{"id":"W2068258779","doi":"10.1109/acii.2013.47","title":"Facing Imbalanced Data--Recommendations for the Use of Performance Metrics","year":2013,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":806,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Mental Health; McMaster University; National Institutes of Health; University of Northern British Columbia","keywords":"Skew; Receiver operating characteristic; Computer science; Artificial intelligence; Machine learning; Precision and recall; Kappa; Pattern recognition (psychology); Statistics; Mathematics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1927615,0.003523107,0.006964528,0.01177033,0.00282944,0.01570882,0.008011551,0.005968012,0.002377681],"category_scores_gemma":[0.5096892,0.001782119,0.002288072,0.01044801,0.005323227,0.02682479,0.007585561,0.008188665,0.002947677],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005601122,"about_ca_system_score_gemma":0.006309843,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004742782,"about_ca_topic_score_gemma":0.003795794,"domain_scores_codex":[0.8832929,0.05431875,0.01614493,0.0123687,0.03193374,0.001940917],"domain_scores_gemma":[0.4797066,0.2720914,0.03772033,0.07417536,0.1273591,0.008947275],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008604572,0.0007290344,0.07929391,0.001791669,0.0007286845,0.0002419894,0.002041185,0.02706338,0.004719854,0.04336506,0.07655354,0.7626113],"study_design_scores_gemma":[0.0006031445,0.001544691,0.03809402,0.005299142,0.0006636988,0.001281189,0.005029681,0.3558243,0.02148849,0.4616138,0.1076207,0.0009370893],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03020939,0.01801861,0.8833676,0.04868975,0.002469717,0.001524939,0.002012909,0.00722289,0.006484203],"genre_scores_gemma":[0.1873922,0.005046889,0.7899827,0.005970465,0.002047464,0.002646924,0.002613941,0.002286945,0.002012413],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1927615,"threshold_uncertainty_score":0.9954689,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2246192492723406,"score_gpt":0.3280352919055073,"score_spread":0.1034160426331666,"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."}}