{"id":"W3046322697","doi":"10.11159/mvml20.107","title":"Taxonomy of Modelling Strategies for Handling Imbalanced Datasets","year":2020,"lang":"en","type":"article","venue":"Proceedings of the World Congress on Electrical Engineering and Computer Systems and Science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Taxonomy (biology); Artificial intelligence; Data science; Machine learning; Data mining; Ecology; Biology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002943549,0.0001147872,0.000223889,0.0001278955,0.0001059917,0.0002739677,0.0008757026,0.0000226272,3.646704e-8],"category_scores_gemma":[0.00003385205,0.00008483708,0.00002554684,0.0007302962,0.0001047128,0.0004958668,0.000211882,0.0001028339,4.700524e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001315429,"about_ca_system_score_gemma":0.00004298285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004651942,"about_ca_topic_score_gemma":6.880091e-8,"domain_scores_codex":[0.9989831,0.000002440838,0.0002541777,0.0003567253,0.0002035903,0.0001999571],"domain_scores_gemma":[0.9993661,0.00008661282,0.00017469,0.0001365858,0.0001518738,0.00008415196],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002026644,0.00002645,0.000231175,0.0004704671,0.00001704701,1.712013e-7,0.0001568696,0.03706798,0.03021361,0.9252142,0.0008755501,0.005706205],"study_design_scores_gemma":[0.0001338005,0.0001002577,0.00007283048,0.0001407036,0.00000337527,0.000002534938,0.000006682187,0.9818145,0.0161279,0.0001242253,0.001376552,0.00009665776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01766291,0.0001872152,0.9810873,0.0002719467,0.0002453669,0.0003941295,0.00001297935,0.00009529708,0.00004284572],"genre_scores_gemma":[0.9622361,0.00001345732,0.03760022,0.00004658101,0.00005136114,0.00003950483,4.69326e-7,0.000004561127,0.000007751104],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9447465,"threshold_uncertainty_score":0.3459556,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02562380933456232,"score_gpt":0.2267311871030607,"score_spread":0.2011073777684984,"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."}}