{"id":"W752888290","doi":"10.1007/s10844-015-0368-1","title":"Types of minority class examples and their influence on learning classifiers from imbalanced data","year":2015,"lang":"en","type":"article","venue":"Journal of Intelligent Information Systems","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":287,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Ottawa","keywords":"Computer science; Outlier; Machine learning; Artificial intelligence; Identification (biology); Class (philosophy); Classifier (UML); Neighbourhood (mathematics); Data mining; Data type; 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":[],"consensus_categories":[],"category_scores_codex":[0.01447692,0.0008253405,0.00106036,0.002456373,0.001011576,0.00258091,0.000873751,0.001124423,0.0005305763],"category_scores_gemma":[0.07782118,0.0003881007,0.0006653268,0.001303614,0.001891854,0.003527752,0.001675586,0.001393664,0.0002380791],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007369442,"about_ca_system_score_gemma":0.000432668,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008182069,"about_ca_topic_score_gemma":0.0008984889,"domain_scores_codex":[0.9898114,0.004118625,0.000768271,0.001571038,0.003348244,0.0003824949],"domain_scores_gemma":[0.882947,0.09750053,0.006125462,0.006334731,0.006018253,0.001073913],"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":[0.003427533,0.0005729983,0.2269756,0.001109336,0.0004647976,0.001285757,0.004555419,0.1915412,0.03758106,0.009722107,0.003360027,0.5194042],"study_design_scores_gemma":[0.0000633952,0.000859607,0.1044574,0.0003031906,0.0003190578,0.001942618,0.003068864,0.7985876,0.06197484,0.02283254,0.005373615,0.0002172188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8546156,0.001783219,0.1397681,0.000571628,0.000130509,0.0001461919,0.0001972341,0.000318057,0.002469531],"genre_scores_gemma":[0.9580126,0.0003137265,0.04093641,0.00005524167,0.00005938441,0.00006170933,0.0002262549,0.00007597881,0.0002587917],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01447692,"threshold_uncertainty_score":0.07656223,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07618345526224594,"score_gpt":0.2870352410138041,"score_spread":0.2108517857515581,"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."}}