{"id":"W2912895282","doi":"10.1016/j.neucom.2018.11.100","title":"Pre-processing approaches for imbalanced distributions in regression","year":2019,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":130,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"European Regional Development Fund; Fundação para a Ciência e a Tecnologia","keywords":"Computer science; Regression; Machine learning; Variable (mathematics); Relevance (law); Regression analysis; Artificial intelligence; Context (archaeology); Feature selection; Set (abstract data type); Data mining; Mathematics; Statistics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000312835,0.0001402926,0.0001774154,0.0001172571,0.0001272482,0.0001554194,0.0008109495,0.00006631316,0.000001054713],"category_scores_gemma":[0.00007960042,0.0001304592,0.0000467855,0.0004846297,0.00002076808,0.0005119629,0.0002736837,0.0001796605,0.000009805332],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006065127,"about_ca_system_score_gemma":0.00006292711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002921887,"about_ca_topic_score_gemma":5.916257e-7,"domain_scores_codex":[0.998585,0.00005318557,0.0003052262,0.0005663274,0.0001561135,0.0003341509],"domain_scores_gemma":[0.9990228,0.0001428015,0.0001853403,0.0005532581,0.0000529815,0.00004283051],"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":[0.00002316316,0.0001811023,0.02264263,0.000229981,0.000003974572,0.000003379657,0.0006091256,0.001242776,0.0233996,0.06456565,0.000891034,0.8862076],"study_design_scores_gemma":[0.0004681148,0.00005405276,0.05397982,0.0001581389,0.000001538142,0.000008830089,0.0000178775,0.9235759,0.01495003,0.003125796,0.00343443,0.00022548],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06668311,0.00003273218,0.9309683,0.0004790309,0.0001454183,0.0006062023,0.000006269956,0.000467029,0.0006118909],"genre_scores_gemma":[0.8459752,0.000001784115,0.1537273,0.00008961211,0.00004032136,0.00006200092,0.00002922761,0.00001144336,0.00006307198],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9223331,"threshold_uncertainty_score":0.5319971,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03953302892903467,"score_gpt":0.2872695688861338,"score_spread":0.2477365399570991,"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."}}