00001541981,0.00003085788,0.000003436541,0.000499364,0.7082524,0.001750825,0.138056,0.0005056058,0.1505474],"study_design_scores_gemma":[0.000135511,0.00003150521,0.00060933,0.00003526195,0.000003530049,0.000005079946,0.00002751347,0.7290077,0.008515215,0.2593768,0.002085436,0.0001671906],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002567119,0.0001015517,0.9973353,0.0009668512,0.0002035663,0.0003522985,0.0001619051,0.0005615682,0.00006026378],"genre_scores_gemma":[0.2495023,0.00001107783,0.7489188,0.0003085135,0.00005589297,0.00005307359,0.001123354,0.0000128791,0.00001411219],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2492456,"threshold_uncertainty_score":0.7425206,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1485671637564458,"score_gpt":0.3960542626513615,"score_spread":0.2474870988949157,"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."}}