{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009075864,0.001351658,0.001727163,0.003678196,0.001139495,0.001300113,0.001874241,0.001285528,0.002285483],"category_scores_gemma":[0.01680551,0.0005350061,0.001978857,0.003216411,0.0009281844,0.001939879,0.00174509,0.002361783,0.001651604],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005520767,"about_ca_system_score_gemma":0.001019022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001340776,"about_ca_topic_score_gemma":0.002488831,"domain_scores_codex":[0.994822,0.002018905,0.0003795325,0.0009162609,0.001701358,0.0001619315],"domain_scores_gemma":[0.995429,0.00174242,0.0003855372,0.001303368,0.001011883,0.0001277768],"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":[0.0003029794,0.0002610782,0.002092484,0.0002747707,0.0004372812,0.0001256558,0.0003006044,0.03378593,0.01508341,0.01123307,0.009048969,0.9270537],"study_design_scores_gemma":[0.0001626054,0.0005251495,0.00468505,0.0001010003,0.000290727,0.0007205858,0.0001722808,0.894112,0.03148017,0.03377352,0.03379772,0.000179129],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002921442,0.0001781012,0.9952233,0.00007426459,0.0001180863,0.0002370937,0.00009313384,0.0008511727,0.0003034291],"genre_scores_gemma":[0.03392754,0.0001807916,0.9633854,0.00008011689,0.000181308,0.0005992955,0.0004037748,0.0001473187,0.001094459],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009075864,"threshold_uncertainty_score":0.04799831,"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."}}