{"id":"W1585078559","doi":"10.1109/ccis.2014.7175758","title":"Building diverse and optimized ensembles of gradient boosted trees for high-dimensional data","year":2014,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Boosting (machine learning); Computation; Gradient boosting; Artificial intelligence; Machine learning; Ensemble learning; Tree (set theory); Feature selection; Big data; Reduction (mathematics); Cloud computing; Decision tree; Data mining; Random forest; Algorithm","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":[0.000434608,0.00006437703,0.0001152518,0.00005729558,0.00008207193,0.00004177599,0.000481608,0.00002276714,0.000005500397],"category_scores_gemma":[0.0001989024,0.00005014536,0.00001315865,0.00006649608,0.00002921782,0.0002612362,0.0004365117,0.00003262621,0.00000149236],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004091808,"about_ca_system_score_gemma":0.00001144757,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001275604,"about_ca_topic_score_gemma":0.00001785069,"domain_scores_codex":[0.999291,0.0000514919,0.0001373863,0.0003088239,0.0001138677,0.00009743259],"domain_scores_gemma":[0.9989162,0.0002860358,0.00008357222,0.0006270129,0.00004294075,0.00004422248],"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":[0.00006108875,0.00008707232,0.0007499331,0.00003876848,0.00003121251,4.620701e-7,0.0001109693,0.001361448,0.01377918,0.7163283,0.00665573,0.2607959],"study_design_scores_gemma":[0.0008353087,0.00008083676,0.006013995,0.00001303488,0.00001108465,0.000002651313,0.00000793383,0.9851517,0.001282091,0.001871492,0.004644057,0.00008581441],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05875323,0.00002874493,0.9399147,0.0009110285,0.00009116136,0.00009427321,0.00002289644,0.00006056882,0.0001234044],"genre_scores_gemma":[0.522689,0.000003706587,0.4770849,0.00005448609,0.00001555506,0.000002402752,0.00007276166,0.000002317399,0.00007482441],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9837903,"threshold_uncertainty_score":0.2044868,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03842223823157406,"score_gpt":0.2849758958860554,"score_spread":0.2465536576544813,"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."}}