{"id":"W2166045895","doi":"10.1007/11731139_15","title":"Boosting Prediction Accuracy on Imbalanced Datasets with SVM Ensembles","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":149,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"","keywords":"Boosting (machine learning); Computer science; Support vector machine; Artificial intelligence; Machine learning; Data mining; Sampling (signal processing); Context (archaeology); Ensemble learning; Oversampling; Pattern recognition (psychology); Data sampling; Bandwidth (computing)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007230949,0.0006447018,0.0005011036,0.0008650728,0.0003649913,0.0007445363,0.003766307,0.0003132116,0.00000799809],"category_scores_gemma":[0.0001882783,0.0005441923,0.00006782109,0.0007072255,0.0005769355,0.001316939,0.0009130203,0.0009192692,0.00004255215],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004387645,"about_ca_system_score_gemma":0.0004641849,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003183942,"about_ca_topic_score_gemma":0.00003899021,"domain_scores_codex":[0.9952155,0.00004497025,0.0006274629,0.002081851,0.001325152,0.0007050276],"domain_scores_gemma":[0.9955117,0.0007370113,0.0006054222,0.002778856,0.0002278914,0.0001391768],"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":[0.00004253322,0.0001219458,0.0003271952,0.00009605936,0.00002328889,0.0002062745,0.0002499663,0.02834466,0.002069205,0.03474829,0.003946203,0.9298244],"study_design_scores_gemma":[0.001354552,0.00150662,0.003971905,0.003471405,0.0000353489,0.0004081308,3.639459e-7,0.8018651,0.05131619,0.09681084,0.03626275,0.002996763],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00005150056,0.00008517252,0.9925771,0.0005582008,0.0005911415,0.0006001991,0.0002437742,0.0007448418,0.004548123],"genre_scores_gemma":[0.1408366,0.00006580652,0.854803,0.002290781,0.0007294677,0.0000626413,0.0007817819,0.00008992726,0.0003400038],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9268276,"threshold_uncertainty_score":0.999701,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0174732329986504,"score_gpt":0.253741026703638,"score_spread":0.2362677937049876,"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."}}