{"id":"W4412049267","doi":"10.1016/j.eswa.2025.128920","title":"A comprehensive review on data-level methods for imbalanced data classification","year":2025,"lang":"en","type":"review","venue":"Expert Systems with Applications","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Artificial intelligence; Data classification; Data mining; Pattern recognition (psychology); Machine learning","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":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00148097,0.0008062026,0.002472767,0.0003982861,0.000402269,0.0003592012,0.014444,0.0003629952,0.000002889646],"category_scores_gemma":[0.0003235443,0.0006127026,0.0001644228,0.001911137,0.0001191224,0.0007890381,0.001810371,0.0004428024,0.0000955862],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002988368,"about_ca_system_score_gemma":0.001259588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002411516,"about_ca_topic_score_gemma":0.000001512961,"domain_scores_codex":[0.9934453,0.0008141714,0.001650706,0.003143893,0.0004627504,0.0004831475],"domain_scores_gemma":[0.9734556,0.002417864,0.001699519,0.02164223,0.0006183637,0.0001664319],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001800613,0.0000796461,3.452367e-8,0.03776914,0.0001123027,2.550074e-7,0.000007934185,1.6506e-7,0.000002547785,0.03390319,0.13449,0.793633],"study_design_scores_gemma":[0.0001435382,0.00003698685,5.708633e-7,0.04161094,0.0002471376,0.00003002145,0.00001120602,0.004378712,0.000002183185,0.00006861555,0.9528704,0.0005997401],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[2.282192e-11,0.4927626,0.4945533,0.0003428785,0.0001493441,0.008144401,0.003302865,0.0004394158,0.0003051752],"genre_scores_gemma":[1.834335e-8,0.5567122,0.3888886,0.0004121977,0.0001527366,0.02896061,0.02446276,0.00004517368,0.0003657118],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.8183804,"threshold_uncertainty_score":0.9996324,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3769644452128858,"score_gpt":0.5124121553384758,"score_spread":0.13544771012559,"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."}}