{"id":"W4403913051","doi":"10.1016/j.mlwa.2024.100597","title":"Enhancing SMOTE for imbalanced data with abnormal minority instances","year":2024,"lang":"en","type":"article","venue":"Machine Learning with Applications","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data mining; Artificial intelligence","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":[0.003368152,0.001159746,0.001353981,0.001189412,0.000728638,0.001273247,0.001452581,0.001194681,0.001054661],"category_scores_gemma":[0.009929182,0.0004197545,0.001272505,0.000748002,0.0008117782,0.001757116,0.00204909,0.002239875,0.000730226],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007215033,"about_ca_system_score_gemma":0.001978778,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004840742,"about_ca_topic_score_gemma":0.01028257,"domain_scores_codex":[0.9986486,0.0003780736,0.00009038355,0.00028172,0.0004324721,0.0001688035],"domain_scores_gemma":[0.9960724,0.001938582,0.0002892369,0.0003942139,0.001124102,0.0001814814],"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":[0.0007820072,0.0005224849,0.01838941,0.0003456241,0.0002999981,0.0002174318,0.0003612902,0.4694421,0.02340619,0.009125152,0.01107124,0.4660371],"study_design_scores_gemma":[0.00002180645,0.00005943673,0.0006972972,0.00001203306,0.00001464486,0.00003050483,0.00003694529,0.9921284,0.003173389,0.002297574,0.001517335,0.00001072983],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08672862,0.0007407998,0.9064832,0.0006323924,0.000214281,0.0001746455,0.0002956773,0.00268739,0.002043061],"genre_scores_gemma":[0.5994841,0.000454811,0.3899616,0.001094058,0.0002802364,0.0004123973,0.002781674,0.0005027485,0.005028394],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004840742,"threshold_uncertainty_score":0.01781273,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01791840181232909,"score_gpt":0.2855672153657165,"score_spread":0.2676488135533874,"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."}}