{"id":"W2897650261","doi":"10.1016/j.eswa.2024.124863","title":"An empirical evaluation of imbalanced data strategies from a practitioner’s point of view","year":2024,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Support vector machine; Artificial intelligence; Gradient boosting; Classifier (UML); Boosting (machine learning); Binary classification; Computer science; Correlation; Random forest; Binary number; Pattern recognition (psychology); Cut-point; Correlation coefficient; Machine learning; Mathematics; Data mining; Statistics","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":[0.0009092326,0.0001347757,0.0002399626,0.0001307669,0.00005989311,0.0002085909,0.00140413,0.000069733,0.00001633728],"category_scores_gemma":[0.00002872232,0.0001079443,0.000023286,0.0006649286,0.00008673064,0.002009813,0.0001239726,0.00009516704,0.00001787704],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007911486,"about_ca_system_score_gemma":0.0005915921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003758298,"about_ca_topic_score_gemma":0.00002399158,"domain_scores_codex":[0.9978175,0.0002224697,0.0005159825,0.000641833,0.0006789436,0.0001233219],"domain_scores_gemma":[0.9960393,0.0001599195,0.0002855557,0.00297139,0.0004819518,0.00006193409],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003245875,0.001154128,0.0003792635,0.0005461685,0.0003288834,0.00000324894,0.006360598,0.001100427,0.1866637,0.6869045,0.03217365,0.08435295],"study_design_scores_gemma":[0.0003656918,0.0001579402,0.001693374,0.0005270654,0.00007186831,0.00002818157,0.001746387,0.9133852,0.01234992,0.00764396,0.06166374,0.0003666954],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004787373,0.002893239,0.9930652,0.0006490818,0.00008311902,0.001185813,0.0003559973,0.0003923647,0.0008964048],"genre_scores_gemma":[0.8903576,0.00009296905,0.1066082,0.00003470359,0.00009809853,0.0018159,0.0009686756,0.00001519754,0.000008688356],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9122847,"threshold_uncertainty_score":0.440184,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09491998972119446,"score_gpt":0.4088449582014986,"score_spread":0.3139249684803041,"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."}}