{"id":"W129457532","doi":"","title":"Learning from Imbalanced Data Sets: A Comparison of Various Strategies *","year":2000,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":453,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Class (philosophy); Connectionism; Computer science; Artificial intelligence; Machine learning; Training set; Artificial neural network","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":[0.02400543,0.001879342,0.002703425,0.006533719,0.00127085,0.00439275,0.004088454,0.002143413,0.001714628],"category_scores_gemma":[0.03577718,0.0005795167,0.001323531,0.005133166,0.001832078,0.008547195,0.005196169,0.002123755,0.001148078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001718826,"about_ca_system_score_gemma":0.002083384,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002251965,"about_ca_topic_score_gemma":0.002662116,"domain_scores_codex":[0.9896526,0.004268782,0.0008040551,0.001120397,0.003773235,0.0003810179],"domain_scores_gemma":[0.9744574,0.01779977,0.001066551,0.003052195,0.003003283,0.0006207519],"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":[0.001058312,0.0003904634,0.005705711,0.0006843513,0.0004381858,0.00006373014,0.0006650905,0.02783629,0.001107486,0.01531604,0.007371752,0.9393626],"study_design_scores_gemma":[0.000475488,0.001260072,0.00869442,0.0005229979,0.0005201768,0.0005056207,0.002230142,0.8608602,0.009302827,0.09357041,0.02189836,0.0001593054],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1060803,0.02321627,0.8491836,0.003394062,0.0005942018,0.001392454,0.0008075674,0.003310448,0.01202107],"genre_scores_gemma":[0.4724387,0.009083277,0.5104118,0.0008604011,0.0004942407,0.000944025,0.00188323,0.0005303164,0.003353986],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02400543,"threshold_uncertainty_score":0.1269544,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05633284169889121,"score_gpt":0.3302678964709482,"score_spread":0.273935054772057,"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."}}