{"id":"W3149775087","doi":"10.18280/isi.260107","title":"Opportunities and Challenges of Feature Selection Methods for High Dimensional Data: A Review","year":2021,"lang":"en","type":"review","venue":"Ingénierie des systèmes d information","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Feature selection; Big data; Overfitting; Computer science; Dimensionality reduction; SPARK (programming language); Data science; Selection (genetic algorithm); Feature (linguistics); Machine learning; Curse of dimensionality; Artificial intelligence; Data mining; The Internet; Dimension (graph theory); Process (computing); Data pre-processing; World Wide Web; Artificial neural network","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029096,0.001044854,0.001731901,0.003105043,0.0003531148,0.00136956,0.001374824,0.0008311548,0.001666414],"category_scores_gemma":[0.005919273,0.0004234645,0.001608178,0.005262487,0.0006352905,0.002151188,0.0005540546,0.001066084,0.0009113408],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000529845,"about_ca_system_score_gemma":0.001162082,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00191741,"about_ca_topic_score_gemma":0.001483865,"domain_scores_codex":[0.9987928,0.0002623607,0.0001743685,0.000232858,0.0004845099,0.00005324552],"domain_scores_gemma":[0.9947599,0.003768333,0.0002500153,0.0001437687,0.001020258,0.00005778504],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005203776,0.00006451798,0.0009766208,0.007016163,0.0001743071,0.00008841577,0.00006322999,0.001935023,0.0007816368,0.003391324,0.01138214,0.9740747],"study_design_scores_gemma":[0.00009689575,0.0007316548,0.01002178,0.01193194,0.001154354,0.002654951,0.0005734506,0.02307272,0.005037136,0.03366038,0.9108055,0.0002591218],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001414998,0.9725885,0.02206792,0.001431194,0.0005384878,0.00004534833,0.0001076222,0.0001137492,0.001692231],"genre_scores_gemma":[0.01567984,0.9624128,0.01856987,0.0006372643,0.001214213,0.0001066383,0.0003366952,0.00004295216,0.0009998078],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.003105043,"threshold_uncertainty_score":0.01538759,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2636172756962408,"score_gpt":0.3835999700800877,"score_spread":0.1199826943838469,"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."}}