{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002243609,0.001057837,0.001790954,0.0008642594,0.0007180879,0.0008413875,0.001466458,0.001158268,0.001057548],"category_scores_gemma":[0.005616688,0.0006303575,0.001389597,0.0009260464,0.000408392,0.001366871,0.001158438,0.001665474,0.0007255427],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004725152,"about_ca_system_score_gemma":0.001136813,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003416354,"about_ca_topic_score_gemma":0.007025584,"domain_scores_codex":[0.9991997,0.0002662068,0.00004845602,0.000188673,0.0001824774,0.00011445],"domain_scores_gemma":[0.9983436,0.0006044531,0.00009360242,0.0003288674,0.0004954288,0.0001341385],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000128648,0.000146881,0.003701554,0.00005164866,0.0001643234,0.00008696139,0.00007278643,0.8748579,0.003748106,0.001934296,0.003783545,0.1113234],"study_design_scores_gemma":[0.000007110352,0.00002226254,0.0002194553,0.000003073902,0.00001098121,0.00001045056,0.000007734292,0.9974697,0.0006599152,0.00131021,0.0002748911,0.000004288138],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1357269,0.0006052385,0.8584974,0.0002371678,0.0001698925,0.0001053093,0.0003807188,0.002595692,0.001681646],"genre_scores_gemma":[0.6313703,0.0002852097,0.364113,0.000277055,0.0001154309,0.0002806844,0.001880527,0.0002966738,0.001381143],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003416354,"threshold_uncertainty_score":0.0118655,"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."}}