{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004304302,0.0001949695,0.0001744961,0.000132496,0.0003726655,0.0004082784,0.001608982,0.00005119053,0.00000615036],"category_scores_gemma":[0.0000385216,0.000148462,0.00002252737,0.0008128356,0.00008461382,0.000996245,0.0002612361,0.0003581706,0.00002747212],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000529724,"about_ca_system_score_gemma":0.0001848976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005906153,"about_ca_topic_score_gemma":0.0001827858,"domain_scores_codex":[0.9983096,0.00003851251,0.0002396703,0.0008561003,0.0002519881,0.000304176],"domain_scores_gemma":[0.997938,0.0002258824,0.0001243596,0.001520205,0.0001128051,0.00007877646],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001050696,0.0002241849,0.01772629,0.0008084594,0.000212657,0.00001535158,0.0008428288,0.000950209,0.00983092,0.5742537,0.00318435,0.3918459],"study_design_scores_gemma":[0.0003838836,0.0002387896,0.003022665,0.0001291903,0.00004234345,0.00005569365,0.00003292732,0.3903707,0.005341982,0.001516736,0.598392,0.000473081],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003407211,0.0004010842,0.9935885,0.001639852,0.00003372865,0.0008039764,0.0001323723,0.00163469,0.001425042],"genre_scores_gemma":[0.3808478,0.00004114923,0.6162663,0.0001215699,0.0001141173,0.001083318,0.0008130688,0.00002746397,0.0006853325],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5952077,"threshold_uncertainty_score":0.6054104,"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."}}