{"id":"W2796045805","doi":"10.1007/s10479-018-2830-2","title":"A clustering-based feature selection method for automatically generated relational attributes","year":2018,"lang":"en","type":"article","venue":"Annals of Operations Research","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Data mining; Cluster analysis; Feature selection; Selection (genetic algorithm); Set (abstract data type); Table (database); Relational database; Lasso (programming language); Machine learning; Artificial intelligence","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":[0.001932141,0.00007970246,0.0001163218,0.0002556372,0.0007142877,0.0002421458,0.0005007383,0.00008090604,0.00003729322],"category_scores_gemma":[0.0006204255,0.00007282575,0.00004769814,0.001248742,0.0001068346,0.0003745995,0.0001193032,0.0001557974,0.00003421141],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001982064,"about_ca_system_score_gemma":0.0004146358,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005946091,"about_ca_topic_score_gemma":0.0001788951,"domain_scores_codex":[0.9985752,0.0001866115,0.0002302289,0.0003258045,0.0003975646,0.0002846087],"domain_scores_gemma":[0.9960635,0.0004069433,0.00002770142,0.0003834284,0.003034139,0.00008434311],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006484617,0.00079318,0.000144053,0.0000925668,0.0001535231,0.000001231801,0.0009814063,0.0698441,0.05621543,0.4514486,0.2894125,0.1308486],"study_design_scores_gemma":[0.0001633337,0.0002953264,0.0007668976,0.00001731674,0.000002105073,0.000002940491,0.000008679969,0.9617853,0.02368153,0.0006399522,0.01256137,0.00007528491],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001343331,0.00002428465,0.9765356,0.02127125,0.0000398602,0.0004028215,0.00009658815,0.00006997984,0.0002162942],"genre_scores_gemma":[0.03534786,0.000003957995,0.9628729,0.0002853756,0.0001675417,0.0002785134,0.0001474643,0.000009000909,0.0008873796],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8919412,"threshold_uncertainty_score":0.5493796,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2624505622004498,"score_gpt":0.4869737738800862,"score_spread":0.2245232116796365,"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."}}