{"id":"W2946709941","doi":"10.48550/arxiv.1905.10437","title":"N-BEATS: Neural basis expansion analysis for interpretable time series forecasting","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":160,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; McGill University","funders":"","keywords":"Computer science; Benchmark (surveying); Residual; Deep learning; Artificial intelligence; Univariate; Series (stratigraphy); Artificial neural network; Time series; Domain (mathematical analysis); Range (aeronautics); Machine learning; Architecture; Data mining; Algorithm; Multivariate statistics; Mathematics","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":[0.001052299,0.000769674,0.00058531,0.0006697477,0.0002155641,0.0007151456,0.0009533537,0.0007143731,0.003554294],"category_scores_gemma":[0.002230241,0.0002106447,0.0005308666,0.0007579546,0.0002774521,0.0008985958,0.0007844637,0.001643313,0.001290346],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003876989,"about_ca_system_score_gemma":0.0005725193,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003593263,"about_ca_topic_score_gemma":0.005003557,"domain_scores_codex":[0.9997265,0.00007672729,0.00001571518,0.00005871597,0.00009129309,0.00003110422],"domain_scores_gemma":[0.9996178,0.0001706046,0.00003358504,0.00007359332,0.00007425,0.00003007539],"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":[0.0003023142,0.0001483203,0.00221992,0.0001647617,0.0001491526,0.0001668513,0.00006967641,0.4760118,0.01157809,0.02520356,0.01956676,0.4644189],"study_design_scores_gemma":[0.000006244471,0.00001581662,0.0001967175,0.000006291994,0.000004447303,0.000009837975,0.000004843574,0.9918396,0.0009581615,0.005686434,0.001267297,0.000004175493],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04379901,0.001427841,0.9418527,0.0008173828,0.0003270437,0.00005922569,0.001018462,0.004628586,0.006069632],"genre_scores_gemma":[0.5943726,0.001075821,0.3887058,0.0003218643,0.0003254861,0.0001128451,0.00348235,0.0005035633,0.01109963],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003593263,"threshold_uncertainty_score":0.01189029,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2311203377402559,"score_gpt":0.2741654235903008,"score_spread":0.04304508585004496,"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."}}