{"id":"W4388736371","doi":"10.1016/j.ejor.2023.11.016","title":"Column generation-based prototype learning for optimizing area under the receiver operating characteristic curve","year":2023,"lang":"en","type":"article","venue":"European Journal of Operational Research","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"","keywords":"Overfitting; Ranking (information retrieval); Computer science; Maximization; Receiver operating characteristic; Artificial intelligence; Machine learning; Feature selection; Binary classification; Support vector machine; Metric (unit); Pattern recognition (psychology); Mathematics; Mathematical optimization; 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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.01072725,0.0001086155,0.0001358982,0.00031299,0.001125591,0.001065486,0.001207573,0.00002446079,0.00004297977],"category_scores_gemma":[0.002077534,0.00008009896,0.00006817046,0.000773628,0.0001030275,0.0006841703,0.0001761543,0.0006210825,0.0000836352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001179409,"about_ca_system_score_gemma":0.0005923837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001879685,"about_ca_topic_score_gemma":0.00000101104,"domain_scores_codex":[0.9963243,0.00164311,0.0005350103,0.0002646368,0.0009193472,0.0003135663],"domain_scores_gemma":[0.9962502,0.0009654693,0.0002069982,0.000333215,0.002153586,0.00009049768],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002350036,0.0002875016,0.001075081,0.00009657764,0.0001712906,0.0002086313,0.002785997,0.3642663,0.3933236,0.07997008,0.1008516,0.0567284],"study_design_scores_gemma":[0.0005484652,0.000666395,0.006561258,0.00009533166,0.000003908813,0.00003797048,0.0001601434,0.9601972,0.007500042,0.0001551314,0.02391037,0.0001638038],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01396461,0.00003655508,0.9740354,0.01024145,0.0001966263,0.0007900828,0.000009104098,0.00008445701,0.0006417134],"genre_scores_gemma":[0.9004883,0.00004253932,0.09703312,0.00047404,0.0006349597,0.0001231191,0.00009583974,0.00003753903,0.001070534],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8865237,"threshold_uncertainty_score":0.9999715,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2154587744986443,"score_gpt":0.3905772167184525,"score_spread":0.1751184422198082,"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."}}