{"id":"W3013316335","doi":"10.29007/h71z","title":"On relationships between imbalance and overlapping of datasets","year":2020,"lang":"en","type":"article","venue":"EPiC series in computing","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"Natural Sciences and Engineering Research Council of Canada; King Abdulaziz City for Science and Technology","keywords":"Support vector machine; Computer science; Precision and recall; Decision tree; Artificial intelligence; Data mining; Machine learning; Recall; k-nearest neighbors algorithm; Pattern recognition (psychology)","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02382487,0.001138385,0.001501888,0.008425708,0.001635616,0.005268331,0.001140968,0.001459391,0.001282125],"category_scores_gemma":[0.2173739,0.0006372517,0.0007161143,0.009774987,0.002970353,0.01279997,0.003273546,0.002482855,0.0002811985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002116668,"about_ca_system_score_gemma":0.001187133,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001460242,"about_ca_topic_score_gemma":0.001319588,"domain_scores_codex":[0.9789619,0.007745746,0.001565222,0.003708834,0.006988555,0.001029766],"domain_scores_gemma":[0.5199134,0.4234082,0.03378182,0.008032373,0.01325902,0.001605204],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00149104,0.0003243257,0.5706674,0.0009734253,0.0007094329,0.00175989,0.001834095,0.07116405,0.002186189,0.04814918,0.007625842,0.2931151],"study_design_scores_gemma":[0.00009835586,0.001196136,0.1897836,0.0009748148,0.0008812179,0.007333425,0.004534618,0.4697954,0.00699025,0.3020839,0.01602676,0.0003015142],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6588987,0.02589004,0.287267,0.006903618,0.0007475497,0.0004044126,0.00163889,0.0008840668,0.01736574],"genre_scores_gemma":[0.95573,0.004248972,0.03663215,0.000470977,0.0008075141,0.000166965,0.001023947,0.0001184248,0.0008010347],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02382487,"threshold_uncertainty_score":0.1259995,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05639342327698976,"score_gpt":0.2835915093782327,"score_spread":0.2271980861012429,"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."}}