{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01012599,0.001029702,0.002092245,0.002456422,0.000702399,0.001710349,0.002086115,0.001133151,0.0008363509],"category_scores_gemma":[0.0198863,0.0006702857,0.001443948,0.00230897,0.0008285598,0.002178635,0.002025449,0.002533391,0.0007567537],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007716983,"about_ca_system_score_gemma":0.0009543257,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000943973,"about_ca_topic_score_gemma":0.001077159,"domain_scores_codex":[0.9953701,0.001906347,0.00027151,0.0006042019,0.001617236,0.0002307024],"domain_scores_gemma":[0.9905869,0.004327372,0.0005689799,0.002237852,0.002063448,0.0002154235],"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":[0.0004069439,0.0003718267,0.008087236,0.0002144557,0.0002425807,0.000151637,0.000283609,0.3871716,0.007318225,0.01398506,0.008073177,0.5736937],"study_design_scores_gemma":[0.00003896306,0.00008663099,0.0007896099,0.00002477162,0.00002594687,0.00007759319,0.00003348284,0.9731848,0.005327262,0.01701707,0.003371358,0.00002251456],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02402752,0.0005182122,0.9717959,0.0003029614,0.0001826351,0.0002745624,0.0001621339,0.001482045,0.001253995],"genre_scores_gemma":[0.2527709,0.0004439974,0.7436776,0.0003648413,0.0002268879,0.0006070378,0.0008399132,0.0001824163,0.0008863565],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01012599,"threshold_uncertainty_score":0.05355203,"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."}}