{"id":"W2040010062","doi":"10.1145/1007730.1007736","title":"Learning from imbalanced data sets with boosting and data generation","year":2004,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":606,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Boosting (machine learning); Machine learning; Computer science; Artificial intelligence; Benchmarking; Classifier (UML); Training set; Gradient boosting; Ensemble learning; Data mining; Random forest","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":[0.0003222386,0.0001980615,0.0001673559,0.0001056951,0.0003836424,0.0006368018,0.003432518,0.00007286271,0.000008761832],"category_scores_gemma":[0.0004966659,0.0001807002,0.000008969001,0.0003690996,0.00007639533,0.006221595,0.002521853,0.000273184,0.00006503921],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000469216,"about_ca_system_score_gemma":0.0001044384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001276227,"about_ca_topic_score_gemma":0.0001409449,"domain_scores_codex":[0.9978958,0.00009588418,0.0003138723,0.001135965,0.0003055945,0.000252875],"domain_scores_gemma":[0.9935837,0.0001469891,0.0001909034,0.005908929,0.00009191391,0.0000775059],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004995339,0.0004140445,0.01311982,0.00004740396,0.0002928872,0.0001422116,0.009118505,0.006061779,0.5167028,0.01936595,0.2208476,0.2138371],"study_design_scores_gemma":[0.00466569,0.0005391771,0.01449964,0.000338661,0.0001584736,0.0001302773,0.0007180895,0.7545464,0.08538315,0.01743417,0.1187609,0.002825395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02282449,0.00006450046,0.9509304,0.02507789,0.0000963905,0.0002634567,0.0001226905,0.0005454391,0.00007473868],"genre_scores_gemma":[0.3785406,0.0000515419,0.6110542,0.002644182,0.0002326781,0.00004877903,0.007379863,0.00002236726,0.00002580333],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7484846,"threshold_uncertainty_score":0.7368741,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.145876779440151,"score_gpt":0.3158766600273255,"score_spread":0.1699998805871745,"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."}}