{"id":"W4316469706","doi":"10.3390/info14010054","title":"A Comparison of Undersampling, Oversampling, and SMOTE Methods for Dealing with Imbalanced Classification in Educational Data Mining","year":2023,"lang":"en","type":"article","venue":"Information","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":340,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Undersampling; Oversampling; Resampling; Random forest; Computer science; Machine learning; Class (philosophy); Data mining; Sampling (signal processing); Artificial intelligence; Bandwidth (computing)","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":[0.0009683475,0.0000886963,0.0001551233,0.0002932725,0.00007535575,0.0001030364,0.0005421008,0.00005746223,0.000001336778],"category_scores_gemma":[0.000332891,0.00008768291,0.00001101586,0.0004468172,0.0000412298,0.002283878,0.0001594059,0.00006780628,0.000002547192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005303537,"about_ca_system_score_gemma":0.0001038215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002968286,"about_ca_topic_score_gemma":0.00001403879,"domain_scores_codex":[0.9989897,0.00003045496,0.0004736742,0.0002044497,0.0001530755,0.0001486641],"domain_scores_gemma":[0.9983493,0.0004581049,0.0004136715,0.000604413,0.0001439146,0.00003059866],"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":[0.00006531984,0.00006155464,0.02665085,0.0003214801,0.00003109942,6.180012e-8,0.009385664,0.001103155,0.006587048,0.287988,0.001561066,0.6662447],"study_design_scores_gemma":[0.0003550835,0.00004511188,0.0471288,0.00007044253,0.000005008169,0.000001509578,0.0005735024,0.9419191,0.002192307,0.003243722,0.004345863,0.0001195354],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007340113,0.00002388627,0.9909887,0.0008116769,0.00006457167,0.0003468254,0.00003685788,0.0001430677,0.0002442492],"genre_scores_gemma":[0.2953897,0.00002009535,0.7036268,0.00004480202,0.000009318019,0.00004715758,0.0008535706,0.000004113036,0.000004403564],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.940816,"threshold_uncertainty_score":0.3575605,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1915929103132564,"score_gpt":0.4664089199150849,"score_spread":0.2748160096018285,"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."}}