{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009342495,0.001575454,0.001207579,0.00355686,0.0007495357,0.003490816,0.004281356,0.001679449,0.001547669],"category_scores_gemma":[0.01877189,0.0006194253,0.001850111,0.003389959,0.001326943,0.006113772,0.003055881,0.002261696,0.001123073],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00110357,"about_ca_system_score_gemma":0.001240266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008097509,"about_ca_topic_score_gemma":0.001129171,"domain_scores_codex":[0.9935173,0.001771108,0.0009576834,0.0009527282,0.002524992,0.0002762268],"domain_scores_gemma":[0.9902164,0.003203708,0.001126519,0.003179063,0.002046785,0.0002276143],"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":[0.0003250122,0.0002497894,0.00805128,0.001016536,0.0002731006,0.0004524862,0.0006028482,0.1236845,0.01133623,0.223746,0.01888462,0.6113775],"study_design_scores_gemma":[0.00005871356,0.0002859558,0.002256196,0.0005498437,0.000136991,0.001511639,0.0003225344,0.6632183,0.02436753,0.2094935,0.09763405,0.0001647918],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.004775941,0.00116431,0.9890353,0.0007121142,0.000102832,0.0002029229,0.0003456598,0.001178336,0.002482522],"genre_scores_gemma":[0.1274642,0.003686748,0.8607947,0.0006166359,0.0002316586,0.000909375,0.002613362,0.0004759509,0.003207232],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.009342495,"threshold_uncertainty_score":0.04940844,"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."}}