{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001419357,0.0003566745,0.001335227,0.0003672155,0.000174011,0.000260491,0.0004057398,0.0002659829,0.00005706171],"category_scores_gemma":[0.0009780454,0.0002892363,0.0001340681,0.0004850367,0.0001089276,0.005661146,0.0004775714,0.0001692298,0.000008954484],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004976751,"about_ca_system_score_gemma":0.0001721725,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005741894,"about_ca_topic_score_gemma":0.000009432605,"domain_scores_codex":[0.998352,0.00005880028,0.0008971515,0.0002768234,0.0002071445,0.0002081183],"domain_scores_gemma":[0.9971669,0.0001993952,0.001341935,0.0004695292,0.0008079292,0.00001429645],"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":[0.000002760978,0.000008248296,2.430867e-7,0.244812,0.00007264972,2.666437e-7,0.0000113652,2.706288e-7,6.996131e-8,0.01728783,0.005163336,0.7326409],"study_design_scores_gemma":[0.00005880869,0.00000850479,0.000003549507,0.0640987,0.0008417694,0.00004149908,0.0000655088,0.0002879571,8.751272e-7,0.0005679844,0.9337512,0.0002736497],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[3.762458e-7,0.9887099,0.008830454,0.0002594485,0.000466606,0.0008834746,0.0002099316,0.00005648303,0.0005833416],"genre_scores_gemma":[0.000002233727,0.9821763,0.008217384,0.0002707957,0.0003806007,0.0001646215,0.008715476,0.00002492472,0.0000476645],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9285879,"threshold_uncertainty_score":0.999956,"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."}}