{"id":"W4287183744","doi":"10.48550/arxiv.2105.04009","title":"RB-CCR: Radial-Based Combined Cleaning and Resampling algorithm for\\n imbalanced data classification","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Resampling; Oversampling; Benchmark (surveying); Computer science; Binary classification; Artificial intelligence; Binary number; Prior probability; Class (philosophy); Data mining; Machine learning; Pattern recognition (psychology); Algorithm; Mathematics; Support vector machine; Bayesian probability","routes":{"ca_aff":true,"ca_fund":false,"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":[0.004704794,0.001482233,0.002391137,0.002444033,0.001385262,0.001780827,0.003751872,0.001983898,0.002711709],"category_scores_gemma":[0.0113927,0.0006708627,0.001761951,0.002060351,0.001024855,0.001880334,0.002086394,0.002697265,0.002833023],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001157071,"about_ca_system_score_gemma":0.002672552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01267096,"about_ca_topic_score_gemma":0.01453983,"domain_scores_codex":[0.9967135,0.0007968709,0.0002771461,0.0007842449,0.001181737,0.0002463823],"domain_scores_gemma":[0.9955759,0.001234249,0.0004427463,0.001121446,0.001456769,0.0001687312],"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":[0.0008642168,0.0003834199,0.005775648,0.0003691162,0.0002649991,0.0002261255,0.0004116044,0.1115411,0.01806212,0.009442911,0.02491696,0.8277417],"study_design_scores_gemma":[0.00008925303,0.0001112802,0.001249067,0.00003842769,0.0000563693,0.00021848,0.00007593858,0.9705621,0.0126058,0.005581096,0.009358929,0.00005321112],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01293239,0.001156718,0.978515,0.00030791,0.0001336879,0.0002114731,0.0002679795,0.005566988,0.0009078434],"genre_scores_gemma":[0.1290776,0.0004572271,0.8636037,0.0006733899,0.0001415771,0.0004588602,0.00209352,0.0007392053,0.002754923],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01267096,"threshold_uncertainty_score":0.02519441,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1662660800452708,"score_gpt":0.2443103710650201,"score_spread":0.07804429101974933,"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."}}