{"id":"W2768421170","doi":"10.1016/j.ins.2017.11.041","title":"Automatic feature engineering for regression models with machine learning: An evolutionary computation and statistics hybrid","year":2017,"lang":"en","type":"article","venue":"Information Sciences","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Conselho Nacional de Desenvolvimento Científico e Tecnológico; Natural Sciences and Engineering Research Council of Canada; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Universal","keywords":"Genetic programming; Computer science; Feature engineering; Symbolic regression; Interpretability; Machine learning; Artificial intelligence; Randomness; Feature (linguistics); Benchmark (surveying); Evolutionary computation; Regression; Data mining; Statistics; Mathematics; Deep learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0002897278,0.00009182981,0.00008161336,0.0001045435,0.001543971,0.0006697614,0.0004358886,0.00002393346,0.000001156378],"category_scores_gemma":[0.00005625493,0.00006872068,0.00001134472,0.000100177,0.0001233891,0.006802212,0.00008816165,0.00007427437,0.000002673464],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002115481,"about_ca_system_score_gemma":0.00007771754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002492963,"about_ca_topic_score_gemma":0.000002418587,"domain_scores_codex":[0.9992617,0.00001186854,0.0001537348,0.0001535991,0.0002777092,0.0001414182],"domain_scores_gemma":[0.9992626,0.00007774688,0.0002389045,0.0001892286,0.000161644,0.00006983548],"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":[0.000007349456,0.00003963506,0.0008419825,0.00007821299,0.000009959135,9.251723e-7,0.001281844,0.4341924,0.00003480272,0.3204256,0.001256176,0.2418311],"study_design_scores_gemma":[0.0002048101,0.0001312539,0.006492174,0.00002681107,0.000002911819,0.00003231605,0.00004605769,0.9808126,0.00001891107,0.01113601,0.0009889588,0.0001071616],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008164526,0.00004330667,0.990256,0.0009204172,0.00006484443,0.0002156462,0.00003411184,0.0001168436,0.0001843149],"genre_scores_gemma":[0.380805,0.000009115023,0.6190384,0.00003342523,0.0000153729,0.00002907211,0.00004646017,0.000001884911,0.00002127542],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5466202,"threshold_uncertainty_score":0.9997559,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0199954237668725,"score_gpt":0.2768263841359542,"score_spread":0.2568309603690817,"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."}}