{"id":"W2546896941","doi":"10.1109/ccece.2016.7726626","title":"Effective input features selection for electricity price forecasting","year":2016,"lang":"en","type":"article","venue":"","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Feature selection; Computer science; Selection (genetic algorithm); Mean absolute percentage error; Preprocessor; Data pre-processing; Artificial intelligence; Feature (linguistics); Data mining; Filter (signal processing); Machine learning; Electricity; Pattern recognition (psychology); Artificial neural network; Engineering","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":[0.0001364725,0.0001330193,0.0001165405,0.0000803763,0.000089229,0.00002090751,0.00006289582,0.0000811003,0.00002358105],"category_scores_gemma":[0.0001493691,0.0000892263,0.0000593575,0.000204664,0.000008784008,0.0001468027,0.00001028621,0.00007480633,0.000006630642],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009878253,"about_ca_system_score_gemma":0.000007973537,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001277967,"about_ca_topic_score_gemma":0.00004194791,"domain_scores_codex":[0.9993336,0.00001235564,0.0001163264,0.0001500543,0.00006972421,0.0003180068],"domain_scores_gemma":[0.9994054,0.0004066461,0.00002264355,0.00006242616,0.00005311496,0.00004976708],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00008164642,0.00002886078,0.004010746,0.0001941384,0.0001729507,0.000001345357,0.0002905243,0.01037746,0.2800113,0.007521905,0.01027932,0.6870298],"study_design_scores_gemma":[0.00122676,0.0003402913,0.003964166,0.0001756041,0.00003311282,0.00006463993,0.00001506133,0.1218546,0.8517869,0.001636021,0.01830471,0.000598149],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3495071,0.0001568474,0.6099869,0.00004739072,0.0004818819,0.0004008539,0.000005859244,0.0009596853,0.03845342],"genre_scores_gemma":[0.9938844,0.00001015725,0.004257283,0.00003027758,0.0003235725,0.00008972175,0.00000218514,0.00003387685,0.001368482],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6864316,"threshold_uncertainty_score":0.3638543,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008776482630540169,"score_gpt":0.2061775400065583,"score_spread":0.1974010573760181,"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."}}